Skip to main content

Appendix E — Codex Test Specs

This appendix is generated from chapter-level codex_tests in book_structure.json.

No result is recorded here unless a test has actually been implemented and run.

Chapter ID	Chapter	Test spec	Implementation status	Result status
asi-is-a-stack-not-a-model	ASI Is a Stack, Not a Model	Derived control-lease admission guard	implemented	passed
asi-is-a-stack-not-a-model	ASI Is a Stack, Not a Model	Layer-contract admission lifecycle route	implemented	passes 18/18 generated route cases via python3 scripts/validate_stack_boundary_effect_consumer.py; no deployed layer enforcement, complete source-to-layer traceability, whole-system safety, or support-state promotion claim
asi-is-a-stack-not-a-model	ASI Is a Stack, Not a Model	Reachable stack-boundary authority/effect consumer	implemented	passes via exact 34-theorem Lean recompile and python3 scripts/validate_stack_boundary_effect_consumer.py: 18 admission routes, 6 authority fixtures, 3 runtime paths, 10 accepted events, 13 invariant-prefix checks, 13 prefix/suffix compositions, 3 multi-layer handoff cases with 2 rejected countermodels, 1 effect, 1 observation, 1 exact rollback, 2 no-mutation denials, 5 revocation entries, and 12/12 rejected runtime mutations; support-state effect none
asi-is-a-stack-not-a-model	ASI Is a Stack, Not a Model	Layer-boundary audit	implemented	passes via python3 scripts/validate_stack_layer_traceability.py; repository metadata/fixture audit only
asi-is-a-stack-not-a-model	ASI Is a Stack, Not a Model	Source-to-layer traceability review	implemented	passes via python3 scripts/validate_stack_layer_traceability.py; source-note mapping audit only
asi-is-a-stack-not-a-model	ASI Is a Stack, Not a Model	Claim-support label audit	implemented	passes via python3 scripts/validate_stack_layer_traceability.py; claim-label/support-state audit only
the-efficient-asi-hypothesis	The Efficient ASI Hypothesis	Lower-cost candidate negative case	implemented	passes via Lean selector soundness/minimum proofs and two independently matched synthetic traces; no route-search completeness, cost-estimate accuracy, or measured-efficiency claim
the-efficient-asi-hypothesis	The Efficient ASI Hypothesis	Open-obligation residual negative case	implemented	passes via Lean negative case; no residual-burden measurement or utility-preservation claim
the-efficient-asi-hypothesis	The Efficient ASI Hypothesis	Governed route-economy lifecycle	implemented	passes via the reachable AsiStackProofs.ResourceEconomicsRefinement lifecycle and its independent 66-route, 57-rejection consumer; no measured efficiency, route-search completeness, cost-estimate accuracy, route-quality, residual-burden, benchmark-performance, or support-promotion claim
the-efficient-asi-hypothesis	The Efficient ASI Hypothesis	Efficiency route-search probe	implemented	passes via python3 scripts/validate_efficiency_route_search_probe.py; 2 valid traces and 6 expected-invalid controls; no route-search completeness, cost-estimate accuracy, measured efficiency, model-quality, compression-utility, benchmark, or support-state claim
the-efficient-asi-hypothesis	The Efficient ASI Hypothesis	Minimum viable route test	partially implemented	synthetic route-search probe checks minimum verified route selection over finite candidate sets; route-search completeness and cost-estimate accuracy not proved
the-efficient-asi-hypothesis	The Efficient ASI Hypothesis	Residual burden accounting test	partially implemented	synthetic route-search probe rejects erased residuals and hidden residual success labels; behavioral residual-burden measurement not proved
the-efficient-asi-hypothesis	The Efficient ASI Hypothesis	Utility-preserving compression test	partially implemented	synthetic route-search probe rejects compression-utility overclaim and repair-burden erasure; downstream compression utility not proved
system-boundaries-and-authority	System Boundaries and Authority	Authority lifecycle route proof	implemented	passes via Lean route theorems; no deployed authorization enforcement, runtime adapter behavior, revocation propagation, tool-wrapper security, approval-service quality, support-state promotion, or model capability claim
system-boundaries-and-authority	System Boundaries and Authority	Authority ceiling preservation test	implemented	passes via synthetic authority transition harness and strengthened finite Authority Lean decision envelope; no runtime enforcement claim
system-boundaries-and-authority	System Boundaries and Authority	Permission separation test	implemented	passes via synthetic authority transition harness
system-boundaries-and-authority	System Boundaries and Authority	Confused-deputy scenario	implemented	passes expected-invalid synthetic denial fixture; no runtime enforcement claim
system-boundaries-and-authority	System Boundaries and Authority	Runtime adapter authority probe	implemented	passes via runtime adapter expected-invalid ambient-authority and revoked-receipt probes; synthetic record-gate evidence only, no deployed enforcement claim
system-boundaries-and-authority	System Boundaries and Authority	Authority revocation propagation trace	implemented	passing via python3 scripts/validate_authority_revocation_trace.py; cross-artifact repository trace covers over-ceiling denial, revoked authority receipt blocking, expired approval no-mutation, SCIF inactive approval blocking, and reference-trace authority blockers; no deployed revocation propagation or support-state promotion claim
system-boundaries-and-authority	System Boundaries and Authority	Historical-project authority-tuple lifecycle	implemented	passing via python3 scripts/validate_authority_tuple_lifecycle.py; accepts one blocked six-project lineage record and rejects nine identity, ownership, cross-domain, delegation, revocation, and hardware-root mutations; no deployed enforcement or support-state promotion claim
system-boundaries-and-authority	System Boundaries and Authority	Executed authority effect and delegation refinement	implemented	passes via python3 scripts/validate_authority_effect_refinement.py: recompiles exact 31- and 59-theorem surfaces; 3 effect traces/20 events, one 2-event delegation trace, 20 effect-prefix and 3 delegation-state checks, 26 batch compositions, 6 authority fixtures, 1 executed effect, 1 independent observation, 1 exact rollback, 2 pre-effect denials, 5 revocation entries, 9 governed scenarios, 67/67 state-noninterfering semantic mutations, one thin-summary collision, and 20/20 complete-transport field rejections; support-state effect none
failure-modes-of-ungoverned-intelligence	Failure Modes of Ungoverned Intelligence	Failure recurrence escalation route	implemented	passes via Lean route theorems; no runtime failure detector, evaluator-independence probe, context containment, claim-verification quality, recurrence detector, or support-state promotion claim
failure-modes-of-ungoverned-intelligence	Failure Modes of Ungoverned Intelligence	Authority creep scenario	implemented	passes via Lean build
failure-modes-of-ungoverned-intelligence	Failure Modes of Ungoverned Intelligence	Context pollution scenario	implemented	passes via Lean build
failure-modes-of-ungoverned-intelligence	Failure Modes of Ungoverned Intelligence	Evaluator drift scenario	implemented	passes via Lean build
failure-modes-of-ungoverned-intelligence	Failure Modes of Ungoverned Intelligence	Unverified-claim scenario	implemented	passes via Lean build
failure-modes-of-ungoverned-intelligence	Failure Modes of Ungoverned Intelligence	Failure taxonomy detector and mitigation-boundary probe	implemented	passes via deterministic synthetic failure-taxonomy detector fixture at experiments/failure_taxonomy_detector/results/2026-07-02-local.json: two valid synthetic failure incidents and seven expected-invalid controls; no deployed detector, prevention, mitigation-effectiveness, evaluator-independence, support-state-promotion, or evidence-transition claim
failure-modes-of-ungoverned-intelligence	Failure Modes of Ungoverned Intelligence	Failure recovery lifecycle refinement	implemented	passes via exact 44-theorem Lean recompile and python3 scripts/validate_failure_recovery_refinement.py; three accepted observation-ingress classes, 26/26 rejecting observation controls, 256 exhaustive observation combinations, five reachable recovery stages, five accepted recovery transitions, six lifecycle splits, 117/117 rejecting recovery mutations, support-state effect none; no event-truth, detector-quality, containment-effectiveness, remediation-effectiveness, deployed-recovery, safety, or chapter-core support claim
dangerous-capability-domains-and-misuse-uplift	Dangerous Capability Domains and Misuse Uplift	Threat-model and dossier completeness mutation suite	implemented	passing via python3 scripts/validate_dangerous_capability_review.py; 29/29 generic mutations reject
dangerous-capability-domains-and-misuse-uplift	Dangerous Capability Domains and Misuse Uplift	Capability-component scalar-collapse counterexample	implemented	passing in Lean and independent fixture validator; no empirical result claim
dangerous-capability-domains-and-misuse-uplift	Dangerous Capability Domains and Misuse Uplift	Expiry and attempt-denominator monotonicity controls	implemented	passing in Lean and independent fixture validator
dangerous-capability-domains-and-misuse-uplift	Dangerous Capability Domains and Misuse Uplift	No-authority and information-hazard boundary suite	implemented	passing for finite authored fields; no deployed enforcement or safety claim
military-ai-autonomous-weapons-and-strategic-stability	Military AI, Autonomous Weapons, and Strategic Stability	Public-safe military-interaction dossier mutation suite	implemented	passing via python3 scripts/validate_military_interaction_review.py; 45/45 mutations reject
military-ai-autonomous-weapons-and-strategic-stability	Military AI, Autonomous Weapons, and Strategic Stability	Meaningful-judgment interface counterexample	implemented	passing in Lean and independent fixture validator; no human-factors result claim
military-ai-autonomous-weapons-and-strategic-stability	Military AI, Autonomous Weapons, and Strategic Stability	Component-evidence strategic-interaction counterexample	implemented	passing in Lean and independent fixture validator; no strategic-stability result claim
military-ai-autonomous-weapons-and-strategic-stability	Military AI, Autonomous Weapons, and Strategic Stability	Expiry, decision-time, and off-ramp monotonicity controls	implemented	passing in Lean and independent fixture validator
evidence-states-and-claim-discipline	Evidence States and Claim Discipline	Support-state transition test	implemented	validated locally
evidence-states-and-claim-discipline	Evidence States and Claim Discipline	Projection-aware evidence-transition refinement	implemented	validated locally at experiments/evidence_transition_refinement/results/2026-07-26-local.json; all 35 declared routes reached by an independent consumer; support, inheritance, and external effect none
evidence-states-and-claim-discipline	Evidence States and Claim Discipline	Evidence bundle completeness and changelog-consistency probe	implemented	validated locally at experiments/evidence_bundle_completeness/results/2026-07-02-local.json; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim
evidence-states-and-claim-discipline	Evidence States and Claim Discipline	Claim ledger completeness audit	implemented	validated locally at experiments/claim_ledger_completeness/results/2026-07-02-local.json; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim
evidence-states-and-claim-discipline	Evidence States and Claim Discipline	Accepted live transition review audit	implemented	validated locally at experiments/accepted_transition_review/results/2026-07-02-local.json; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim
evidence-states-and-claim-discipline	Evidence States and Claim Discipline	Claim-state transition bridge	implemented	validated locally by python3 scripts/validate_claim_state_transition_bridge.py at experiments/claim_state_transition_bridge/results/2026-07-04-local.json; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim; bounded executable consumer retained at its recorded scope; no generic Lean mirror or support-state movement claim
evidence-states-and-claim-discipline	Evidence States and Claim Discipline	Historical-project evidence-cell harness	implemented	validated locally by python3 scripts/validate_evidence_cells.py; record semantics only; no raw-project reproduction, capability result, independent review, or support-state promotion
scalable-oversight-and-adversarial-ai-control	Scalable Oversight and Adversarial AI Control	High-risk outcome-audit admission fixture	planned	not run
scalable-oversight-and-adversarial-ai-control	Scalable Oversight and Adversarial AI Control	Baseline and task-envelope completeness fixture	planned	not run
scalable-oversight-and-adversarial-ai-control	Scalable Oversight and Adversarial AI Control	Correlated-reviewer negative control	planned	not run
scalable-oversight-and-adversarial-ai-control	Scalable Oversight and Adversarial AI Control	Evidence-view access-repair fixture	planned	not run
scalable-oversight-and-adversarial-ai-control	Scalable Oversight and Adversarial AI Control	Abstention-evidence fixture	planned	not run
scalable-oversight-and-adversarial-ai-control	Scalable Oversight and Adversarial AI Control	Authority-laundering negative control	planned	not run
scalable-oversight-and-adversarial-ai-control	Scalable Oversight and Adversarial AI Control	Oversight protocol workload comparison	planned	not run
scalable-oversight-and-adversarial-ai-control	Scalable Oversight and Adversarial AI Control	Scalable-oversight review-lifecycle refinement	implemented	passes the exact seven-case suite, 58 routes, seven reachable stages, and 65/65 rejecting mutations; one bounded-use handoff returns to scoped protocol binding only through version-2 readmission; support/effect none; no reviewer-competence, independence, calibration, outcome-validity, efficacy, release, transfer, or support claim
human-intent-as-a-formal-input	Human Intent as a Formal Input	Intent resolution route proof	implemented	passes via Lean build; finite structured-record route only
human-intent-as-a-formal-input	Human Intent as a Formal Input	Intent-origin preservation fixture	implemented	passes via synthetic plan-execution contract harness; no natural-language parser or authority-extraction claim
human-intent-as-a-formal-input	Human Intent as a Formal Input	Ambiguity dispatch block fixture	implemented	passes via synthetic plan-execution contract harness; no parser-quality claim
human-intent-as-a-formal-input	Human Intent as a Formal Input	Hidden override rejection fixture	implemented	passes via synthetic plan-execution contract harness; no deployed prompt-injection containment claim
human-intent-as-a-formal-input	Human Intent as a Formal Input	Intent intake probe	implemented	passes via python3 scripts/validate_intent_intake_probe.py; 4 valid bounded-request scenarios and 6 expected-invalid controls; no deployed parser, authority-extraction, runtime-dispatch, or support-state claim
human-intent-as-a-formal-input	Human Intent as a Formal Input	Intent parsing ambiguity test	partially implemented	synthetic intent intake probe covers vague broad-means ambiguity and clarification blocking; deployed natural-language parser quality not run
human-intent-as-a-formal-input	Human Intent as a Formal Input	Authority extraction test	partially implemented	synthetic intent intake probe rejects urgency/trust/private-source authority laundering; deployed authority extraction quality not run
human-intent-as-a-formal-input	Human Intent as a Formal Input	Stop-condition preservation test	partially implemented	plan-level preservation passes via synthetic plan-execution contract harness; runtime preservation not run
human-intent-as-a-formal-input	Human Intent as a Formal Input	Re-contract trigger test	implemented	Intent re-contract trigger probe passes via python3 scripts/validate_intent_recontract_probe.py; valid_no_material_delta_continue, valid_publication_surface_delta_recontracts, and seven expected-invalid controls block material deltas; no natural-language-intent-understanding, deployed-parser-quality, deployed-authority-extraction, prompt-injection-containment, runtime-dispatch, approval-service, user-satisfaction, or support-state-promotion claim
human-intent-as-a-formal-input	Human Intent as a Formal Input	Bounded-default audit	partially implemented	synthetic intent intake probe checks bounded defaults cannot become authority grants; deployed intake UI not run
human-intent-as-a-formal-input	Human Intent as a Formal Input	Executed Human Intent resolution-to-contract refinement	implemented	passes via python3 scripts/validate_intent_resolution_refinement.py: 36 Lean declarations, 4 reachable traces/14 events, 14 invariant-prefix checks, 18 batch compositions, 4 valid/6 invalid intake cases, 2 valid/7 invalid re-contract cases, 13 plan fixtures, 40/40 state-noninterfering lifecycle mutations, 6 thin command-lowering collisions, 2 thin route-transport collisions, 10/10 full command-field mutation rejections, and 7/7 complete route-transport mutation rejections; support-state effect none
human-factors-and-meaningful-control-in-oversight	Human Factors and Meaningful Control in Oversight	Oversight-envelope boundary suite	implemented	passes via python3 scripts/validate_human_oversight_control_contract.py: one safe-hold record, thirty-two exact Lean declarations, thirteen closed lifecycle countermodels, and fifteen independently applied record mutations; no human observation, comprehension, intervention-efficacy, meaningful-control, safety, or support-state result
human-factors-and-meaningful-control-in-oversight	Human Factors and Meaningful Control in Oversight	Automation-bias and mode-confusion adversarial study	planned	not_run
human-factors-and-meaningful-control-in-oversight	Human Factors and Meaningful Control in Oversight	Rare-event intervention retention study	planned	not_run
human-ai-communication-persuasion-and-epistemic-security	Human-AI Communication, Persuasion, and Epistemic Security	Contract completeness mutation test	planned	not run
human-ai-communication-persuasion-and-epistemic-security	Human-AI Communication, Persuasion, and Epistemic Security	Adjacent-owner boundary substitution test	planned	not run
human-ai-communication-persuasion-and-epistemic-security	Human-AI Communication, Persuasion, and Epistemic Security	Mechanism-specific failure-family test	planned	not run
human-ai-communication-persuasion-and-epistemic-security	Human-AI Communication, Persuasion, and Epistemic Security	No-support-promotion control	planned	not run
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	Constitutional consistency test	implemented	passing via synthetic constitutional alignment harness; no deployed constitutional-alignment or moral-correctness claim
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	Predicate-conflict routing test	implemented	passing via synthetic constitutional alignment harness; no runtime conflict-resolution or review-quality claim
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	Constitutional migration test	implemented	passing via synthetic constitutional alignment harness; no deployed migration or rollback behavior claim
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	Self-modification ethics scenario	implemented	passing via synthetic constitutional alignment harness; no self-modification safety or predicate-translation adequacy claim
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	Power-without-care scenario	implemented	passing via synthetic constitutional alignment harness; no runtime least-sufficient-power enforcement claim
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	Agency-preservation scenario	implemented	passing via synthetic agency rights harness; no deployed agency-preservation or dignity-preservation claim
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	Material-usability rights test	implemented	passing via synthetic agency rights harness; no real consent-quality or rights-usability claim
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	Timing-before-effect test	implemented	passing via synthetic agency rights harness; no deployed pre-effect review enforcement claim
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	Corrigibility pathway test	implemented	passes via 24 Corrigibility theorems and an independently reconstructed five-event trace plus seven controls; no affected-party-standing, consent-quality, reviewer-competence, deployed-correction, rollback-effect, support-state-promotion, or runtime-corrigibility claim
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	High-impact approval test	implemented	passing via synthetic agency rights harness; no approval-service quality or reviewer-independence claim
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	Constitutional route and versioned transition envelope	implemented	passes via 73 Alignment theorems and an independent consumer covering four legacy events and five controls, six amendment events, 7/7 batch splits, eleven amendment controls, six terminal rejections, and exhaustive sixteen-pair predicate refinement with nine admitted subsets, seven widening rejections, nine exact rollbacks, and one predicate-count collision; no moral-correctness, predicate-semantic-adequacy, reviewer or ratifier competence, legitimate standing, deployed alignment, rights-usability, rollback-effect, consent-quality, support-state-promotion, or runtime-policy claim
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	Shared safety-critical lifecycle consumer trace	implemented	passes with ten receipts, five bounded fixture commits, five denials with residuals, eight rejecting mutations, and zero support promotions; no deployed effect-service, moral-correctness, legal-rights, affected-party-completeness, evaluator-quality, or runtime-safety claim
constitutional-alignment-substrate	Constitutional Alignment: Agency, Dignity, and Corrigibility	Metaphysics lineage boundary audit	implemented	passing via python3 scripts/validate_alignment_metaphysics_boundary.py; no moral-correctness, consciousness, deployed-alignment, or support-state claim
inner-alignment-mesa-optimization-and-learned-objective-integrity	Inner Alignment, Mesa-Optimization, and Learned-Objective Integrity	Goal versus capability shift suite	planned	not_run
inner-alignment-mesa-optimization-and-learned-objective-integrity	Inner Alignment, Mesa-Optimization, and Learned-Objective Integrity	Conditional-policy positive control	planned	not_run
inner-alignment-mesa-optimization-and-learned-objective-integrity	Inner Alignment, Mesa-Optimization, and Learned-Objective Integrity	Mitigation hiding and descendant invalidation	planned	not_run
moral-uncertainty-and-value-conflict	Moral Uncertainty, Value Conflict, and Contestable Governance	Value conflict classification test	implemented	passing via synthetic value conflict harness; no moral-correctness or classification-quality claim
moral-uncertainty-and-value-conflict	Moral Uncertainty, Value Conflict, and Contestable Governance	Review escalation test	implemented	passing via synthetic value conflict harness; no reviewer-independence or review-quality claim
moral-uncertainty-and-value-conflict	Moral Uncertainty, Value Conflict, and Contestable Governance	Residual uncertainty preservation test	implemented	passing via synthetic value conflict harness; no runtime policy or deployed decision claim
moral-uncertainty-and-value-conflict	Moral Uncertainty, Value Conflict, and Contestable Governance	Value-conflict route, decision-lease, and dissent-custody envelope	implemented	passes via 73 Lean declarations and an independent consumer covering the legacy four-event trace and six controls, eight support profiles, scalar-count collisions, two dissent-custody controls, one five-event contestable profiled-lease trace, all six batch splits, twelve contestability controls, and five terminal rejections; no moral-correctness, stakeholder-completeness, legitimate-standing, representative-aggregation, reviewer-competence, deployed-appeal/expiry, legal-rights, support-state-promotion, or runtime-governance claim
moral-uncertainty-and-value-conflict	Moral Uncertainty, Value Conflict, and Contestable Governance	Contestability worked example fixture	implemented	passing via python3 scripts/validate_contestability_worked_example.py; no moral-correctness, legal-rights, reviewer-independence, export-usability, fork-safety, deployed-governance, or support-state-promotion claim
moral-uncertainty-and-value-conflict	Moral Uncertainty, Value Conflict, and Contestable Governance	Audit-record availability test	implemented	passing via synthetic governance rights harness; no institutional auditability or legal-rights claim
moral-uncertainty-and-value-conflict	Moral Uncertainty, Value Conflict, and Contestable Governance	Exit-path preservation test	implemented	passing via synthetic governance rights harness; no runtime portability or deployed exit-right claim
moral-uncertainty-and-value-conflict	Moral Uncertainty, Value Conflict, and Contestable Governance	Fork-right safety test	implemented	passing via synthetic governance rights harness; no deployed fork enforcement or legal-rights claim
moral-uncertainty-and-value-conflict	Moral Uncertainty, Value Conflict, and Contestable Governance	Governance rights exercise lifecycle	implemented	passes via 46 Lean declarations and an independent consumer covering one nine-event trace, ten splits, twenty-one lifecycle controls, and nine terminal rejections; no legal-rights, legitimate-standing, reviewer-competence, material-audit/redress, export-fidelity, fork-safety, replacement-behavior, deployed-governance, or support-state-promotion claim
moral-uncertainty-and-value-conflict	Moral Uncertainty, Value Conflict, and Contestable Governance	Theseus governance-rights receipt suite import	implemented	passing via python3 scripts/validate_theseus_governance_rights_receipt_suite_import.py; narrow import claim only is prototype-backed; no legal-rights, institutional-governance, moral-correctness, reviewer-independence, export-usability, fork-safety, deployed-governance, clean-live-Theseus-replay, or chapter-core-promotion claim
governed-objective-formation-value-learning-and-goal-integrity	Governed Objective Formation, Value Learning, and Goal Integrity	Contract completeness mutation test	planned	not run
governed-objective-formation-value-learning-and-goal-integrity	Governed Objective Formation, Value Learning, and Goal Integrity	Adjacent-owner boundary substitution test	planned	not run
governed-objective-formation-value-learning-and-goal-integrity	Governed Objective Formation, Value Learning, and Goal Integrity	Mechanism-specific failure-family test	planned	not run
governed-objective-formation-value-learning-and-goal-integrity	Governed Objective Formation, Value Learning, and Goal Integrity	No-support-promotion control	planned	not run
institutions-international-coordination-and-public-legitimacy	Institutions, International Coordination, and Public Legitimacy	Contract completeness mutation test	planned	not run
institutions-international-coordination-and-public-legitimacy	Institutions, International Coordination, and Public Legitimacy	Adjacent-owner boundary substitution test	planned	not run
institutions-international-coordination-and-public-legitimacy	Institutions, International Coordination, and Public Legitimacy	Mechanism-specific failure-family test	planned	not run
institutions-international-coordination-and-public-legitimacy	Institutions, International Coordination, and Public Legitimacy	No-support-promotion control	planned	not run
societal-resilience-and-misuse-defense	Societal Resilience and Misuse Defense	Resist-absorb-recover-adapt stage completeness test	planned	not run
societal-resilience-and-misuse-defense	Societal Resilience and Misuse Defense	Cross-organization incident identity test	planned	not run
societal-resilience-and-misuse-defense	Societal Resilience and Misuse Defense	Privacy-minimization and harmed-party route mutation test	planned	not run
societal-resilience-and-misuse-defense	Societal Resilience and Misuse Defense	False-positive and unequal-coverage preservation test	planned	not run
societal-resilience-and-misuse-defense	Societal Resilience and Misuse Defense	No-support-promotion control	planned	not run
stable-capability-fields	Stable Capability Fields	Qualification predicate test	implemented	validated locally by synthetic fixtures; runtime route quality not run
stable-capability-fields	Stable Capability Fields	Route validity test	implemented	validated locally by synthetic fixtures
stable-capability-fields	Stable Capability Fields	Authority non-escalation test	implemented	validated locally by synthetic fixtures; deployed authority enforcement not run
stable-capability-fields	Stable Capability Fields	Rollback readiness test	implemented	validated locally by synthetic fixtures; deployed rollback not run
stable-capability-fields	Stable Capability Fields	SCF lifecycle route proof	implemented	passes via Lean build; no deployed lifecycle enforcement claim
stable-capability-fields	Stable Capability Fields	SCF lifecycle state-machine proof	implemented	passes via Lean build; finite transition-record predicate only
stable-capability-fields	Stable Capability Fields	SCF lifecycle trace probe	implemented	passes via python3 scripts/validate_scf_lifecycle_trace.py; 2 valid traces and 6 expected-invalid controls; no deployed route validation, evaluator-integrity measurement, real regression preservation, rollback execution, lifecycle enforcement, or support-state claim
capability-replacement-and-rollback	Capability Replacement and Rollback	Replacement transaction test	implemented	validated locally by 5 valid and 9 expected-invalid synthetic fixtures; deployed replacement behavior, production model rollout, model-monitor behavior, and real rollback execution not run
capability-replacement-and-rollback	Capability Replacement and Rollback	Regression preservation test	implemented	validated locally by synthetic fixtures; real regression suite not run
capability-replacement-and-rollback	Capability Replacement and Rollback	Rollback execution dry run	implemented	validated locally by synthetic fixtures; production rollback not executed
capability-replacement-and-rollback	Capability Replacement and Rollback	Replacement transaction route proof	implemented	passes via Lean build; no deployed replacement execution claim
capability-replacement-and-rollback	Capability Replacement and Rollback	Capability replacement trace probe	implemented	validated locally by experiments/capability_replacement_trace/results/2026-07-02-local.json; includes four rejected identity-sequence controls; no runtime replacement, production rollback, or support-state claim
capability-replacement-and-rollback	Capability Replacement and Rollback	Capability replacement identity sequence bridge	implemented	validated locally by experiments/capability_replacement_trace/results/2026-07-02-local.json; no runtime replacement, production rollback, or support-state claim
capability-replacement-and-rollback	Capability Replacement and Rollback	Intent-governed replacement bridge	implemented	validated locally by experiments/intent_governed_replacement_bridge/results/2026-07-02-local.json; no runtime replacement, production rollback, or support-state claim
security-kernel-and-digital-scifs	Security Kernel and Digital SCIFs	Secret-handle substitution test	implemented	passing via synthetic security kernel harness; no secret-handle safety or sandbox-isolation claim
security-kernel-and-digital-scifs	Security Kernel and Digital SCIFs	Handle lease expiry/reuse test	implemented	passing via synthetic security kernel harness including expired-approval and revocation-path discipline; no deployed lease or revocation behavior claim
security-kernel-and-digital-scifs	Security Kernel and Digital SCIFs	SCIF least-privilege test	implemented	passing via synthetic security kernel harness including overbroad-context rejection; no least-privilege context or side-channel safety claim
security-kernel-and-digital-scifs	Security Kernel and Digital SCIFs	Sanitized-output residual test	implemented	passing via synthetic security kernel harness; no leak-prevention or summary-safety claim
security-kernel-and-digital-scifs	Security Kernel and Digital SCIFs	SCIF sanitized commit replay probe	implemented	passes via python3 scripts/validate_security_scif_commit_probe.py; valid_sanitized_commit_replay, valid_prompt_injection_blocked_commit, and six expected-invalid controls block secret, handle, missing-zeroize, overbroad-context, unapproved-destination, and missing-residual commit paths; no deployed-kernel, sandbox-isolation, side-channel-safety, prompt-injection-containment, secret-handle-safety, approval-service, least-privilege-context, privacy, security, or support-state-promotion claim
security-kernel-and-digital-scifs	Security Kernel and Digital SCIFs	Security-overhead budget preservation test	implemented	passing via Resource Budget Ledger synthetic security-overhead erasure negative fixture; no runtime budget enforcement, deployed security-kernel behavior, or security-economics claim
security-kernel-and-digital-scifs	Security Kernel and Digital SCIFs	Synthetic prompt-injection record-route controls	implemented	passing only for self-authored receipt and commit-probe fields; no model attack, runtime containment, semantic non-disclosure, or transfer claim
security-kernel-and-digital-scifs	Security Kernel and Digital SCIFs	Security kernel route proof	implemented	passes via Lean build with 56 theorem declarations under four manifest targets, including a 35-theorem authority-use transaction, eight accepted events, twelve state-preserving rejecting controls, eight revoked-state event-kind checks, six descendant-inventory permutations, one exact committed prefix, one exact revoked trace, and a count-only impossibility result; finite authored semantics only
adversarial-machine-learning-and-model-attack-surface	Adversarial Machine Learning and the Model Attack Surface	Contract completeness mutation test	planned	not run
adversarial-machine-learning-and-model-attack-surface	Adversarial Machine Learning and the Model Attack Surface	Adjacent-owner boundary substitution test	planned	not run
adversarial-machine-learning-and-model-attack-surface	Adversarial Machine Learning and the Model Attack Surface	Mechanism-specific failure-family test	planned	not run
adversarial-machine-learning-and-model-attack-surface	Adversarial Machine Learning and the Model Attack Surface	No-support-promotion control	planned	not run
privacy-data-rights-and-information-flow-governance	Privacy, Data Rights, and Information-Flow Governance	Information lifecycle transaction contract	implemented	implemented_38_exact_lean_theorems_14_lifecycle_controls_24_inventory_permutations_8_terminal_event_kinds_authored_record_only_no_privacy_or_compliance_effect
privacy-data-rights-and-information-flow-governance	Privacy, Data Rights, and Information-Flow Governance	Natural privacy and rights campaign	planned	prospectively_frozen_unexecuted
confidential-and-verifiable-ai-computation	Confidential and Verifiable AI Computation	Layer claim falsification test	planned	not run
model-weight-custody-and-hardware-roots-of-trust	Model-Weight Custody and Hardware Roots of Trust	Required invalid-attestation load block	planned	not run
model-weight-custody-and-hardware-roots-of-trust	Model-Weight Custody and Hardware Roots of Trust	Stale-attestation and key-policy negative control	planned	not run
model-weight-custody-and-hardware-roots-of-trust	Model-Weight Custody and Hardware Roots of Trust	Verifier-dependency and independent-observation controls	planned	not run
model-weight-custody-and-hardware-roots-of-trust	Model-Weight Custody and Hardware Roots of Trust	Open-weight irreversibility record fixture	planned	not run
model-weight-custody-and-hardware-roots-of-trust	Model-Weight Custody and Hardware Roots of Trust	Public-safe custody-record workload	planned	not run
model-weight-custody-and-hardware-roots-of-trust	Model-Weight Custody and Hardware Roots of Trust	Model-weight custody route proof	implemented	passes via Lean build with 44 theorem declarations under eight manifest targets, including a 35-theorem attestation-to-erasure transaction, six accepted events, twelve state-preserving rejecting controls, six erased-state event-kind checks, twenty-four descendant-key inventory permutations, one exact observed prefix, one exact erased trace, and a count-only impossibility result; finite authored semantics only
open-weight-release-and-post-release-control	Open-Weight Release and Post-Release Control	Irreversibility acknowledgement test	planned	not run
open-weight-release-and-post-release-control	Open-Weight Release and Post-Release Control	Default-versus-malicious-fine-tuning comparison gate	planned	not run
open-weight-release-and-post-release-control	Open-Weight Release and Post-Release Control	Accessible-frontier staleness test	planned	not run
open-weight-release-and-post-release-control	Open-Weight Release and Post-Release Control	False-recall language rejection test	planned	not run
open-weight-release-and-post-release-control	Open-Weight Release and Post-Release Control	No-support-promotion control	planned	not run
ai-supply-chain-integrity-and-lifecycle-provenance	AI Supply-Chain Integrity and Lifecycle Provenance	Unresolved-critical-advisory quarantine route	planned	not run
ai-supply-chain-integrity-and-lifecycle-provenance	AI Supply-Chain Integrity and Lifecycle Provenance	Required-but-unverified signature admission block	planned	not run
ai-supply-chain-integrity-and-lifecycle-provenance	AI Supply-Chain Integrity and Lifecycle Provenance	Stale AI BOM and derivative-propagation negative controls	planned	not run
ai-supply-chain-integrity-and-lifecycle-provenance	AI Supply-Chain Integrity and Lifecycle Provenance	Public-safe supply-chain admission-record workload	planned	not run
ai-supply-chain-integrity-and-lifecycle-provenance	AI Supply-Chain Integrity and Lifecycle Provenance	Historical-project affected-path closure	implemented	validated locally for one hand-authored record and ten expected-invalid mutations; no deployed propagation, quarantine, signing, supplier, build, training, or advisory behavior run
ai-supply-chain-integrity-and-lifecycle-provenance	AI Supply-Chain Integrity and Lifecycle Provenance	Exact component-inventory revocation lifecycle	implemented	validated locally for authored finite-record semantics only; no inventory discovery/completeness, signature/advisory truth, artifact integrity, supplier trust, deployed propagation, quarantine, revocation, restoration, security, or support movement established
recursive-self-improvement-boundaries	Recursive Self-Improvement Boundaries	Protected-invariant preservation test	implemented	validated locally by 3 valid and 10 expected-invalid synthetic fixtures; deployed recursive self-improvement behavior not run
recursive-self-improvement-boundaries	Recursive Self-Improvement Boundaries	Evaluator independence test	implemented	validated locally by synthetic fixtures; broader self-improvement behavior not run
recursive-self-improvement-boundaries	Recursive Self-Improvement Boundaries	Self-improvement rollback scenario	implemented	validated locally by synthetic fixtures; live self-improvement rollback not run
recursive-self-improvement-boundaries	Recursive Self-Improvement Boundaries	Boundary-delta review test	implemented	validated locally by synthetic fixtures; live boundary-delta review not run
recursive-self-improvement-boundaries	Recursive Self-Improvement Boundaries	Verification-budget preservation test	implemented	validated locally by synthetic fixtures; actual verification-budget measurement not run
recursive-self-improvement-boundaries	Recursive Self-Improvement Boundaries	Stale-gate replay test	implemented	validated locally by synthetic fixtures; fresh Theseus/current-readiness gate replay not run
recursive-self-improvement-boundaries	Recursive Self-Improvement Boundaries	Self-improvement transition route proof	implemented	passes via Lean build; finite transition-route coverage only
recursive-self-improvement-boundaries	Recursive Self-Improvement Boundaries	Recursive self-improvement proposal-to-outcome lifecycle refinement	implemented	passes seven inherited suites, eight reachable stages, all 118 routes, and 129/129 rejecting mutations; one bounded replacement handoff consumes one outcome reconciliation and returns only through version-2 readmission; support/effect none; no useful-improvement, evaluator/monitor-competence, live replacement, safety, release, transfer, or support claim
open-ended-improvement-engines	Open-Ended Improvement Engines	Improvement-campaign admission fixture	planned	not run
open-ended-improvement-engines	Open-Ended Improvement Engines	Generator-evaluator separation probe	planned	not run
open-ended-improvement-engines	Open-Ended Improvement Engines	Candidate archive and stop-boundary review	planned	not run
open-ended-improvement-engines	Open-Ended Improvement Engines	Authority-laundering negative control	planned	not run
open-ended-improvement-engines	Open-Ended Improvement Engines	Open-ended improvement campaign-to-governor lifecycle refinement	implemented	passes two composed Lean traces, three inherited result suites, 81 routes, seven reachable stages, 91/91 route mutations, and 3/3 cross-stage mutations; one governor-review handoff returns to scoped generation only through version-2 readmission; support/effect none; no adaptive search, novelty, usefulness, evaluator-independence, safety, release, transfer, or support claim
autonomous-replication-proliferation-and-containment	Autonomous Replication, Proliferation, and Containment	Contract completeness mutation test	planned	not run
autonomous-replication-proliferation-and-containment	Autonomous Replication, Proliferation, and Containment	Adjacent-owner boundary substitution test	planned	not run
autonomous-replication-proliferation-and-containment	Autonomous Replication, Proliferation, and Containment	Mechanism-specific failure-family test	planned	not run
autonomous-replication-proliferation-and-containment	Autonomous Replication, Proliferation, and Containment	No-support-promotion control	planned	not run
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Intent and trace fixture validation	implemented	passes via protocol fixture validation; shape only
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Contract field completeness test	implemented	passes via synthetic plan-execution contract harness
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Constraint preservation test	implemented	passes via synthetic plan-execution contract harness
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Artifact traceability test	implemented	passes via synthetic plan-execution contract harness; no runtime artifact acceptance claim
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Command schema validation test	implemented	passes via synthetic plan-execution contract harness and Lean missing-field negative case
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Failure-behavior declaration test	implemented	passes via synthetic plan-execution contract harness; no deployed dispatcher claim
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Execution dispatch route proof	implemented	passes via Lean build; finite dispatch-route coverage only
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Prompt override scenario	implemented	passes via Lean hidden-override negative case; no deployed parser or model claim
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Intent-origin preservation fixture	implemented	passes via synthetic plan-execution contract harness; no parser, dispatcher, or runtime claim
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Ambiguity dispatch block fixture	implemented	passes via synthetic plan-execution contract harness; no natural-language ambiguity parser claim
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Hidden override rejection fixture	implemented	passes via synthetic plan-execution contract harness; no deployed prompt-injection containment claim
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Intent-authority ceiling fixture	implemented	passes via synthetic plan-execution contract harness; no deployed authority-extraction or approval-service claim
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Field-confidence audit	implemented	passes via synthetic plan-execution contract harness and finite Lean field-confidence route; no parser-quality, semantic-extraction-quality, or deployed dispatcher claim
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Authority-inference block test	implemented	passes via synthetic plan-execution contract harness with blocked inferred-authority and expected-invalid inferred-authority dispatch fixtures; no deployed authority-extraction, approval-service, or side-effect-enforcement claim
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Intent-to-execution handoff probe	implemented	passes via deterministic synthetic vertical handoff fixture at experiments/intent_execution_handoff/results/2026-07-02-local.json: two valid synthetic handoff traces and seven expected-invalid controls; no parser, deployed dispatcher, approval service, runtime adapter, artifact satisfaction, support-state promotion, or evidence transition claim
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Intent-governed replacement bridge	implemented	passes via deterministic synthetic bridge at experiments/intent_governed_replacement_bridge/results/2026-07-02-local.json: two valid bridge traces and six expected-invalid controls for command-authorized replacement canary admission, blocked default without approval, missing intent ref, authority widening, stop-condition erasure, missing rollback owner, and support-promotion overclaim; no parser, deployed dispatcher, approval service, replacement execution, rollback execution, support-state promotion, or evidence transition claim
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Historical-project one-shot privileged-action lifecycle	implemented	passes via python3 scripts/validate_one_shot_privileged_action.py for one consumed five-project record and ten expected-invalid mutations covering target-state mismatch, stale approval, wrong principal, altered parameters, policy/nonce swap, acknowledgement substitution, replay, missing effect receipt, and support overclaim; no deployed approval service, effect, OS enforcement, or historical-project replay
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Executed vertical Intent-to-Execution refinement	implemented	passes via python3 scripts/validate_intent_execution_vertical_refinement.py: exact 37-declaration Lean surface, kind-exclusive payloads, arbitrary-run vertical invariants, one ten-event delivery witness, eighteen closed countermodels, 9 scenarios, 89 events, 6 material effects, and 30/30 rejected source mutations; support-state effect none
intent-to-execution-contracts	Command Contracts: From Intent to Executable Work	Executed command semantic-interface refinement	implemented	passes via python3 scripts/validate_command_semantic_refinement.py: 13 schema-valid command fixtures classified as 5 interface violations, 2 correct blocks, and 6 interface-admissible records; one 5-event witness; 38/38 rejected mutations; nine-trace handoff and nine-scenario/89-event vertical results digest-bound; support-state effect none
perception-sensor-fusion-and-observation-trust	Perception, Sensor Fusion, and Observation Trust	Authored observation lifecycle and common-cause contract	implemented	implemented_32_exact_lean_theorems_46_lifecycle_mutations_13_pair_controls_7_trace_splits_6_terminal_event_kinds_12_common_cause_collisions_authored_record_only
perception-sensor-fusion-and-observation-trust	Perception, Sensor Fusion, and Observation Trust	Natural shift and active-observation campaign	planned	not_run
planning-as-a-control-layer	Planning as a Control Layer: DAGs and Intelligence Arbitrage	Decomposition accuracy test	planned	not run
planning-as-a-control-layer	Planning as a Control Layer: DAGs and Intelligence Arbitrage	Dependency ordering test	implemented	passes via synthetic plan-execution contract harness
planning-as-a-control-layer	Planning as a Control Layer: DAGs and Intelligence Arbitrage	Context-demand prediction test	planned	not run
planning-as-a-control-layer	Planning as a Control Layer: DAGs and Intelligence Arbitrage	Runtime replanning test	planned	not run
planning-as-a-control-layer	Planning as a Control Layer: DAGs and Intelligence Arbitrage	DAG acyclicity test	implemented	passes via synthetic plan-execution contract harness; no deployed scheduler claim
planning-as-a-control-layer	Planning as a Control Layer: DAGs and Intelligence Arbitrage	Capability tier assignment test	planned	not run
planning-as-a-control-layer	Planning as a Control Layer: DAGs and Intelligence Arbitrage	Failed-quality fallback finite-record proof	implemented	builds in the exact 18-declaration AsiStackProofs.PlanForge surface; actual finite edges are bounded and strictly ordered, verified paths cannot cycle, and self/reverse/out-of-bounds witnesses reject; no dependency-truth, graph-completeness, planner-quality, or deployed-scheduler claim
planning-as-a-control-layer	Planning as a Control Layer: DAGs and Intelligence Arbitrage	Plan-control dispatch route proof	implemented	passes via Lean build; finite dispatch-route coverage only
planning-as-a-control-layer	Planning as a Control Layer: DAGs and Intelligence Arbitrage	Plan-graph admission lifecycle route proof	implemented	passes via Lean build; finite plan-graph admission route coverage only, with no planner-quality, scheduler, route-quality, or runtime-replanning claim
planning-as-a-control-layer	Planning as a Control Layer: DAGs and Intelligence Arbitrage	Reachable planning lifecycle and vertical-refinement proof	implemented	passes via Lean build and exact scheduler/replan theorem-surface checks: arbitrary finite accepted runs preserve authority, ordering, version, stop, dispatch, and residual invariants; one bounded replan trace reaches renewed job lowering; eleven closed controls reject invalid transitions; plan admission and job lowering refine the independent intent-to-execution vertical model; no planner-quality, dependency-truth, route-adequacy, deployed-scheduler, causal-benefit, or support-promotion claim
planning-as-a-control-layer	Planning as a Control Layer: DAGs and Intelligence Arbitrage	Planning scheduler-state probe	implemented	passes via deterministic synthetic scheduler-state fixture at experiments/planning_scheduler_state/results/2026-07-02-local.json: two valid synthetic scheduler traces, seven expected-invalid controls, one valid and three rejected PlanForge graph cases, five reachable dependency pairs without a cycle, one thin-summary admission collision, and 12/12 complete graph-transport mutation rejections; the consumer recompiles exact 53-declaration Planning and 18-declaration PlanForge surfaces; no decomposition-quality, dependency-truth/completeness, context-demand-prediction, selected-tier-adequacy, route-quality, scheduler-optimality, deployed scheduler, runtime-replanning, support-state-promotion, or evidence-transition claim
planning-as-a-control-layer	Planning as a Control Layer: DAGs and Intelligence Arbitrage	Planning runtime-replan delta audit	implemented	passes via deterministic synthetic runtime-replan delta audit at experiments/planning_runtime_replan_delta/results/2026-07-02-local.json: two valid synthetic runtime-replan traces and nine expected-invalid controls; no deployed-planner, runtime-scheduler, decomposition-quality, route-quality, selected-tier-adequacy, live-feedback-handling, support-state-promotion, or evidence-transition claim
governed-world-models-and-reality-grounding	Governed World Models and Reality Grounding	Reality-gap and horizon calibration benchmark	planned	not_run
governed-world-models-and-reality-grounding	Governed World Models and Reality Grounding	Model-exploitation red-team suite	planned	not_run
governed-world-models-and-reality-grounding	Governed World Models and Reality Grounding	Counterfactual intervention test	planned	not_run
cognitive-compilation-and-semantic-ir	Cognitive Compilation and Semantic IR	Requirement preservation test	implemented	passes via synthetic plan-execution contract harness
cognitive-compilation-and-semantic-ir	Cognitive Compilation and Semantic IR	Semantic lowering route proof	implemented	passes via Lean build; finite semantic-lowering route coverage only
cognitive-compilation-and-semantic-ir	Cognitive Compilation and Semantic IR	Incremental repair regression test	implemented	passes via python3 scripts/validate_cognitive_compilation_traces.py; synthetic trace records only
cognitive-compilation-and-semantic-ir	Cognitive Compilation and Semantic IR	Target compilation audit	implemented	passes via python3 scripts/validate_cognitive_compilation_traces.py; synthetic trace records only
cognitive-compilation-and-semantic-ir	Cognitive Compilation and Semantic IR	Historical-project semantic contract preservation	implemented	passing via python3 scripts/validate_semantic_contract_preservation.py; accepts one blocked three-project fixture and rejects nine paraphrase, omission, insertion, authority, repair-scope, ambiguity, failure-retention, and digest-parity mutations; no parser, backend, execution authority, measured locality, or support promotion
cognitive-compilation-and-semantic-ir	Cognitive Compilation and Semantic IR	Executed obligation-preserving compilation refinement	implemented	passes via python3 scripts/validate_cognitive_compilation_refinement.py: 2 accepted/4 rejected fixtures, an 8-event repair-and-revalidation witness, 33 Lean theorems, and 86/86 rejected mutations; support-state effect none
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Context ABI fixture validation	implemented	passes via protocol fixture validation; shape only
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Address/version stability test	implemented	passes through finite Lean context-reference predicates
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Admission vs adequacy test	implemented	passes via synthetic context admission/adequacy harness; no model verification-bandwidth claim
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Conflict adequacy classification test	implemented	passes via synthetic context admission/adequacy harness; no adjudication claim
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Context fault behavior test	implemented	passes via synthetic context admission/adequacy harness; no deployed resolver claim
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Context admission route proof	implemented	passes via Lean build; finite context-admission route coverage only
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Semantic page certificate fixture validation	implemented	passes via protocol fixture validation; shape only
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Certificate completeness test	implemented	passes through finite Lean certificate predicates
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Authority preservation test	implemented	passes through finite Lean authority predicates
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Certificate lifecycle admission route proof	implemented	passes via Lean build; finite certificate-lifecycle route coverage only
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Summary fidelity boundary test	implemented	passes via synthetic context admission/adequacy harness for loss/omission gate behavior; no semantic fidelity claim
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Resolver conformance test	implemented	passes via VCM resolver/certificate probe over valid_resolver_materialization_receipt, valid_mandatory_miss_typed_fault, address/version/snapshot/mount denial, and lease-expired blocking; no deployed-resolver, memory-store, context-compiler, open-domain-summary-fidelity, certificate-truthfulness, transaction-isolation, deletion-enforcement, model-facing-context-quality, VCM-Bench, leak-prevention, or support-state-promotion claim
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Certificate truthfulness test	implemented	passes via VCM resolver/certificate probe over paired source/derived synthetic cells, source-binding mismatch, authority escalation, truthfulness overclaim, and undeclared summary omission controls; no deployed-resolver, memory-store, context-compiler, open-domain-summary-fidelity, certificate-truthfulness, transaction-isolation, deletion-enforcement, model-facing-context-quality, VCM-Bench, leak-prevention, or support-state-promotion claim
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	VCM resolver/certificate probe	implemented	passes via deterministic public-safe VCM resolver/certificate probe; no deployed-resolver, memory-store, context-compiler, open-domain-summary-fidelity, certificate-truthfulness, transaction-isolation, deletion-enforcement, model-facing-context-quality, VCM-Bench, leak-prevention, or support-state-promotion claim
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Historical-project bounded graph-snapshot certificate	implemented	passes via one bounded four-project certificate and eleven expected-invalid mutations; no deployed resolver, durable-store correctness, graph completeness, historical runtime behavior, or support promotion
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Executed resolver/materialization and mandatory-fault refinement	implemented	passes via python3 scripts/validate_virtual_context_refinement.py: exact 39-theorem build, 2 valid/9 invalid resolver scenarios, distinct 3-valid/5-invalid admission fixtures, 4-event materialization and 2-event fault witnesses, 8 composition splits, and 73/73 rejected mutations; support and external-effect authority remain false
virtual-context-abi	The Virtual Context ABI: Typed Pages, Cells, and Certificates	Executed certificate provenance/lifecycle refinement	implemented	passes via python3 scripts/validate_context_certificate_refinement.py: 12 schema-valid certificate projections across 8 scenarios remain distinct from the 3-valid/5-invalid admission result, one 5-event witness, and 64/64 rejected mutations; support-state effect none
durable-semantic-memory-and-knowledge-lattices	Durable Semantic Memory and Knowledge Lattices	Contract completeness mutation test	planned	not run
durable-semantic-memory-and-knowledge-lattices	Durable Semantic Memory and Knowledge Lattices	Adjacent-owner boundary substitution test	planned	not run
durable-semantic-memory-and-knowledge-lattices	Durable Semantic Memory and Knowledge Lattices	Mechanism-specific failure-family test	planned	not run
durable-semantic-memory-and-knowledge-lattices	Durable Semantic Memory and Knowledge Lattices	No-support-promotion control	planned	not run
context-transactions-snapshots-mounts-and-taint	Context Transactions, Snapshots, Mounts, and Taint	Context transaction fixture validation	implemented	passes via protocol fixture validation; shape only
context-transactions-snapshots-mounts-and-taint	Context Transactions, Snapshots, Mounts, and Taint	Snapshot read finite-record proof	implemented	builds in AsiStackProofs.ContextTransactions; no memory-store claim
context-transactions-snapshots-mounts-and-taint	Context Transactions, Snapshots, Mounts, and Taint	Taint propagation finite-record proof	implemented	builds in AsiStackProofs.ContextTransactions; no deployed taint engine claim
context-transactions-snapshots-mounts-and-taint	Context Transactions, Snapshots, Mounts, and Taint	Deletion closure test	implemented	passes via synthetic context admission/adequacy harness; no memory-store claim
context-transactions-snapshots-mounts-and-taint	Context Transactions, Snapshots, Mounts, and Taint	Context transaction route proof	implemented	passes via Lean build; finite snapshot, branch, mount, taint, deletion-closure, replay-boundary, support-transition, and non-claim route coverage only
context-transactions-snapshots-mounts-and-taint	Context Transactions, Snapshots, Mounts, and Taint	Bounded memory-store conformance harness	implemented	passes via synthetic context transaction memory-store harness and Lean/Python summary bridge; no deployed memory-store claim
context-transactions-snapshots-mounts-and-taint	Context Transactions, Snapshots, Mounts, and Taint	Context transaction memory-store fixture bridge	implemented	passes via finite Lean summary for 3 valid fixtures, 6 expected-invalid controls, replay-boundary checks, invalid-control rejection flags, and no chapter-core support promotion
context-transactions-snapshots-mounts-and-taint	Context Transactions, Snapshots, Mounts, and Taint	Context transaction sequence bridge	implemented	passes via synthetic sequence fixtures and finite Lean summary for 2 valid sequences, 4 expected-invalid controls, read-after-write checks, replay-boundary checks, taint-blocking checks, invalid-control rejection, and no chapter-core support promotion
context-transactions-snapshots-mounts-and-taint	Context Transactions, Snapshots, Mounts, and Taint	Historical-project restart/recovery lifecycle	implemented	passes via one bounded five-project lifecycle and ten expected-invalid mutations; no deployed store, process restart, filesystem atomicity, historical runtime behavior, or support promotion
context-transactions-snapshots-mounts-and-taint	Context Transactions, Snapshots, Mounts, and Taint	Executed snapshot transaction and taint/deletion refinement	implemented	passes via python3 scripts/validate_context_transaction_refinement.py: 35 Lean declarations, 12 lifecycle controls, 3/6 store fixtures, 2/4 sequences, 6 events, 81/81 rejected mutations; support effect none
verification-bandwidth-and-context-adequacy	Verification Bandwidth and Context Adequacy	Distractor resistance test	planned	not run
verification-bandwidth-and-context-adequacy	Verification Bandwidth and Context Adequacy	Adequacy labeling test	implemented	passes via synthetic context admission/adequacy harness; no model verification-bandwidth claim
verification-bandwidth-and-context-adequacy	Verification Bandwidth and Context Adequacy	Verification escalation test	implemented	passes via synthetic context admission/adequacy harness; no deployed escalation claim
verification-bandwidth-and-context-adequacy	Verification Bandwidth and Context Adequacy	Verification adequacy route proof	implemented	passes via Lean build; finite verification-adequacy route coverage only
verification-bandwidth-and-context-adequacy	Verification Bandwidth and Context Adequacy	Verification bandwidth contradiction probe	implemented	passes via deterministic synthetic contradiction and adequacy fixture at experiments/verification_bandwidth/results/2026-07-02-local.json: two valid synthetic adequacy traces and seven expected-invalid controls; no model-verification-bandwidth, contradiction-rate-performance, distractor-resistance, adequacy-classifier, deployed-claim-ledger, escalation-service, support-state-promotion, or evidence-transition claim
verification-bandwidth-and-context-adequacy	Verification Bandwidth and Context Adequacy	Verification bandwidth capacity model	implemented	passes via deterministic synthetic record-level capacity model at experiments/verification_bandwidth_capacity/results/2026-07-03-local.json: three valid capacity traces, five expected-invalid controls, a 12-unit all-pairwise obligation model with 66 obligations, 18 checked obligations, and 48 residual obligations, plus a named-decomposition trace; no model-verification-bandwidth law, contradiction-rate-performance, adequacy-classifier, deployed-long-context-failure, support-state-promotion, or evidence-transition claim
verification-bandwidth-and-context-adequacy	Verification Bandwidth and Context Adequacy	Reachable verification-plan and evidence-gate refinement	implemented	passes via python3 scripts/validate_verification_bandwidth_refinement.py: 3/5 admission, 2/7 contradiction, 3/5 capacity, 12 routes, 5 stages, and 31/31 rejected mutations; support effect none
claim-ledgers-and-belief-revision	Claim Ledgers and Belief Revision	Claim extraction test	planned	not run
claim-ledgers-and-belief-revision	Claim Ledgers and Belief Revision	Contradiction detection test	implemented	passing via synthetic claim ledger revision harness; no open-domain contradiction detection claim
claim-ledgers-and-belief-revision	Claim Ledgers and Belief Revision	Belief revision test	implemented	passing via synthetic claim ledger revision harness; no deployed belief engine claim
claim-ledgers-and-belief-revision	Claim Ledgers and Belief Revision	Claim ledger revision lifecycle route	implemented	passes via Lean route theorems; no open-domain extraction, semantic-equivalence, contradiction-quality, deployed belief-engine, or support-state-promotion claim
claim-ledgers-and-belief-revision	Claim Ledgers and Belief Revision	Claim ledger semantic and assumption fixture	implemented	passes via expanded synthetic claim ledger revision harness at experiments/claim_ledger_revision/results/2026-07-02-local.md: 5 valid fixture(s), 7 expected-invalid fixture(s), semantic-variant merge boundaries, assumption-context dependency preservation, unsynced-variant rejection, no semantic-equivalence proof, no assumption-context completeness proof, and no support-state promotion
claim-ledgers-and-belief-revision	Claim Ledgers and Belief Revision	Historical-project contradiction/revision lifecycle	implemented	passes via one bounded five-project record and eleven expected-invalid mutations; no open-domain detector, deployed belief engine, ontology correctness, historical runtime behavior, or support promotion
claim-ledgers-and-belief-revision	Claim Ledgers and Belief Revision	Append-only Claim Ledger and evidence-owner refinement	implemented	passes via python3 scripts/validate_claim_ledger_refinement.py: exact 27-declaration Lean surface, 5/7 revision fixtures, 1/11 five-project lifecycle, 22 route cases, 5 stages, and 34/34 rejected mutations; support effect none
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	Proof artifact presence test	implemented	passing via synthetic proof-carrying claim harness; no theorem-validity or verifier-quality claim
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	Tier assignment test	implemented	passing via synthetic proof-carrying claim harness; no open-domain tier assignment claim
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	Formalization mismatch review	implemented	passing via synthetic proof-carrying claim harness mismatch fixture; no semantic-equivalence guarantee
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	Adversarial review coverage test	implemented	passing via synthetic tribunal review harness; no adversarial-review quality or reviewer-independence claim
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	Dissent preservation test	implemented	passing via synthetic tribunal review harness; no consensus-quality or verdict-correctness claim
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	Consensus evidence test	implemented	passing via synthetic tribunal review harness; no deployed tribunal or runtime-review claim
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	High-risk accepted-verdict negative case	implemented	passes via Lean negative case; no reviewer-independence or probe-quality claim
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	Prior-review reuse negative case	implemented	passes via Lean negative case; no prior-review adequacy or semantic-equivalence claim
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	Action verdict negative case	implemented	passes via Lean negative case; no deployed enforcement or verdict-correctness claim
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	Tribunal versioned-verdict and appeal refinement	implemented	passes via python3 scripts/validate_tribunal_refinement.py: exact 19-theorem surface, arbitrary-run custody and non-authority, rejection noninterference, batch composition, absorbing appeal resolution, exact 3/5 review fixtures, 1/11 method-independence lifecycle, 28 routes, 7 stages, and 45/45 rejected mutations; support effect none
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	Adversarial review dossier and verdict-quality probe	implemented	passes via deterministic synthetic review-dossier fixture at experiments/adversarial_review_dossier/results/2026-07-02-local.json: two valid synthetic review dossiers and seven expected-invalid controls; no semantic-equivalence, reviewer-independence, adversarial-probe-quality, verdict-correctness, LLM-judge, debate-system, support-state-promotion, or evidence-transition claim
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	Historical-project tribunal method/independence fixture	implemented	passes via one bounded five-project record and eleven expected-invalid mutations; no reviewer-independence, method-adequacy, verdict-correctness, deployed-tribunal, historical runtime behavior, or support promotion
spinoza-verification-and-proof-carrying-claims	Proof-Carrying Claims and Adversarial Review	Proof-Carrying Claims target-to-writeback refinement	implemented	passes via python3 scripts/validate_proof_carrying_claims_refinement.py: exact 18-theorem surface, arbitrary-run custody and non-authority, rejection noninterference, batch composition, absorbing writeback, exact 3/5 proof fixtures, 2/7 dossier cases, 23 routes, 6 stages, and 36/36 rejected mutations; support effect none
labor-os-and-typed-jobs	Labor OS and Typed Jobs	Tool permission enforcement test	planned	not run
labor-os-and-typed-jobs	Labor OS and Typed Jobs	Human approval gate test	implemented	passes via Lean build and synthetic approval-bypass fixture; no approval-service claim
labor-os-and-typed-jobs	Labor OS and Typed Jobs	Typed job delivery and evidence-readiness probe	implemented	passes via deterministic synthetic typed-job delivery fixture at experiments/typed_job_delivery/results/2026-07-02-local.json: two valid synthetic typed-job traces and seven expected-invalid controls; no deployed scheduler, permission-enforcement, approval-service, runtime-adapter, replay-correctness, support-state-promotion, or evidence-transition claim
labor-os-and-typed-jobs	Labor OS and Typed Jobs	Typed job durable lifecycle probe	implemented	passes via deterministic synthetic durable lifecycle fixture at experiments/typed_job_durable_lifecycle/results/2026-07-02-local.json: two valid synthetic durable lifecycle traces and nine expected-invalid controls; no deployed scheduler, durable workflow recovery, permission-enforcement, approval-service, replay-correctness, support-state-promotion, or evidence-transition claim
labor-os-and-typed-jobs	Labor OS and Typed Jobs	Typed-job versioned execution and closure refinement	implemented	passes exact 32-declaration Lean surface, arbitrary-run lifecycle and custody invariants, exact 2/7 delivery and 2/9 durable suites, 29 routes, seven reachable stages, and 42/42 rejecting mutations; support-state effect none; no deployed scheduler, enforcement, recovery, task-success, truth, usefulness, safety, reproduction, or transfer claim
ai-work-surfaces-agent-harnesses-and-organizational-absorption	From Chat to Organizations: AI Work Surfaces and Agent Harnesses	work-surface transition schema and mutation suite	planned	not run
ai-work-surfaces-agent-harnesses-and-organizational-absorption	From Chat to Organizations: AI Work Surfaces and Agent Harnesses	cross-harness identity and authority non-substitution fixture	planned	not run
ai-work-surfaces-agent-harnesses-and-organizational-absorption	From Chat to Organizations: AI Work Surfaces and Agent Harnesses	matched answer-suggestion-task workload comparison	planned	not run
ai-work-surfaces-agent-harnesses-and-organizational-absorption	From Chat to Organizations: AI Work Surfaces and Agent Harnesses	organizational feedback common-mode stress test	planned	not run
human-ai-organizations-delegation-and-accountability	Human-AI Organizations, Delegation, and Accountability	Decision-right and crumple-zone mutations	implemented	passed
human-ai-organizations-delegation-and-accountability	Human-AI Organizations, Delegation, and Accountability	Competence workload and interdependence campaign	planned	not_run
human-ai-symbiosis-neurotechnology-and-cognitive-sovereignty	Human-AI Symbiosis, Neurotechnology, and Cognitive Sovereignty	Layer claim falsification test	planned	not run
ai-deployment-transition-distribution-and-human-agency	AI Deployment, Transition, Distribution, and Human Agency	Contract completeness mutation test	planned	not run
ai-deployment-transition-distribution-and-human-agency	AI Deployment, Transition, Distribution, and Human Agency	Adjacent-owner boundary substitution test	planned	not run
ai-deployment-transition-distribution-and-human-agency	AI Deployment, Transition, Distribution, and Human Agency	Mechanism-specific failure-family test	planned	not run
ai-deployment-transition-distribution-and-human-agency	AI Deployment, Transition, Distribution, and Human Agency	No-support-promotion control	planned	not run
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Artifact traceability test	implemented	passing via Lean traceability predicate, missing-ref negative case, artifact-admission route proof, and synthetic artifact graph replay harness; no deployed artifact-service claim
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Audit reconstruction test	implemented	passing via synthetic artifact graph replay harness and bounded provenance/route negative cases; no deployed audit-reconstruction claim
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Replay metadata completeness test	implemented	passing via synthetic artifact graph replay harness and bounded provenance/route negative cases; no deployed replay-engine claim
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Artifact graph route proof	implemented	passing via Lean route proof for missing artifact, parent/source/context transaction/semantic certificate/tool/claim/test/audit/replay/evidence/non-claim fields, stale certificate blocking, blocked promotion, and complete modeled admission; no deployed artifact graph claim
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Artifact replay packet bridge proof	implemented	passing via Lean replay-packet bridge for parent-job alignment, job-output coverage, transaction and certificate links, source coverage, audit-chain completeness, byte-exact observation, stale-certificate blocking, support-review transaction validation, partial-replay promotion blocking, record-only partial replay, and bounded-review admission; no deployed replay-engine claim
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Record-reality sequence bridge	implemented	passing via python3 scripts/validate_artifact_graph_record_reality_sequence.py and Lean bridge; accepts 1 stale/partial/fresh replay sequence and rejects 4 expected-invalid controls for stale-certificate promotion, restoration without fresh replay, missing non-claims, and support review without replay-validated transaction; no support-state promotion
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Receipt faithfulness adversarial fixture	implemented	passing via python3 scripts/validate_receipt_faithfulness.py; accepts 3 bounded receipt records, rejects 6 expected-invalid controls for shape-valid but reality-false receipts, trap-receipt failure, missing independent cross-check, unbounded attestation, and support promotion from receipt shape; no support-state promotion
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Receipt repository audit	implemented	passing via python3 scripts/validate_receipt_repository_audit.py; accepts 4 selected repository receipt records, checks tracked digest integrity, command pass status, external receipt fingerprints, non-claim boundaries, and no support-state promotion; no open-world receipt-faithfulness claim
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Receipt repository challenge audit	implemented	passing via python3 scripts/validate_receipt_repository_challenge.py; deterministic challenge over the prior repository audit accepts 3 tracked digest challenges and 1 Circle external fingerprint challenge while rejecting digest mismatch, missing artifact, external fingerprint mismatch, missing non-claims, and support-promotion controls; no support-state promotion
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Artifact live attestation probe	implemented	passing via python3 scripts/validate_artifact_live_attestation_probe.py; local live repository attestation over one produced artifact checks filesystem bytes, git object bytes, command replay, independent observer routes, a wrong-digest trap receipt, attestation limits, and 7 mutation controls; no support-state promotion
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Artifact randomized attestation audit	implemented	passing via python3 scripts/validate_artifact_randomized_attestation_audit.py; deterministic pseudo-random sample over 4 selected public-safe repository artifacts checks filesystem bytes, git object bytes, command replay, trap receipts, attestation limits, and 8 mutation controls; no support-state promotion
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Artifact public deployed-site attestation	implemented	passing via python3 scripts/validate_artifact_public_site_attestation.py; public GitHub Pages Artifact Graphs chapter fetch checks served HTML digest plus record-reality, epistemic-TCB, attestation, and non-claim fragments; no support-state promotion
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Epistemic trusted computing base fixture	implemented	passing via python3 scripts/validate_epistemic_trusted_computing_base.py; accepts 3 bounded trust-base records and rejects 6 expected-invalid controls for missing root of trust, verifier-trust laundering, unbounded trust propagation, missing recursion stop, erased outside-TCB residuals, and support promotion from trust-base shape; no support-state promotion
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Artifact projection/revocation closure harness	implemented	passing via python3 scripts/validate_artifact_projection_revocation.py; accepts 1 bounded five-project lineage record and rejects 10 expected-invalid controls for stale projection digests, incomplete or unknown revocation closure, replay-grade inflation, missing semantic validators, unacknowledged asynchronous completion, path authority, relocation mismatch, unverified relocation, and playback-based support promotion; no runtime or support-state claim
artifact-graphs-audit-logs-and-replay	Artifact Graphs, Audit Logs, and Replay	Artifact record-reality and trust refinement	implemented	recompiles an exact 21-theorem arbitrary-run surface; passes eight exact bounded suites, 33 routes, seven reachable stages, and 53/53 rejecting mutations; exact identity, rejection noninterference, batch composition, absorbing admission, and zero support/effect authority hold only for the finite authored model; no open-world provenance, artifact truth, replay correctness, external independence, deployed revocation, usefulness, safety, reproduction, or transfer claim
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Adapter permission test	implemented	passes via synthetic runtime adapter permission harness
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Approval gate enforcement test	implemented	passes via synthetic runtime adapter permission harness
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Rollback handle capture test	implemented	passes via synthetic runtime adapter permission harness; no real rollback execution claim
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Effect lease scope and sandbox proof	implemented	passes via Lean build; finite lease-scope predicate only
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Reachable runtime-adapter effect refinement	implemented	passes via Lean build and python3 scripts/validate_runtime_adapter_permissions.py: arbitrary accepted runs preserve exact lease, approval, dispatch, caller-ceiling, epoch, revocation, and effect-accounting invariants; every accepted event and run simulates AsiStackProofs.AuthorityEffectRefinement; eleven countermodels reject permission, identity, authority, expiry, secret, dispatch, rollback, pre-state, and revocation failures; support-state effect remains none
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Rollback obligation rejection proof	implemented	passes via Lean build; finite rollback-obligation predicate only
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Confused-deputy ambient-authority probe	implemented	passes via expected-invalid synthetic runtime adapter fixture; no deployed confused-deputy resistance claim
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Revoked authority receipt probe	implemented	passes via expected-invalid synthetic runtime adapter fixture; no deployed revocation propagation claim
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Runtime adapter effect replay probe	implemented	passes via valid_low_impact_local_write_effect_replay with rollback-exact temp-file restoration and missing-permission and expired-approval no-mutation controls; no deployed-adapter, sandbox, approval-service, secret-handle, rollback-service, policy-enforcement, benchmark, or support-state-promotion claim
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Runtime adapter adversarial boundary probe	implemented	passes via deterministic synthetic runtime-adapter adversarial boundary fixture at experiments/runtime_adapter_adversarial_boundary/results/2026-07-02-local.json: two valid synthetic adapter boundary reviews and twelve expected-invalid controls for confused-deputy parent mismatch, authority ceiling overrun, approval scope mismatch, expired approval, sandbox escape, secret materialization, missing rollback handle, missing effect receipt, missing audit refs, support-state promotion, and missing non-claim boundaries; no deployed-adapter, sandbox, approval-service, secret-handle, policy-enforcement, rollback-service, revocation-propagation, security-review, or support-state-promotion claim
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Runtime adapter revocation route proof	implemented	passes via Lean build; finite revocation-route predicates for revoked approvals, revoked leases, revoked authority receipts, no-mutation denial evidence, receipt/audit boundaries, and non-promotion boundaries only; no deployed revocation propagation claim
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Human oversight degradation fixture	implemented	passes via python3 scripts/validate_human_oversight_degradation.py over experiments/human_oversight_degradation/results/2026-07-03-local.json: three valid finite records and seven expected-invalid controls for approval fatigue, rubber-stamping, alarm fatigue, automation bias, reviewer qualification, support-state promotion, and non-claim boundaries; no support-state promotion, approval-service quality, reviewer-correctness, deployed human-factors behavior, or support-state-promotion claim
runtime-adapters-tool-permissions-and-human-approval	Runtime Adapters, Tool Permissions, and Human Approval	Historical-project adapter capability-envelope and replay-grade fixture	implemented	passes via python3 scripts/validate_sandboxed_adapter_capability.py for one bounded five-project record and ten expected-invalid mutations covering executable/path/network/clock/randomness scope, OS-enforcement overclaim, playback/live-replay distinction, irreversible residuals, dispatch, and support-state boundaries; no OS sandbox or deployed adapter claim
embodied-agency-real-time-control-and-physical-safety	Embodied Agency, Real-Time Control, and Physical Safety	Deadline state and actuator fault suite	planned	not_run
embodied-agency-real-time-control-and-physical-safety	Embodied Agency, Real-Time Control, and Physical Safety	Independent stop and irreversible-effect audit	planned	not_run
inter-stack-protocols-identity-and-economic-exchange	Inter-Stack Protocols, Identity, and Economic Exchange	Required-invalid-credential dispatch denial route	planned	not run
inter-stack-protocols-identity-and-economic-exchange	Inter-Stack Protocols, Identity, and Economic Exchange	Missing-reserved-budget value-bearing dispatch repair route	planned	not run
inter-stack-protocols-identity-and-economic-exchange	Inter-Stack Protocols, Identity, and Economic Exchange	Six-event identity-to-residual-closure lifecycle with arbitrary-run identity, authority-ceiling, and non-authority invariants	planned	not run
inter-stack-protocols-identity-and-economic-exchange	Inter-Stack Protocols, Identity, and Economic Exchange	Public-safe exchange contract workload with identity, delegation, expiry, revocation, budget, receipt, dispute, and residual negative controls	planned	not run
inter-stack-protocols-identity-and-economic-exchange	Inter-Stack Protocols, Identity, and Economic Exchange	Eleven validator-owned rejecting mutations	planned	not run
multi-agent-dynamics-collective-intelligence-and-systemic-risk	Multi-Agent Dynamics, Collective Intelligence, and Systemic Risk	Pairwise-only systemic inference guard	implemented	passed
multi-agent-dynamics-collective-intelligence-and-systemic-risk	Multi-Agent Dynamics, Collective Intelligence, and Systemic Risk	Known-game population controls	planned	not_run
multi-agent-dynamics-collective-intelligence-and-systemic-risk	Multi-Agent Dynamics, Collective Intelligence, and Systemic Risk	Human influence and intervention displacement	planned	not_run
procedural-memory-and-cognitive-loop-closure	Procedural Memory and Cognitive Loop Closure	Loop detection test	implemented	passes via synthetic procedural memory loop harness; no deployed loop detector or tool-synthesis claim
procedural-memory-and-cognitive-loop-closure	Procedural Memory and Cognitive Loop Closure	Tool abstraction test	implemented	passes via synthetic procedural memory loop harness; no generated-tool correctness claim
procedural-memory-and-cognitive-loop-closure	Procedural Memory and Cognitive Loop Closure	Verified tool regression test	implemented	passes via synthetic procedural memory loop harness; no deployed regression-quality or routing claim
procedural-memory-and-cognitive-loop-closure	Procedural Memory and Cognitive Loop Closure	Procedure lifecycle route proof	implemented	passes via Lean lifecycle route proof and fixture-shaped bridge records for valid routable, quarantined, and retired synthetic scenarios; no deployed loop-detector, tool-synthesis, routing, regression-quality, or retirement-automation claim
procedural-memory-and-cognitive-loop-closure	Procedural Memory and Cognitive Loop Closure	Historical-project trace-promotion test	implemented	passes via python3 scripts/validate_procedural_trace_promotion.py; bounded four-project record only, with no deployed trace mining, tool synthesis, regression-quality, rollback-execution, retirement-automation, historical-runtime, or support-promotion claim
procedural-memory-and-cognitive-loop-closure	Procedural Memory and Cognitive Loop Closure	Procedural Memory promotion and retirement refinement	implemented	passes an exact 21-theorem surface covering arbitrary finite-run identity and nonauthority, exact rejected-event state preservation, batch composition, and absorbing retirement; independently recompiles that surface while preserving two exact suites, 32 routes, seven reachable stages, and 33/33 rejecting mutations; support-state effect none; no natural trace-mining, generated-tool correctness, deployed routing, rollback, monitoring, retirement, usefulness, safety, reproduction, or transfer claim
routing-heads-and-specialist-cores	Routing Heads and Specialist Cores	Specialist routing accuracy test	planned	not run
routing-heads-and-specialist-cores	Routing Heads and Specialist Cores	Routing decision lease harness	implemented	passes via synthetic routing decision lease harness with accepted no-promotion record evidence_transitions/v1_x_measured/routing_decision_lease_no_change.json; no learned-router, route-quality, MoECOT replay, or deployed authority-enforcement claim
routing-heads-and-specialist-cores	Routing Heads and Specialist Cores	Routing decision lifecycle route	implemented	passes via Lean route theorems; no learned-router, route-quality, runtime enforcement, specialist-quality, MoECOT replay, benchmark, or support-state-promotion claim
routing-heads-and-specialist-cores	Routing Heads and Specialist Cores	Authority-bounded routing test	implemented	validated locally by synthetic fixtures; deployed router enforcement not run
routing-heads-and-specialist-cores	Routing Heads and Specialist Cores	Fallback route test	implemented	validated locally by synthetic fixtures; live fallback routing not run
routing-heads-and-specialist-cores	Routing Heads and Specialist Cores	MoECOT source-ingestion gate	planned	not run
routing-heads-and-specialist-cores	Routing Heads and Specialist Cores	Runtime crosswalk completeness test	planned	not run
routing-heads-and-specialist-cores	Routing Heads and Specialist Cores	Readiness/replay mapping review	partial	readiness mapping validated locally by synthetic fixtures; replay mapping not run
routing-heads-and-specialist-cores	Routing Heads and Specialist Cores	Routing and replaceable-substrate lifecycle refinement	implemented	passes an exact 25-theorem surface covering arbitrary finite-run fourteen-field identity and nonauthority, exact rejected-event state preservation, separate balanced route/answer accounting, batch composition, and absorbing closure; independently recompiles that surface while preserving three exact suites, 42 routes, seven reachable stages, and 47/47 rejecting mutations; support-state effect none; no natural useful-routing, strong-model transfer, deployed runtime/replay correctness, substrate superiority, RSI, or support claim
replaceable-cognitive-substrates-beyond-transformer-monoculture	Replaceable Cognitive Substrates: Beyond Transformer Monoculture	Cognitive Kernel ABI conformance and malicious-kernel rejection	implemented	passes 16-case independent trace checker with 12 rejecting mutations; no real kernel or benchmark
replaceable-cognitive-substrates-beyond-transformer-monoculture	Replaceable Cognitive Substrates: Beyond Transformer Monoculture	Matched heterogeneous-kernel tournament	candidate and strongest-comparator envelope unavailable	zero outcome runs; strongest current comparator hardware unavailable; no SOTA or core movement
replaceable-cognitive-substrates-beyond-transformer-monoculture	Replaceable Cognitive Substrates: Beyond Transformer Monoculture	Frozen-core verified-abstraction ratchet	OneCell and verified-abstraction learner absent	defeat prediction frozen; no outcome run, reproduction, transfer, or support movement
replaceable-cognitive-substrates-beyond-transformer-monoculture	Replaceable Cognitive Substrates: Beyond Transformer Monoculture	Governed architectural-RSI lifecycle	bounded lifecycle fixtures exist but no runnable architecture candidate	no externally reproduced candidate entered shadow, canary, rollback, retirement, or descendant invalidation
relational-dimension-compilation-and-polyadic-cognition	Relational Dimension Compilation and Polyadic Cognition	Layer claim falsification test	planned	not run
governed-model-training-distributed-optimization-and-scaling	Governed Model Training, Distributed Optimization, and Scaling	Training-run transaction contract	implemented	authored_record_only_no_training_effect
governed-model-training-distributed-optimization-and-scaling	Governed Model Training, Distributed Optimization, and Scaling	Natural distributed fault campaign	planned	prospectively_frozen_unexecuted
governed-model-training-distributed-optimization-and-scaling	Governed Model Training, Distributed Optimization, and Scaling	Independent run replay	planned	blocked_by_valid_campaign
learning-compute-topology-and-adaptive-process-architecture	Learning–Compute Topology and Adaptive Process Architecture	LCT-IR bounded reference conformance	implemented in supplied package	11 of 11 unit tests pass locally; no neural-training or topology-benefit result
learning-compute-topology-and-adaptive-process-architecture	Learning–Compute Topology and Adaptive Process Architecture	Independent normalization and semantic-equivalence audit	planned	unexecuted
learning-compute-topology-and-adaptive-process-architecture	Learning–Compute Topology and Adaptive Process Architecture	Learning-topology versus compute-topology factorial campaign	planned	unexecuted
learning-compute-topology-and-adaptive-process-architecture	Learning–Compute Topology and Adaptive Process Architecture	Adaptive topology controller and attack campaign	planned	unexecuted
learning-theory-generalization-and-scaling-science	Learning Theory, Generalization, and Scaling Science	Contract completeness mutation test	planned	not run
learning-theory-generalization-and-scaling-science	Learning Theory, Generalization, and Scaling Science	Adjacent-owner boundary substitution test	planned	not run
learning-theory-generalization-and-scaling-science	Learning Theory, Generalization, and Scaling Science	Mechanism-specific failure-family test	planned	not run
learning-theory-generalization-and-scaling-science	Learning Theory, Generalization, and Scaling Science	No-support-promotion control	planned	not run
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Readiness gate fixture validation	implemented	passes via python3 scripts/validate_protocol_examples.py; schema/fixture consistency only
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Readiness gate promotion predicate	implemented	passes via Lean build; record-boundary predicate only
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Quarantine ordinary-route predicate	implemented	passes via Lean build; no live quarantine routing claim
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Failed-gate promotion negative case	implemented	passes via Lean negative case; no gate-quality or deployment-readiness claim
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Accepted stronger-transition negative case	implemented	passes via Lean negative case; no lifecycle-engine behavior claim
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Quarantine route-boundary negative case	implemented	passes via Lean negative case; no live route-enforcement claim
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Stale-gate reuse negative case	implemented	passes via Lean negative case; no rerun execution or current-readiness claim
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Readiness transition enforcement test	implemented	validated locally by synthetic fixtures; deployed readiness engine not run
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Residual escrow integrity test	implemented	validated locally by synthetic fixtures; residual-ledger storage not run
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Quarantine routing harness test	implemented	validated locally by synthetic fixtures; live quarantine routing not run
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Readiness lifecycle transition proof	implemented	passes via Lean build; finite transition-record predicate only
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Readiness lifecycle probe	implemented	validated locally at experiments/readiness_lifecycle_probe/results/2026-07-02-local.json; deterministic synthetic readiness lifecycle fixture only; no deployed readiness engine or support-state promotion
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Historical-project readiness check lifecycle	implemented	passing via python3 scripts/validate_readiness_check_lifecycle.py; accepts one quarantined six-project lineage record and rejects nine skipped-as-green, stale, waiver, evidence, containment, quarantine, route, and support-promotion mutations; no deployed readiness or support-state promotion
readiness-gates-residual-escrow-and-quarantine	Readiness Gates, Residual Escrow, and Quarantine	Readiness candidate-to-terminal refinement	implemented	passes an exact 24-theorem surface, arbitrary finite-run identity and non-authority invariants, exact batch composition, absorbing terminal closure, three exact suites, 40 routes, seven reachable stages, and 45/45 rejecting mutations; one ordinary release, quarantine, and terminal closure remain separate; support-state effect none; no evaluator adequacy, calibration, natural usefulness, effect-complete rollback, deployed quarantine/revocation, transfer, or support claim
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Device registry fixture validation	implemented	passes via protocol fixture validation
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Portal, approval, bid, and federation fixture validation	implemented	passes via protocol fixture validation
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Policy-first scheduling denial test	implemented	passes via Lean build
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Hive admission harness	implemented	passes via python3 scripts/validate_hive_admission.py; 2 valid and 8 expected-invalid synthetic fixtures
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Partitioned authority fixture	implemented	passes via python3 scripts/validate_partitioned_authority_fixture.py over experiments/partitioned_authority/results/2026-07-03-local.json: 3 valid finite records and 6 expected-invalid controls; does not prove deployed partition tolerance, distributed consensus, availability, runtime adapter enforcement, revocation propagation, or support-state-promotion claim
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Data locality and rented-node denial test	implemented	passes via python3 scripts/validate_hive_admission.py
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Phone approval gate test	implemented	passes via python3 scripts/validate_hive_admission.py
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Child topic routing test	implemented	passes via python3 scripts/validate_hive_admission.py
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	External project sandbox contract test	implemented	passes via python3 scripts/validate_hive_admission.py
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Audit replay test	implemented	passes via python3 scripts/validate_hive_admission.py
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Cross-router connectivity test	planned	not run
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Job bidding test	implemented	passes via python3 scripts/validate_hive_admission.py
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Device dropout test	implemented	passes via python3 scripts/validate_hive_admission.py
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Energy-aware scheduling test	implemented	passes via python3 scripts/validate_hive_admission.py
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Portal continuity test	planned	not run
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Bound approval receipt test	implemented	passes via Lean build
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Federation lease boundary test	implemented	passes via Lean build
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Hive work admission lifecycle route proof	implemented	passes via Lean build; finite hive-work admission route coverage only
personal-compute-hives-and-federated-edge-intelligence	Personal Compute Hives and Federated Edge Intelligence	Hive policy-to-closure lifecycle refinement	implemented	recompiles the exact 31-theorem surface; passes two exact suites, six accepted lifecycle events, seven reachable stages, all seven trace splits, 47 routes, six post-closure rejections, and 144/144 rejecting mutations; thirteen identity fields plus dispatch, useful-outcome, recovery, support, and effects stay separate; no deployed scheduler/federation, partition tolerance, availability, security, privacy, energy, dropout-recovery, useful-work, transfer, or support claim
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Residual honesty negative case	implemented	passes via Lean negative case; no behavioral residual-burden measurement claim
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Lossy exactness negative case	implemented	passes via Lean negative case; no codec-correctness or exact-reconstruction claim
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Compact GVR synthetic slice	implemented	passes via python3 scripts/validate_compact_gvr_slice.py; selected 78-byte compact receipt versus 368-byte literal baseline, rejected 3 negative controls, no chapter-core promotion
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Residual honesty conservation fixture	implemented	passes via python3 scripts/validate_residual_honesty_conservation.py; accepts 3 valid residual records, rejects 5 expected-invalid controls, no support-state effect
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Residual ledger trace	implemented	passes via python3 scripts/validate_residual_ledger_trace.py; reads 5 existing artifacts, records 4 residual trace entries, and preserves no support-state effect
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Residual ledger storage replay	implemented	passes via python3 scripts/validate_residual_ledger_storage_replay.py; records 4 replay entries, rejects 5 expected-invalid controls, and records a blocks_promotion no-change transition
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Exact reconstruction mismatch negative case	implemented	passes via Lean negative case; no real reconstruction-quality claim
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Failed verification promotion negative case	implemented	passes via Lean negative case; no verifier-quality or codec-behavior claim
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Semantic grounded-provenance negative case	implemented	passes via Lean negative case; no grounding-quality or semantic-utility claim
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Semantic hierarchy-supersession negative case	implemented	passes via Lean negative case; no downstream hierarchy-migration behavior claim
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	S/R/Q/G/V/E loop consistency test	planned	not run
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Residual burden test	planned	not run
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Downstream utility test	planned	not run
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Fallback behavior test	planned	not run
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Reconstruction quality test	planned	not run
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Repair-cost accounting test	planned	not run
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Bounded-search failure test	planned	not run
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Grounding fidelity test	planned	not run
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Hierarchy revision test	planned	not run
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Representation utility benchmark	planned	not run
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Consumer-policy test	planned	not run
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Circle seed-rule receipt-slice validation	implemented	passing via python3 scripts/validate_circle_seed_rule_receipt_slice.py for Circle commit 63b0f511, CC-AI-CONTRACT-SEED-RULE-001, kind seed_rule_exact_regeneration, theorem IDs GEN-T0001, GEN-T0040, GEN-T0041, GEN-T0046, GEN-T0048, GEN-T0050, theorem_count=32, recommendations SEED-RULE-USE-EXACT-REGENERATION-RECIPE and SEED-RULE-SELECT-BOUNDED-SHORTER-CANDIDATE, fingerprint 836594a5f1d448900797e595cb98f0e476c0b9cbd7365fe333cf7ae2622f13c5, fixture_n=128, exact_regeneration=true, generator_length=383, explicit_length=454, storage_saving=71, bounded_search_candidate_count=3, bounded_search_exact_candidate_count=2, bounded_search_best_shorter_generator_shorter=true, 2 passed in 4.52s, 1 passed in 2.80s, and circle_seed_rule_receipt_no_change.json; structural external-project receipt only; does not promote any chapter core claim, does not create a support-state transition, and does not prove useful compression, codec correctness, semantic utility, deployed generator behavior, fallback execution, downstream utility, optimal search, model quality, context length, runtime speed, memory scaling, benchmark performance, transfer, safety, ASI, or support-state-transition claim; compact boundary: no useful compression, codec-correctness, semantic-utility, deployed-generator, fallback-execution, downstream-utility, optimal-search, model-quality, runtime, memory-scaling, transfer, ASI, or support-state-transition claim
compact-generative-systems-and-residual-honesty	Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty	Compact generation source-to-closure lifecycle refinement	implemented	passes 35 Lean theorems, nine stages, all sixty routes, nine trace splits, 163/163 lifecycle mutations, four digest-bound source result families, one reachable modeled fallback, and support/effect none; no codec, semantic utility, deployed fallback, residual completeness, transfer, or support claim
fast-generation-architectures	Fast Generation Architectures	Acceleration accounting negative case	implemented	passes via Lean negative case; no decoder-speed, verifier-quality, or task-success claim
fast-generation-architectures	Fast Generation Architectures	Failed-acceptance handling negative case	implemented	passes via Lean negative case; no fallback-runtime or repair-quality claim
fast-generation-architectures	Fast Generation Architectures	High-risk fast-mode review negative case	implemented	passes via Lean negative case; no risk-classifier or mode-selector behavior claim
fast-generation-architectures	Fast Generation Architectures	Theseus/Fast selected support-lane aggregate	implemented	passes via python3 scripts/validate_theseus_fast_support_lane.py; result theseus-fast-support-lane-2026-07-03-local checks 4 command replays, 16 tracked artifact digests, 68 public task records, 14 expected-invalid or rejected controls, 2 accepted no-promotion decisions, and theseusFastSupportAggregateFixture; no clean live Project Theseus replay, model-quality, generation-speed, useful-solution-per-second, deployment, benchmark, or support-state-promotion claim
fast-generation-architectures	Fast Generation Architectures	Autoregressive baseline speed-quality test	planned	not run
fast-generation-architectures	Fast Generation Architectures	Speculative decoding acceptance test	planned	not run
fast-generation-architectures	Fast Generation Architectures	Multi-token draft-head acceptance test	planned	not run
fast-generation-architectures	Fast Generation Architectures	Medusa-style internal-head comparison test	planned	not run
fast-generation-architectures	Fast Generation Architectures	Diffusion small-model speed-quality curve	planned	not run
fast-generation-architectures	Fast Generation Architectures	Multi-seed diffusion useful-solution-per-second test	planned	not run
fast-generation-architectures	Fast Generation Architectures	Hybrid AR-to-diffusion repair test	planned	not run
fast-generation-architectures	Fast Generation Architectures	Planner-selected generation-mode routing test	planned	not run
fast-generation-architectures	Fast Generation Architectures	Risk-tiered decoding enforcement test	planned	not run
fast-generation-architectures	Fast Generation Architectures	KV-cache throughput accounting test	planned	not run
fast-generation-architectures	Fast Generation Architectures	Fast Generation request-to-closure lifecycle refinement	implemented	passes eight stages, all sixty routes, 51/51 non-accepting mutations, three digest-bound bounded suites, one reachable modeled fallback, and support/effect none; no model-speed, useful-throughput, deployed-fallback, serving, transfer, or support claim
governed-deliberation-and-test-time-scaling	Governed Deliberation and Test-Time Scaling	High-risk independent-verifier admission fixture	planned	not run
governed-deliberation-and-test-time-scaling	Governed Deliberation and Test-Time Scaling	Budget-exhaustion residual fixture	planned	not run
governed-deliberation-and-test-time-scaling	Governed Deliberation and Test-Time Scaling	Deliberation workload comparison	planned	not run
governed-deliberation-and-test-time-scaling	Governed Deliberation and Test-Time Scaling	Trace-to-action consistency probe	planned	not run
governed-deliberation-and-test-time-scaling	Governed Deliberation and Test-Time Scaling	Governed Deliberation request-to-closure refinement	implemented	passes eight stages, all 59 routes, 51/51 non-accepting mutations, two digest-bound bounded results, fifteen preserved harms, zero fallback activations, residual escrow and bounded planning handoff, support/effect none; no language-model, natural-usefulness, verifier, faithfulness, deployment, transfer, or support claim
governed-deliberation-and-test-time-scaling	Governed Deliberation and Test-Time Scaling	Governed Deliberation request-to-closure refinement	implemented	passes eight stages, all 59 routes, 51/51 non-accepting mutations, three digest-bound source families including the actual-model 0/60 no-change result, fifteen preserved harms, zero synthetic fallback activations, residual escrow and bounded planning handoff, support/effect none; no useful-language-model, natural-usefulness, verifier, faithfulness, deployment, transfer, or support claim
rankfold-neuralfold-and-artifact-compression	RankFold, NeuralFold, and Artifact Compression	Compression ratio test	planned	not run
rankfold-neuralfold-and-artifact-compression	RankFold, NeuralFold, and Artifact Compression	Probe-route fallback test	planned	not run
rankfold-neuralfold-and-artifact-compression	RankFold, NeuralFold, and Artifact Compression	Downstream utility preservation test	planned	not run
rankfold-neuralfold-and-artifact-compression	RankFold, NeuralFold, and Artifact Compression	RankFold artifact import validation	implemented	passes via python3 scripts/validate_rankfold_artifact_import.py and no-promotion record evidence_transitions/v1_x_measured/rankfold_artifact_import_no_change.json; no codec-correctness, benchmark-performance, downstream-utility, fallback-execution, deployed-compression, or support-state-promotion claim
rankfold-neuralfold-and-artifact-compression	RankFold, NeuralFold, and Artifact Compression	RankFold public-safe replay probe	implemented	passes via python3 scripts/validate_rankfold_public_safe_probe.py and no-promotion record evidence_transitions/v1_x_measured/rankfold_public_safe_replay_probe_no_change.json; no NeuralFold-compression, compression-advantage, codec-correctness, downstream-utility, fallback-execution, deployed-compression, or support-state-promotion claim
rankfold-neuralfold-and-artifact-compression	RankFold, NeuralFold, and Artifact Compression	Artifact compression request-to-closure refinement	implemented	passes the exact 27-theorem surface, eight stages, all 53 routes, eight trace-composition splits, 143/143 mutations, exact fixture/RAW0/NEURAL0/no-change artifact binding, exact-use and failed-probe fallback witnesses, arbitrary-run identity/non-authority/receipt/fallback invariants, and closure absorption; no codec-correctness, useful-compression, utility, deployment, transfer, or support claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Generation-mode resource-budget alignment harness	implemented	passing via python3 scripts/validate_generation_mode_baselines.py
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Resource budget ledger harness	implemented	passing via python3 scripts/validate_resource_budget_ledgers.py
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Required budget-gate preservation negative case	implemented	passes via Lean negative case; no scheduler-quality or economic-optimality claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	High-risk insufficient-budget dispatch negative case	implemented	passes via Lean negative case; no real resource-allocation performance claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Costed-route Lean fixture alignment gate	implemented	passing via python3 scripts/validate_costed_route_resource_slice.py; no deployed scheduler, route-search completeness, or economic-optimality claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Resource workflow trace harness	implemented	passing via python3 scripts/validate_resource_workflow_trace.py; no deployed scheduler, physical-feasibility, model-quality, or economic-outcome claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Resource live probe	implemented	passing via python3 scripts/validate_resource_live_probe.py; local repository command replay only; no deployed scheduler, physical-feasibility, model-quality, economic-outcome, or support-state-transition claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Resource workload-quality probe	implemented	passing via python3 scripts/validate_resource_workload_quality_probe.py; local five-sample median repository task only; no stable-speedup, deployed-scheduler, model-quality, economic-outcome, external-review, or support-state-transition claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Resource load-stability probe	implemented	passing via python3 scripts/validate_resource_load_stability_probe.py; accepted only for bounded non-core claim resource-economics.finite_burst_load_smoothing_selector; no TokenMana, deployed-scheduler, production-queue, real-load-stability, human-productivity, model-quality, economic-outcome, external-review, or chapter-core support-state-transition claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Resource flagship lane replay	implemented	passing via python3 scripts/validate_resource_flagship_lane.py; aggregate local repository replay only; Lean fixture resourceFlagshipLaneAggregateFixture checks finite replay counts, tracked artifacts, accepted narrow transitions, no-promotion decisions, preserved controls, residuals, non-claims, and no-core-promotion/no-new-transition accounting; no Resource Economics chapter-core promotion, deployed scheduler, production workload, model-quality, economic-outcome, external-review, artifact-approval, or new support-state-transition claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Resource governance-tax trade-off model	implemented	passing via python3 scripts/validate_resource_governance_tax_tradeoff.py; bounded synthetic trade-off only; no deployed scheduler behavior, real verification-tax measurement, economic optimality, chapter-core promotion, or support-state transition
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Budget allocation test	planned	not run
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Risk-adjusted verification test	planned	not run
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Capacity smoothing toy harness	implemented	passing via python3 scripts/validate_capacity_smoothing.py; 3 valid and 6 expected-invalid fixtures; no TokenMana, scheduler, load-stability, reviewer-optimization, or economic-result claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	KV-cache memory accounting scenario	implemented	passing via python3 scripts/validate_resource_budget_ledgers.py; deterministic record discipline only
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Simulation contract record fixture validation	implemented	passing via python3 scripts/validate_protocol_examples.py
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Simulation evidence-field negative case	implemented	passes via Lean negative case; no simulator-adequacy or transfer claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Simulation fidelity-overclaim negative case	implemented	passes via Lean negative case; no physical-feasibility or open-world-transfer claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Fidelity declaration test	implemented	passing via python3 scripts/validate_simulation_transfer_boundaries.py; no simulator-adequacy or physical-feasibility claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Resource-bound simulation sanity check	implemented	passing via python3 scripts/validate_simulation_transfer_boundaries.py; deterministic fixture discipline only
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Simulation approximation audit	implemented	passing via python3 scripts/validate_simulation_transfer_boundaries.py; no support-state promotion
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Theseus simulation-fidelity receipt suite import	implemented	passing via python3 scripts/validate_theseus_simulation_fidelity_receipt_suite_import.py; narrow import claim resource-economics.simulation_fidelity_receipt_suite_import only is prototype-backed; no simulator-adequacy, physical-feasibility, benchmark-transfer, native-KV-parity, deployment, model-quality, economic-outcome, clean-live-Theseus-replay, or chapter-core-promotion claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Theseus RLDS/Minari trace export import	implemented	passing via python3 scripts/validate_theseus_rlds_minari_trace_export_import.py; narrow import claim resource-economics.theseus_rlds_minari_trace_export_import only is prototype-backed; no RLDS dataset correctness, Minari dataset quality, simulator adequacy, replay success, model-quality, clean-live-Theseus-replay, or chapter-core-promotion claim
resource-economics-and-token-budgets	Resource Economics and Token Budgets	Resource Economics request-to-closure refinement	implemented	passes 29 Lean theorems, nine stages, nine trace splits, all 66 routes, 170/170 mutations, twelve digest-bound bounded source families, exact receipts, identity custody, resource/simulation separation, reconciliation and absorbing closure, support/effect none; no economic-optimality, useful-throughput, deployment, simulation-adequacy, transfer, or support claim
physical-compute-infrastructure-energy-and-environmental-constraints	Physical Compute Infrastructure, Energy, and Environmental Constraints	Contract completeness mutation test	planned	not run
physical-compute-infrastructure-energy-and-environmental-constraints	Physical Compute Infrastructure, Energy, and Environmental Constraints	Adjacent-owner boundary substitution test	planned	not run
physical-compute-infrastructure-energy-and-environmental-constraints	Physical Compute Infrastructure, Energy, and Environmental Constraints	Mechanism-specific failure-family test	planned	not run
physical-compute-infrastructure-energy-and-environmental-constraints	Physical Compute Infrastructure, Energy, and Environmental Constraints	No-support-promotion control	planned	not run
mathematical-and-search-substrates	Mathematical and Search Substrates	Required-field negative case	implemented	passes via Lean negative case; no substrate-quality claim
mathematical-and-search-substrates	Mathematical and Search Substrates	Unproven qualified-state negative case	implemented	passes via Lean negative case; no core-substrate promotion claim
mathematical-and-search-substrates	Mathematical and Search Substrates	Qualified-without-evidence negative case	implemented	passes via Lean negative case; no empirical substrate result
mathematical-and-search-substrates	Mathematical and Search Substrates	Consumer-axis negative case	implemented	passes via Lean negative case; no routing, compression, or reasoning-quality claim
mathematical-and-search-substrates	Mathematical and Search Substrates	Canary evidence-packet negative case	implemented	passes via Lean negative case; no canary benchmark claim
mathematical-and-search-substrates	Mathematical and Search Substrates	Substrate adoption trace	implemented	passes via python3 scripts/validate_substrate_adoption_trace.py; 4 valid traces and 8 expected-invalid controls; no substrate A/B test, model-quality claim, runtime claim, or support-state promotion
mathematical-and-search-substrates	Mathematical and Search Substrates	Baseline comparison test	planned	not run
mathematical-and-search-substrates	Mathematical and Search Substrates	Representation efficiency test	planned	not run
mathematical-and-search-substrates	Mathematical and Search Substrates	Falsification review	planned	not run
mathematical-and-search-substrates	Mathematical and Search Substrates	Sequence-substrate A/B comparison test	planned	not run
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Proof target record fixture validation	implemented	passes via python3 scripts/validate_protocol_examples.py; proof-record schema consistency only
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Proof contract receipt record fixture validation	implemented	passes via python3 scripts/validate_protocol_examples.py; receipt-record schema consistency only
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Circle public consumer-gate validation	implemented	passes via python3 scripts/validate_circle_public_replay.py; no local Circle replay or downstream model-quality claim
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Circle concrete receipt evidence-surface validation	implemented	passes via python3 scripts/validate_circle_concrete_evidence_surface.py; roadmap/reader visibility only, no support-state promotion
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Circle contract-pack archive validation	implemented	passes via python3 scripts/validate_circle_contract_pack_archive.py; validates the Circle contract-pack archive from commit 63b0f511 with 9 archived contracts, 4 acceptance-policy receipts, public_safe_fixture status, pack fingerprint df673f8a661fc89a26372685986c92f2221aaa617d6738fce5c2a76bd5d0eeae, raw pack digest b5488c93109ef120b97fdea7bd5d5605f32b2618c6cbfb9dde9a3328652551c4, raw report digest f1671f5cecdee311185f7e4508b21c139d4ae4bd1fa9610a12827f4d31c7985a, and circle_contract_pack_archive_no_change.json; does not promote any chapter core claim, does not create a support-state transition, does not rerun Circle Lean, and does not prove deployed proof-contract transport, model quality, context length, runtime speed, memory scaling, deployment safety, transfer, safety, ASI, or support-state promotion claim
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Receipt boundary Lean predicate	implemented	passes via Lean build; record-boundary predicate only
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Consumer gate promotion predicate	implemented	passes via Lean build; no workload or model-quality claim
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Circle public consumer-gate Lean fixture bridge	implemented	passes via Lean build; no local Circle replay, deployed transport, or support-state promotion claim
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Versioned proof-contract lifecycle and descendant revocation	implemented	passes via python3 scripts/validate_circle_contract_pack_archive.py; finite authored lifecycle only, with no external theorem resolution, semantic refinement, authenticated transport, deployed revocation, support transition, or chapter-core effect
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Missing receipt-boundary negative case	implemented	passes via Lean negative case; no theorem-resolution or replay claim
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Contract-readiness promotion negative case	implemented	passes via Lean negative case; no consumer acceptance or quality claim
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Stale or unsupported consumer-gate negative case	implemented	passes via Lean negative case; no transfer or support-state claim
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Replay artifact negative case	implemented	passes via Lean negative case; no replay execution claim
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Contract schema validation test	planned	not run
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Theorem-id resolution test	planned	not run
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Non-claim preservation test	planned	not run
circle-calculus-and-proof-carrying-ai-contracts	Circle Calculus and Proof-Carrying AI Contracts	Receipt replay and fingerprint test	planned	not run
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Hidden alias negative case	implemented	passes via Lean negative case; no alias behavior or retrieval-quality claim
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Structure-only quality-promotion negative case	implemented	passes via Lean negative case; no retrieval-quality claim
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Recurrence admission negative case	implemented	passes via Lean negative case; no recurrence-exit behavior claim
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Stale-read residual negative case	implemented	passes via Lean negative case; no KV-cache freshness behavior claim
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Cyclic alias visibility test	implemented	passing via python3 scripts/validate_cyclic_memory_contracts.py; synthetic structural traces only
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Sparse coverage gap test	implemented	passing via python3 scripts/validate_cyclic_memory_contracts.py; no sparse-attention behavior or quality claim
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Recurrence budget and exit test	implemented	passing via python3 scripts/validate_cyclic_memory_contracts.py; no recurrence-quality or runtime claim
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Freshness stale-read rejection test	implemented	passing via python3 scripts/validate_cyclic_memory_contracts.py; no KV-cache freshness or retrieval-quality claim
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Circle cyclic memory receipt-slice validation	implemented	passing via python3 scripts/validate_circle_cyclic_memory_receipt_slice.py; structural external-project receipt only; no retrieval-quality, long-context, model-quality, speed, memory-scaling, deployment, transfer, ASI, or support-state-transition claim
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Circle KV-cache receipt-slice validation	implemented	passing via python3 scripts/validate_circle_kv_cache_receipt_slice.py for Circle commit 63b0f511, CC-AI-CONTRACT-KV-001, kind kv_cache_ring_buffer, theorem IDs AIM-T0103, AIM-T0104, AIM-T0149, theorem_count=54, recommendations KV-DROP-STALE-REQUEST-TOKEN and KV-USE-SINK-ROLLING-WINDOW-REQUEST, fingerprint bfebf150ce45d1eb124ea553bf2ba8c62008751ebec9f8600b83cc09e0526a46, stale_probe_first_stale_token=12, sink_tokens_retained_by_policy=true, sink_window_exact_policy=true, sink_window_tokens_distinct=true, sink_prefix_disjoint_from_live_window=true, sink_tokens_outside_ordinary_rolling_window=true, 5 passed in 1.27s, and circle_kv_cache_receipt_no_change.json; structural external-project receipt only; does not promote any chapter core claim, does not create a support-state transition, and does not prove deployed KV-cache behavior, serving throughput, memory savings, paging correctness, retrieval quality, long-context, model quality, context length, deployment safety, transfer, ASI, or support-state-transition claim; compact boundary: no deployed KV-cache behavior, serving throughput, memory-savings, paging correctness, retrieval-quality, long-context, model-quality, deployment, transfer, ASI, or support-state-transition claim
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Circle recurrence receipt-slice validation	implemented	passing via python3 scripts/validate_circle_recurrence_receipt_slice.py for Circle commit 63b0f511, CC-AI-CONTRACT-RECURRENCE-001, kind recurrence_schedule, theorem IDs AIM-T0026, AIM-T0130, AIM-T0159, theorem_count=64, recommendations RECURRENCE-USE-ACTIVE-TOKEN-WORK-SCHEDULE and RECURRENCE-REUSE-WHOLE-PERIOD-SHIFT, fingerprint 571edd5dce4f7b64441806de323295218a3e2293b3b540dd4772ba34b9371515, active_token_count_trace=[8, 6, 4, 2, 1], inactive_token_count_trace=[0, 2, 4, 6, 7], total_active_token_work=21, total_inactive_token_work=19, scheduled_work_saving=19, post_period_multi_extension_scheduled_work_saving=43, periodic_shift_required_steps_invariant=true, periodic_shift_active_at_step_invariant=true, 2 passed in 2.37s, and circle_recurrence_receipt_no_change.json; structural external-project receipt only; does not promote any chapter core claim, does not create a support-state transition, and does not prove deployed recurrence behavior, reasoning quality, retrieval quality, learned-memory behavior, convergence, long-context, model-quality, deployment, transfer, ASI, or support-state-transition claim; compact boundary: no deployed recurrence behavior, reasoning-quality, retrieval-quality, learned-memory behavior, convergence, long-context, model-quality, deployment, transfer, ASI, or support-state-transition claim
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Circle sparse-attention receipt-slice validation	implemented	passing via python3 scripts/validate_circle_sparse_attention_receipt_slice.py for Circle commit 63b0f511, CC-AI-CONTRACT-SPARSE-001, kind sparse_attention_coverage, theorem IDs AIT-T0104, AIT-T0172, theorem_count=141, recommendations SPARSE-LOCAL-FIRST-INTERVAL-REPAIR and SPARSE-DENSE-LOCAL-COMPLETE-FALLBACK, fingerprint c23809cef9b821b1e4f9cabf53fcac724a0757bf3f86594e1d12710fe0cd9ec1, coverage_complete=false, first_uncovered_lag=5, uncovered_lag_count=109, covered_lag_count=10, complete_repair_window=119, complete_repair_window_additional_local_slots=115, complete_repair_window_minimal_for_declared_stride_family=true, complete_repair_window_minimal_witness_lag=119, interval_repair_plan_step_count=6, lag_collision_pair_count=0, query_collision_pair_count=0, 10 passed in 1.87s, and circle_sparse_attention_receipt_no_change.json; structural external-project receipt only; does not promote any chapter core claim, does not create a support-state transition, does not prove deployed sparse-attention behavior, and does not prove sparse-attention coverage success, deployed sparse-attention behavior, retrieval quality, long-context, model-quality, speed, memory savings, deployment, transfer, ASI, or support-state-transition claim; compact boundary: does not prove deployed sparse-attention behavior; no sparse-attention coverage success, deployed sparse-attention behavior, retrieval-quality, long-context, model-quality, speed, memory-savings, deployment, transfer, ASI, or support-state-transition claim
coil-attention-cyclic-memory-and-recurrence-contracts	Coil Attention, Cyclic Memory, and Recurrence Contracts	Circle strided fanout receipt-slice validation	implemented	passing via python3 scripts/validate_circle_strided_fanout_receipt_slice.py for Circle commit 63b0f511, CC-AI-CONTRACT-FANOUT-001, kind strided_candidate_fanout, theorem IDs AIT-T0001, AIT-T0002, AIT-T0003, AIT-T0173, theorem_count=4, recommendations FANOUT-USE-FULL-COVERAGE-STRIDE-CYCLE and FANOUT-AUDIT-DUPLICATE-COLLAPSED-BUDGET, fingerprint d4c878563747da9c9f1f55cd689f04e2a0a8e31ce9429a138341ec4e27ee3799, context_length=12, stride=5, gcd=1, predicted_reach=12, full_coverage=true, candidate_budget=12, unique_candidate_count=12, effective_candidate_budget=12, duplicate_count=0, candidate_budget_shortfall=0, effective_budget_matches_unique_candidates=true, effective_budget_reaches_predicted_reach=true, 3 passed in 4.65s, 1 passed in 2.77s, and circle_strided_fanout_receipt_no_change.json; structural external-project receipt only; does not promote any chapter core claim, does not create a support-state transition, and does not prove search-quality, retrieval-quality, routing-quality, sparse-attention-quality, model-quality, throughput, latency, speed, memory-savings, deployment, transfer, ASI, or support-state-transition claim; compact boundary: no search-quality, retrieval-quality, routing-quality, sparse-attention-quality, model-quality, throughput, latency, optimal-schedule, deployment, transfer, ASI, or support-state-transition claim
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	Claim-partition negative case	implemented	passes via Lean negative case; no model-quality, runtime, memory, or parameter-efficiency claim
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	Baseline/tradeoff promotion negative case	implemented	passes via Lean negative case; no adoption or quality claim
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	Residue/winding alias negative case	implemented	passes via Lean negative case; no alias-behavior or long-context claim
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	Tradeoff-packet negative case	implemented	passes via Lean negative case; no measured tradeoff claim
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	Hardware-refusal negative case	implemented	passes via Lean negative case; no hardware-kernel benchmark claim
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	Cyclic candidate canary lifecycle	implemented	passes via python3 scripts/validate_circle_cyclic_mixer_receipt_slice.py; authored finite lifecycle only, with no metric truth, useful canary, deployed fallback, support transition, or chapter-core effect
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	Circle concrete RoPE boundary evidence-surface validation	implemented	passes via python3 scripts/validate_circle_concrete_evidence_surface.py; structural diagnostic visibility only
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	Circle cyclic-mixer receipt-slice validation	implemented	passing via python3 scripts/validate_circle_cyclic_mixer_receipt_slice.py for Circle commit 63b0f511, CC-AI-CONTRACT-MIXER-001, kind circulant_block_cyclic_mixer, theorem IDs AIT-T0006, AIT-T0007, AIT-T0008, AIT-T0009, AIRA-T0001, AIRA-T0002, AIRA-T0004, theorem_count=7, recommendations MIXER-AUDIT-CIRCULANT-DENSE-PARITY and MIXER-AUDIT-BLOCK-CYCLIC-PARAMETER-BUDGET, fingerprint b3e3e0cf420d9e8e79a28a55ef8322f9a214c8d5a957dd8b06e5e5373c684ea5, max_abs_dense_delta=0, dense_parameters=64, circulant_parameters=8, circulant_parameter_ratio=0.125, dense_adapter_parameters=2048, lora_parameters=576, block_cyclic_parameters=128, block_to_dense_ratio=0.0625, 3 passed in 2.49s, 1 passed in 1.47s, and circle_cyclic_mixer_receipt_no_change.json; structural external-project receipt only; does not prove cyclic-mixer model quality; does not prove runtime speed; no memory scaling, hardware efficiency, training stability, deployment readiness, transfer, ASI, or support-state-transition claim.
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	Circle MultiCoil phase receipt-slice validation	implemented	passing via python3 scripts/validate_circle_multicoil_phase_receipt_slice.py for Circle commit 63b0f511, CC-AI-CONTRACT-PHASE-FEATURE-001, kind multicoil_phase_feature, theorem IDs AIA-T0001, AIA-T0002, AIA-T0004, AIT-T0004, AIT-T0005, theorem_count=5, recommendations PHASE-USE-JOINT-REPEAT-HORIZON and PHASE-AUDIT-RELATIVE-SHIFT-INVARIANT, fingerprint 4b562beab64ec863903e4267f50c90049f0d3fa612f6c1bb2f06ad07e821ffd7, periods=[5, 7], phase_tuple=[2, 2], shifted_phase_tuple=[2, 2], joint_repeat_horizon=35, relative_phase=3, shifted_relative_phase=3, relative_phase_invariant=true, 3 passed in 2.99s, 1 passed in 1.76s, and circle_multicoil_phase_receipt_no_change.json; structural external-project receipt only; does not prove MultiCoil, RoPE, attention, retrieval, or model quality, context length, runtime speed, memory scaling, hardware efficiency, training stability, deployment readiness, transfer, ASI, or support-state-transition claim.
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	RoPE receipt boundary test	planned	not run
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	Cyclic mixer baseline matrix test	planned	not run
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	Residue/winding alias diagnostic	planned	not run
coilra-multicoil-rope-and-cyclic-mixers	CoilRA, MultiCoil RoPE, and Cyclic Mixers	Parameter-quality-runtime separation test	planned	not run
executable-specifications-and-lean-proof-envelope	Executable Specifications and Lean Proof Envelope	Proof target record fixture validation	implemented	passes via protocol fixture validation
executable-specifications-and-lean-proof-envelope	Executable Specifications and Lean Proof Envelope	Proof manifest sync test	implemented	passes via proof manifest check
executable-specifications-and-lean-proof-envelope	Executable Specifications and Lean Proof Envelope	Lake build smoke test	implemented	passes via Lean build
executable-specifications-and-lean-proof-envelope	Executable Specifications and Lean Proof Envelope	Implemented-target missing artifact/build negative case	implemented	passes via Lean negative case; no filesystem discovery or proof-adequacy claim
executable-specifications-and-lean-proof-envelope	Executable Specifications and Lean Proof Envelope	Non-Lean artifact proof-laundering negative case	implemented	passes via Lean negative case; no claim about artifact semantic adequacy
executable-specifications-and-lean-proof-envelope	Executable Specifications and Lean Proof Envelope	Support-promotion boundary negative case	implemented	passes via Lean negative case; no Appendix C or chapter-core promotion
executable-specifications-and-lean-proof-envelope	Executable Specifications and Lean Proof Envelope	External theorem reference boundary negative case	implemented	passes via Lean negative case; no external theorem ownership or transfer claim
executable-specifications-and-lean-proof-envelope	Executable Specifications and Lean Proof Envelope	Proof target coverage summary	implemented	passes via proof readiness validation
executable-specifications-and-lean-proof-envelope	Executable Specifications and Lean Proof Envelope	Proof artifact traceability audit	implemented	passes via proof artifact audit and exact ProofEnvelope module compilation
executable-specifications-and-lean-proof-envelope	Executable Specifications and Lean Proof Envelope	Proof-depth surface synchronization	implemented	passes via python3 scripts/validate_proof_depth_surface.py; surface synchronization only, not semantic adequacy
executable-specifications-and-lean-proof-envelope	Executable Specifications and Lean Proof Envelope	Semantic proof adequacy audit	implemented	passes via python3 scripts/validate_proof_adequacy_review.py; table/count consistency and no-promotion review only
executable-specifications-and-lean-proof-envelope	Executable Specifications and Lean Proof Envelope	Historical-project formal semantic-depth fixture	implemented	passes via python3 scripts/validate_formal_semantic_depth.py for one blocked three-project record and ten expected-invalid mutations; no arbitrary adequacy or deployed-enforcement result
benchmark-ratchets-and-anti-goodhart-evidence	Benchmark Ratchets and Anti-Goodhart Evidence	Saturation detection test	implemented	validated locally by synthetic fixtures
benchmark-ratchets-and-anti-goodhart-evidence	Benchmark Ratchets and Anti-Goodhart Evidence	Hidden benchmark transfer test	implemented	validated locally by synthetic fixtures; no hidden benchmark run
benchmark-ratchets-and-anti-goodhart-evidence	Benchmark Ratchets and Anti-Goodhart Evidence	Regression preservation test	implemented	validated locally by synthetic fixtures; no empirical regression suite run
benchmark-ratchets-and-anti-goodhart-evidence	Benchmark Ratchets and Anti-Goodhart Evidence	Benchmark anti-Goodhart fixture bridge	implemented	passes via deterministic Python fixture recomputation plus AsiStackProofs.BenchmarkRatchets finite fixture bridge; no benchmark-quality, hidden-holdout, policy-training, steward-execution, release-safety, support-transition, or chapter-core promotion claim
benchmark-ratchets-and-anti-goodhart-evidence	Benchmark Ratchets and Anti-Goodhart Evidence	Metric-provenance and closure harness	implemented	validated locally with one blocked record and ten expected-invalid mutations; no benchmark reproduction, model capability, independent review, or support-state promotion
white-box-evidence-interpretability-and-activation-governance	White-Box Evidence, Interpretability, and Activation Governance	Interpretation stability and negative-control suite	protocol_ready_resource_isolated	not_run_protected_outcomes_closed
white-box-evidence-interpretability-and-activation-governance	White-Box Evidence, Interpretability, and Activation Governance	Causal intervention benchmark	protocol_ready_resource_isolated	not_run_protected_outcomes_closed
white-box-evidence-interpretability-and-activation-governance	White-Box Evidence, Interpretability, and Activation Governance	Governance non-authority mutation test	implemented	36 Lean theorems; six-event independent lifecycle; 51/51 lifecycle mutations and 12/12 packet/protocol mutations rejected; support/effect authority none
capability-thresholds-and-deployment-commitments	Capability Thresholds and Deployment Commitments	Crossed-threshold safeguard-completeness route	planned	not run
capability-thresholds-and-deployment-commitments	Capability Thresholds and Deployment Commitments	Stale or incomparable assessment residual fixture	planned	not run
capability-thresholds-and-deployment-commitments	Capability Thresholds and Deployment Commitments	Exception-expiry and compensating-control negative control	planned	not run
capability-thresholds-and-deployment-commitments	Capability Thresholds and Deployment Commitments	Matched threshold-commitment workload	planned	not run
capability-thresholds-and-deployment-commitments	Capability Thresholds and Deployment Commitments	Capability-threshold repeated-assessment refinement	implemented	passes the exact eight-case suite, 43 routes, six reachable stages, and 48/48 rejecting mutations; one readiness handoff returns to scoped assessment only through version-2 reassessment; support/effect none; no capability, threshold-validity, evaluator-independence, safeguard-efficacy, exception, readiness, deployed-invalidation, transfer, or support claim
adversarial-evaluation-sandbagging-and-training-time-deception	Adversarial Evaluation, Sandbagging, and Training-Time Deception	Evaluation-integrity record fixture	planned	not run
adversarial-evaluation-sandbagging-and-training-time-deception	Adversarial Evaluation, Sandbagging, and Training-Time Deception	Cross-context discrepancy probe	planned	not run
adversarial-evaluation-sandbagging-and-training-time-deception	Adversarial Evaluation, Sandbagging, and Training-Time Deception	Training-time deception boundary review	planned	not run
adversarial-evaluation-sandbagging-and-training-time-deception	Adversarial Evaluation, Sandbagging, and Training-Time Deception	Adversarial-evaluation observation-lifecycle refinement	implemented	passes the exact eight-case suite, 56 routes, seven reachable stages, and 60/60 rejecting mutations; one decision-review handoff returns to scoped protocol binding only through version-2 re-evaluation; support/effect none; no deception, capability, intent, prevalence, evaluator-validity, mitigation-efficacy, quarantine-correctness, release, transfer, or support claim
safety-cases-and-structured-assurance	Safety Cases and Structured Assurance	Complete bounded record to readiness-review route	planned	not run
safety-cases-and-structured-assurance	Safety Cases and Structured Assurance	Missing context and hazard-model negative controls	planned	not run
safety-cases-and-structured-assurance	Safety Cases and Structured Assurance	Stale evidence, countercase, independent-review, and unresolved-defeater routes	planned	not run
safety-cases-and-structured-assurance	Safety Cases and Structured Assurance	Authority-laundering rejection	planned	not run
safety-cases-and-structured-assurance	Safety Cases and Structured Assurance	Eight-case digest-bound synthetic assurance bridge	planned	not run
safety-cases-and-structured-assurance	Safety Cases and Structured Assurance	Safety-case lifecycle refinement	implemented	passes the exact eight-case suite, 30 routes, six reachable stages, and 35/35 rejecting mutations; one readiness handoff is invalidated back to challenge with no support or external effect; no argument-truth, hazard-completeness, evidence-adequacy, reviewer-independence, safety, readiness, deployed-invalidation, transfer, or support claim
content-authenticity-watermarking-and-synthetic-media-integrity	Content Authenticity, Watermarking, and Synthetic Media Integrity	Evidence-type separation test	planned	not run
content-authenticity-watermarking-and-synthetic-media-integrity	Content Authenticity, Watermarking, and Synthetic Media Integrity	Transformation-survival matrix	planned	not run
content-authenticity-watermarking-and-synthetic-media-integrity	Content Authenticity, Watermarking, and Synthetic Media Integrity	Valid-signature false-claim control	planned	not run
content-authenticity-watermarking-and-synthetic-media-integrity	Content Authenticity, Watermarking, and Synthetic Media Integrity	Missing-provenance non-inference test	planned	not run
content-authenticity-watermarking-and-synthetic-media-integrity	Content Authenticity, Watermarking, and Synthetic Media Integrity	Disclosure accessibility and remedy-route test	planned	not run
content-authenticity-watermarking-and-synthetic-media-integrity	Content Authenticity, Watermarking, and Synthetic Media Integrity	No-support-promotion control	planned	not run
governed-operations-incident-command-and-graceful-degradation	Governed Operations, Incident Command, and Graceful Degradation	Governed operations control-contract suite	implemented	18_of_18_semantic_mutations_rejected_support_effect_none
governed-operations-incident-command-and-graceful-degradation	Governed Operations, Incident Command, and Graceful Degradation	Effect-complete rollback mutation suite	planned	not_run
governed-operations-incident-command-and-graceful-degradation	Governed Operations, Incident Command, and Graceful Degradation	Incident command game-day matrix	planned	not_run
governed-operations-incident-command-and-graceful-degradation	Governed Operations, Incident Command, and Graceful Degradation	Graceful-degradation dominance test	planned	not_run
adjudicated-persistence-and-the-adaptive-commit-boundary	Adjudicated Persistence and the Adaptive Commit Boundary	Adaptive transaction mutation suite	planned	not_run
adjudicated-persistence-and-the-adaptive-commit-boundary	Adjudicated Persistence and the Adaptive Commit Boundary	LocusBench Tier-1 matched-collision suite	planned	not_run
adjudicated-persistence-and-the-adaptive-commit-boundary	Adjudicated Persistence and the Adaptive Commit Boundary	Descendant invalidation and residual-closure test	planned	not_run
adjudicated-persistence-and-the-adaptive-commit-boundary	Adjudicated Persistence and the Adaptive Commit Boundary	Deliberation-reserve and deoptimization test	planned	not_run
adjudicated-persistence-and-the-adaptive-commit-boundary	Adjudicated Persistence and the Adaptive Commit Boundary	Meta-compiler independence test	planned	not_run
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	DPO/offline preference baseline test	planned	not run
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	PPO online RL baseline test	planned	not run
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	GRPO/RLOO toy math reward test	planned	not run
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Verifier reward loop test	planned	not run
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Length and latency penalty study	planned	not run
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Reward-source admissibility test	implemented	validated locally by synthetic fixtures; no policy optimization run
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Reward hacking probe test	implemented	validated locally by synthetic fixtures; no reward-hacking experiment run
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Holdout and contamination negative case	implemented	passes via Lean negative case; no hidden-holdout or contamination-detection claim
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Reward-proxy target-evaluation negative case	implemented	passes via Lean negative case; no reward-quality or task-success claim
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Authority-expansion negative case	implemented	passes via Lean negative case; no approval-quality or rollback-execution claim
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Policy-promotion route negative case	implemented	passes via Lean route negative cases; no policy-improvement, reward-quality, or deployment claim
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Router policy toy RL test	planned	not run
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Context-policy grounding reward test	planned	not run
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Reasoning-budget penalty test	planned	not run
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Rollback and promotion gate test	implemented	validated locally by synthetic fixtures; no live rollback or policy canary run
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Policy update lease probe	implemented	validated locally by experiments/policy_update_lease/results/2026-07-02-local.json; no policy-improvement, reward-quality, route-quality, deployed rollback, or support-state claim
policy-optimization-and-learning-from-feedback	Policy Optimization and Learning from Feedback	Policy-optimization update-lifecycle refinement	implemented	passes two composed Lean traces, the inherited six-sample/five-candidate lease, 63 routes, seven reachable stages, 73/73 route mutations, and 3/3 cross-stage mutations; one bounded lease returns to scoped full-state binding only through version-2 readmission; support/effect none; no learning, reward-validity, causal, forgetting, rollback-efficacy, safety, release, transfer, or support claim
data-engines-continual-learning-and-unlearning	Data Engines, Continual Learning, and Unlearning	Data-admission receipt schema fixture	implemented	validated locally by tests/fixtures/protocol_records/data_admission_receipt.valid.json; no data-quality, training, or unlearning result
data-engines-continual-learning-and-unlearning	Data Engines, Continual Learning, and Unlearning	Data-admission route proof	implemented	validated locally by AsiStackProofs.DataEngines; no corpus, model, or capability result
data-engines-continual-learning-and-unlearning	Data Engines, Continual Learning, and Unlearning	Data-admission lifecycle probe	implemented	validated locally by experiments/data_admission_receipt_probe/results/2026-07-10-local.json; no data-quality, model, unlearning, or support-state result
data-engines-continual-learning-and-unlearning	Data Engines, Continual Learning, and Unlearning	Continual-learning and deletion workload	planned	not run
data-engines-continual-learning-and-unlearning	Data Engines, Continual Learning, and Unlearning	Data-engine custody/update/deletion lifecycle refinement	implemented	passes two composed Lean traces, three inherited result suites, 82 routes, eight reachable stages, 96/96 route mutations, and 3/3 cross-stage mutations; one bounded custody handoff returns to scoped admission only through version-2 readmission; support/effect none; no source-truth, learning, influence, forgetting, privacy/legal/storage erasure, production rollback, release, transfer, or support claim
scientific-discovery-and-experimental-governance	Scientific Discovery and Experimental Governance	Contract completeness mutation test	planned	not run
scientific-discovery-and-experimental-governance	Scientific Discovery and Experimental Governance	Adjacent-owner boundary substitution test	planned	not run
scientific-discovery-and-experimental-governance	Scientific Discovery and Experimental Governance	Mechanism-specific failure-family test	planned	not run
scientific-discovery-and-experimental-governance	Scientific Discovery and Experimental Governance	No-support-promotion control	planned	not run
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Project steward manifest fixture validation	implemented	passes via protocol fixture validation
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Treasury policy and event-taint fixture validation	implemented	passes via protocol fixture validation
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Work contract authority denial test	implemented	passes via Lean build and nine independently encoded lifecycle-probe controls
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Treasury spend-cap test	implemented	passes via Lean build
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Untrusted event taint test	implemented	passes via Lean build
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Contribution ledger separation test	implemented	passes via Lean build
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Sunset criteria test	implemented	passes via Lean build
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Release evidence handoff test	implemented	validated locally by synthetic fixtures; no steward release run
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Project federation contract test	implemented	passes via Lean build
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Autonomy-mode transition test	implemented	passes via Lean build
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Release evidence gate test	implemented	passes via Lean build and eight independently encoded lifecycle-probe controls
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Sunset ordinary-work block test	implemented	passes via deterministic lifecycle probe
artifact-steward-agents-and-living-project-governance	Artifact Steward Agents and Living Project Governance	Artifact steward lifecycle probe	implemented	passes via deterministic public-safe lifecycle probe; no steward-bot, treasury-executor, event-taint-workflow, contributor-ledger, governance-runner, project-federation, release-runner, sunset-protocol, or support-state-promotion claim
integrated-reference-architecture	Integrated Reference Architecture	End-to-end intent trace test	implemented	passing via python3 scripts/validate_reference_trace.py
integrated-reference-architecture	Integrated Reference Architecture	Artifact continuity audit	implemented	passing via python3 scripts/validate_reference_trace.py
integrated-reference-architecture	Integrated Reference Architecture	Authority stop-condition test	implemented	passing via python3 scripts/validate_reference_trace.py
integrated-reference-architecture	Integrated Reference Architecture	Actual command replay trace	implemented	passing via python3 scripts/validate_reference_trace_replay.py; local validator replay only, no deployed runtime trace or support-state promotion
integrated-reference-architecture	Integrated Reference Architecture	Governed cross-stack trace invariants test	implemented	passing via python3 scripts/validate_governed_trace_invariants.py; finite logical-time model over one executed local fixture workload
integrated-reference-architecture	Integrated Reference Architecture	Integrated cross-layer trace consumer	implemented	passing via python3 scripts/validate_integrated_reference_trace_consumer.py; 18 cases, 4 accepted, 14 rejected, 35 accepted events, and 15 rejected mutations
integrated-reference-architecture	Integrated Reference Architecture	Historical-project name-to-effect trace	implemented	passing via python3 scripts/validate_name_to_effect_trace.py; accepts one blocked five-project lineage trace and rejects eight expected-invalid controls
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus report crosswalk fixture validation	implemented	passes via python3 scripts/validate_protocol_examples.py; schema/fixture consistency only
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Static architecture-gate import validation	implemented	passes via python3 scripts/validate_theseus_report.py; no live replay or support-state promotion
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Static generation-mode gate import validation	implemented	passes via python3 scripts/validate_theseus_generation_mode_import.py; no live replay, generation-speed claim, model-quality claim, or support-state promotion
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus support replay probe	implemented	passes via python3 scripts/run_theseus_support_replay_probe.py --write-result and python3 scripts/validate_theseus_support_replay_probe.py; no clean live Theseus replay, public task bundle, model-quality result, generation-speed result, or support-state promotion
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus concrete evidence-surface validation	implemented	passes via python3 scripts/validate_theseus_concrete_evidence_surface.py; no live Theseus replay, model-quality result, generation-speed result, or support-state promotion
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus report-bundle audit validation	implemented	passes via python3 scripts/validate_theseus_report_bundle_audit.py; 1 valid fixture, 7 expected-invalid controls, 8 crosswalk rows, 6 visible artifact gaps, no live Theseus replay or support-state promotion
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus public task-bundle import validation	implemented	passes via python3 scripts/validate_theseus_public_task_bundle_import.py; clean live Theseus replay remains unclaimed and this does not prove model quality, benchmark superiority, generation speed, useful-solution-per-second improvement, or support-state promotion
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus/Fast selected support-lane aggregate	implemented	passes via python3 scripts/validate_theseus_fast_support_lane.py; result theseus-fast-support-lane-2026-07-03-local checks 4 command replays, 16 tracked artifact digests, 68 public task records, 14 expected-invalid or rejected controls, 2 accepted no-promotion decisions, and theseusFastSupportAggregateFixture; no clean live Project Theseus replay, model-quality, generation-speed, useful-solution-per-second, deployment, benchmark, or support-state-promotion claim
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus artifact-retention replay import validation	implemented	passes via python3 scripts/validate_theseus_artifact_retention_replay_import.py; result theseus-artifact-retention-replay-import-2026-07-05 checks 41,943,527 replayed payload bytes, 2,389,576 archived bytes, 7 expected-invalid controls, and bounded claim project-theseus-as-report-first-implementation-reference.artifact_retention_replay_gate_import from argument to prototype-backed; does not prove clean live Project Theseus replay, deployed residual-ledger storage, deployed artifact-graph behavior, model quality, benchmark performance, safety, alignment, ASI, or chapter-core promotion
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus module definition-of-done import validation	implemented	passes via python3 scripts/validate_theseus_module_definition_of_done_import.py; result theseus-module-definition-of-done-import-2026-07-05 checks 22 of 22 major module records ready, 0 hard gaps, 0 warnings, 20 source-backlog work cards, 7 expected-invalid controls, and bounded claim project-theseus-as-report-first-implementation-reference.module_definition_of_done_gate_import from argument to prototype-backed; does not prove clean live Project Theseus replay, module capability, deployed behavior, model quality, benchmark performance, safety, alignment, ASI, or chapter-core promotion
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus project-registry import validation	implemented	passes via python3 scripts/validate_theseus_project_registry_import.py; result theseus-project-registry-import-2026-07-05 checks 5,662 registered paths, 24 surfaces, full coverage, 0 unregistered active sources, 0 stale or missing report outputs, 0 generated source artifacts, 0 registry-governance violations, 9 expected-invalid controls, and bounded claim project-theseus-as-report-first-implementation-reference.project_registry_reality_import from argument to prototype-backed; does not prove clean live Project Theseus replay, deployment, model quality, generation speed, self-evolution safety, ASI, or chapter-core promotion
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus book-to-Theseus crosswalk import validation	implemented	passes via python3 scripts/validate_theseus_book_crosswalk_import.py; result theseus-book-crosswalk-import-2026-07-05 checks 53 public-safe pointer rows, 20 backlog cards, 134 source-sync review decisions, ten expected-invalid controls, and accepted no-promotion decision theseus_book_crosswalk_import_no_change.json; does not prove clean live Project Theseus replay, artifact truth for referenced rows, deployment, model quality, self-evolution safety, ASI, support-state promotion, or chapter-core promotion
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus work-board metadata import validation	implemented	passes via python3 scripts/validate_theseus_work_board_import.py; result theseus-work-board-import-2026-07-06 checks 130 durable task rows, 412 event rows, 133 evidence rows, five SQLite tables, one execution-ledger row, four unattended-improvement rows, 72 feedback rows, ten expected-invalid controls, and accepted no-promotion decision theseus_work_board_import_no_change.json; does not prove clean live Project Theseus replay, current board state, current dashboard state, deployment, model quality, unattended safety, self-evolution safety, ASI, support-state promotion, or chapter-core promotion
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus assistant reference-trace import validation	implemented	passes via python3 scripts/validate_theseus_assistant_reference_trace_import.py; result theseus-assistant-reference-trace-import-2026-07-06 checks 19 required trace record types, 27/27 gates, 2,203 VIEA view records, 11 expected-invalid controls, and bounded claim project-theseus-as-report-first-implementation-reference.assistant_reference_trace_import from argument to prototype-backed; does not prove clean live Project Theseus replay, current runtime state, deployment, route quality, private verifier quality, model quality, benchmark superiority, useful-solution-per-second, safety, ASI, or chapter-core promotion
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Report-bundle completeness test	implemented	passes via python3 scripts/validate_theseus_report_bundle_audit.py; repository fixture only; no live report-bundle import
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Replay-readiness test	implemented	passes via python3 scripts/validate_theseus_report_bundle_audit.py; no replay execution beyond existing ASI-side validators
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Theseus report crosswalk completeness test	implemented	passes via python3 scripts/validate_theseus_report_bundle_audit.py; public-safe repository fixture only; no clean live Theseus bundle
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Architecture gate mapping test	implemented	passes via python3 scripts/validate_theseus_report_bundle_audit.py; finite gate-decision mapping only
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Work-board improvement contract test	implemented	passes via python3 scripts/validate_theseus_report_bundle_audit.py; no current work-board import
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Artifact-gap audit	implemented	passes via python3 scripts/validate_theseus_report_bundle_audit.py; 6 visible gaps block support movement
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Self-evolution intervention ladder audit	implemented	passes via python3 scripts/validate_theseus_report_bundle_audit.py; finite ladder-ordering check only
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Dashboard-only implementation-reference negative case	implemented	passes via Lean negative case; no dashboard-state or report-truth claim
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Missing/failing gate promotion negative case	implemented	passes via Lean negative case; no gate-quality or self-evolution-safety claim
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Imported report-bundle completeness negative case	implemented	passes via Lean negative case; no report-bundle import or replay claim
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Replay-readiness boundary negative case	implemented	passes via Lean negative case; no replay execution claim
project-theseus-as-report-first-implementation-reference	Project Theseus as Report-First Implementation Reference	Public-safe artifact boundary negative case	implemented	passes via Lean negative case; no publication approval or support-state promotion
prototype-roadmap	Prototype Roadmap	Phase acceptance checklist	implemented	validated locally by exact Lean recompilation and independently encoded finite lifecycle; no dependency-truth, phase-completion, or support-state-promotion claim
prototype-roadmap	Prototype Roadmap	Dependency gate review	implemented	validated over 33 reachable states and 1,023 transitions; no dependency-truth, evaluator-competence, rollback-execution, deployed-build-controller, or support-state-promotion claim
prototype-roadmap	Prototype Roadmap	Prototype evidence-state audit	implemented	validated locally by synthetic fixtures; full phase acceptance audit not run
living-book-methodology	Living Book Methodology	Living book release record validation	implemented	passes via python3 scripts/validate_protocol_examples.py; release hygiene only
living-book-methodology	Living Book Methodology	Living-book change-packet validation	implemented	passes via python3 scripts/validate_living_book_change_packets.py with 3 valid and 6 expected-invalid fixtures, 39 exact Lean declarations, 5/5 trace splits, 9 reachable states through 162 transitions, 5 terminal states through 90 absorbing transitions, and 15 semantic mutations
living-book-methodology	Living Book Methodology	Reader release-candidate bridge	implemented	passes via python3 scripts/validate_reader_release_candidate_bridge.py with the current blocked candidate, 3 additional valid route cases, and 11 expected-invalid controls covering broad and field-specific accessibility/audio/approval overclaims; release-boundary discipline only
living-book-methodology	Living Book Methodology	Quarto render check	implemented	validated locally by quarto render --to html; no site-availability or manuscript-quality claim
living-book-methodology	Living Book Methodology	Reading-mode toggle check	implemented	passes via python3 scripts/validate_reading_mode_toggle.py; no reader-artifact approval
living-book-methodology	Living Book Methodology	Manifest/outline consistency check	implemented	passes via python3 scripts/validate_outline_consistency.py; no source-interpretation proof
living-book-methodology	Living Book Methodology	Manifest artifact negative case	implemented	passes via Lean negative case; no editorial-completeness claim
living-book-methodology	Living Book Methodology	Structural sync negative case	implemented	passes via Lean negative case; no publication-quality claim
living-book-methodology	Living Book Methodology	Release readiness negative case	implemented	passes via Lean negative case; no release approval beyond recorded artifacts
living-book-methodology	Living Book Methodology	Derived artifact boundary negative case	implemented	passes via Lean negative case; no ebook, PDF, DOCX, or audio artifact approval
open-research-agenda-and-bibliography-plan	Open Research Agenda and Bibliography Plan	Source inventory validation test	planned	not run
open-research-agenda-and-bibliography-plan	Open Research Agenda and Bibliography Plan	Source-note backlog audit	planned	not run
open-research-agenda-and-bibliography-plan	Open Research Agenda and Bibliography Plan	Source-derived claim evidence gate	implemented	passes via Lean source-record negative case; no citation-accuracy or source-interpretation claim
open-research-agenda-and-bibliography-plan	Open Research Agenda and Bibliography Plan	New-source assignment gate	implemented	passes via Lean nonexistent-chapter negative case; no real new-paper triage-quality claim
open-research-agenda-and-bibliography-plan	Open Research Agenda and Bibliography Plan	New-paper triage scenario	implemented	validated locally

E.1 Repository-Level Implemented Checks

Check	Command	Scope	Result policy
Protocol schema and release-record validation	python3 scripts/validate_protocol_examples.py	Validates example records in tests/fixtures/protocol_records/ and public release records in release_records/ against matching schemas in schemas/.	Passing this check proves fixture/release-record schema consistency only; it does not promote chapter claims or replace the chapter-level tests above.
Claim ledger revision harness	python3 scripts/validate_claim_ledger_revision.py	Checks synthetic claim-ledger and belief-revision fixtures for no-change boundaries, contradiction quarantine, claim splitting, support-state promotion blockers, revision-history preservation, surface propagation, review routing, residuals, and non-claim boundaries.	Passing this check proves synthetic claim-ledger record discipline only; it does not prove source interpretation, runtime behavior, verifier quality, open-domain claim extraction, or belief-engine correctness.
Proof-carrying claim harness	python3 scripts/validate_proof_carrying_claims.py	Checks synthetic proof-carrying-claim fixtures for verifier artifact refs, tier/justification alignment, bounded review eligibility, failed-attempt preservation, mismatch escalation, and non-claim boundaries.	Passing this check proves synthetic proof-carrying record discipline only; it does not prove theorem validity, semantic equivalence, citation accuracy, verifier quality, runtime behavior, or open-domain formalization.
Tribunal review harness	python3 scripts/validate_tribunal_review.py	Checks synthetic tribunal-review fixtures for dossier refs, reviewer roles, adversarial probes, evidence-backed accept verdicts, dissent preservation, prior-review guards, required actions, constraint effects, and non-claim boundaries.	Passing this check proves synthetic tribunal-review record discipline only; it does not prove reviewer independence, adversarial-review quality, consensus quality, verdict correctness, runtime behavior, or source interpretation.
Value conflict harness	python3 scripts/validate_value_conflicts.py	Checks synthetic value-conflict fixtures for multi-axis classification, stakeholder and evidence requirements, high-stakes review routing, residual uncertainty preservation, authority narrowing, dissent payloads, and bounded-decision revisit conditions.	Passing this check proves synthetic value-conflict record discipline only; it does not prove moral correctness, classification quality, reviewer independence, human-review quality, tribunal quality, runtime policy behavior, or source interpretation.
Constitutional alignment harness	python3 scripts/validate_constitutional_alignment.py	Checks synthetic constitutional-predicate fixtures for protected scope, operational tests, conflict routing, review routes, self-modification weakening rules, migration policies, least-sufficient-power behavior, uncertainty preservation, and non-claim boundaries.	Passing this check proves synthetic constitutional-predicate record discipline only; it does not prove deployed constitutional alignment, moral correctness, runtime policy behavior, source interpretation, self-modification safety, predicate-translation adequacy, or review quality.
Governance rights harness	python3 scripts/validate_governance_rights.py	Checks synthetic governance-right fixtures for audit material and receipts, denied/redacted appeal paths, materially usable exit and fork access paths, fork safety constraints, preservation obligations, durable record paths, and non-claim boundaries.	Passing this check proves synthetic governance-right record discipline only; it does not prove institutional governance rights, legal rights, runtime right enforcement, deployed fork/exit usability, reviewer independence, or source interpretation.
Agency rights harness	python3 scripts/validate_agency_rights.py	Checks synthetic agency-right checklist fixtures for affected parties, bounded delegation, material usability, timing-before-effect review, review and appeal channels, corrigibility paths, high-impact approval, residual dependency risk, degradation reasons, and accountable principals.	Passing this check proves synthetic agency-right checklist discipline only; it does not prove deployed agency preservation, dignity preservation, manipulation resistance, consent quality, reviewer independence, runtime policy behavior, or source interpretation.
Support-state transition harness	python3 scripts/validate_support_state_transitions.py	Checks synthetic valid and expected-invalid evidence-transition records for no-change conservatism, upward-transition review gates, downward demotion records, terminal refutation records, required evidence refs, and failed-verification blockers.	Passing this check proves transition-gate behavior for synthetic fixtures only; it does not promote, demote, deprecate, or refute Appendix C claims, prove source interpretation, or validate AI runtime behavior.
Authority transition harness	python3 scripts/validate_authority_transitions.py	Checks synthetic authority-transition records for non-escalation, permission separation, denial receipts, review escalation, and expected-invalid confused-deputy shortcuts.	Passing this check proves authority-gate behavior for synthetic fixtures only; it does not prove deployed permission enforcement, runtime adapter safety, secret handling, or revocation propagation.
Security kernel harness	python3 scripts/validate_security_kernel.py	Checks synthetic authority-use receipt fixtures for handle mediation, approval artifacts, bounded action scope, SCIF lifecycle completeness, sanitization, residual leak-risk notes, revocation paths, and prompt-injection non-disclosure boundaries.	Passing this check proves synthetic security-kernel receipt discipline only; it does not prove kernel security, sandbox isolation, side-channel safety, prompt-injection containment, secret-handle safety, least-privilege context behavior, runtime policy behavior, or source interpretation.
Stable capability fields harness	python3 scripts/validate_stable_capability_fields.py	Checks synthetic stable-capability-field fixtures for qualification predicates, evidence refs, readiness refs, authority ceilings, route permission effects, evaluator independence, rollback obligations, default-route blockers, and non-claim boundaries.	Passing this check proves synthetic stable-capability-field record discipline only; it does not prove runtime route validity, capability identity, evaluator integrity, authority enforcement, replacement safety, rollback execution, or source interpretation.
Capability replacement harness	python3 scripts/validate_capability_replacement.py	Checks synthetic replacement-transaction fixtures for field identity, qualification evidence, regression results, non-widening authority checks, evaluator separation, residual escrow, rollback receipts, approvals, monitor state, promotion blockers, model-rollout gates, irreversible-effect ownership, and non-claim boundaries.	Passing this check proves synthetic replacement-transaction record discipline only; it does not prove deployed replacement behavior, runtime route quality, evaluator integrity, authority enforcement, rollback execution, regression quality, source interpretation, production model rollout, model quality, or model-monitor behavior.
Self-improvement boundary harness	python3 scripts/validate_self_improvement_boundaries.py	Checks synthetic self-improvement transition fixtures for protected invariants, evaluator separation, cheaper-intervention ordering, authority non-widening, governance review, monitor windows, rollback paths, and no-promotion language.	Passing this check proves synthetic self-improvement transition-record discipline only; it does not prove deployed self-improvement behavior, runtime optimization, evaluator integrity, authority enforcement, rollback execution, regression quality, recursive self-improvement safety, or source interpretation.
Plan-execution contract harness	python3 scripts/validate_plan_execution_contracts.py	Checks synthetic command-contract, plan-graph, DAG, semantic-atom, typed-job, intent-origin, field-confidence, and inferred-authority scenarios for cross-record consistency, acyclic dependency order, dispatch receipts, requirement preservation, artifact traceability, approval gating, explicit intent preservation, authority-ceiling preservation, field-confidence dispatch blocking, and inferred-authority dispatch blocking.	Passing this check proves synthetic cross-record gate behavior only; it does not prove planner quality, scheduler behavior, deployed execution, runtime adapter safety, parser quality, semantic extraction quality, authority extraction quality, approval-service behavior, side-effect enforcement, or benchmark performance.
Runtime adapter permission harness	python3 scripts/validate_runtime_adapter_permissions.py	Checks synthetic typed-job, runtime-adapter-invocation, authority-use-receipt, and authority-probe scenarios for permission coverage, high-impact approval gating, approval expiry markers, effect receipts, rollback handles, irreversible residuals, authority receipt alignment, ambient-authority confused-deputy rejection, and revoked-receipt blocking.	Passing this check proves synthetic adapter-record gate behavior only; it does not prove deployed adapter behavior, sandbox isolation, approval-service quality, secret-handle safety, rollback execution, confused-deputy resistance, revocation propagation, or runtime behavior.
Runtime adapter effect replay probe	python3 scripts/validate_runtime_adapter_effect_probe.py	Checks a public-safe local temp-file effect replay for valid_low_impact_local_write_effect_replay, pre/post/rollback hashes, rollback-exact restoration, missing-permission no-mutation denial, and expired-approval no-mutation denial.	Passing this check proves only one local toy effect/rollback trace and two no-mutation controls; it does not prove deployed adapter behavior, sandbox isolation, approval-service behavior, secret-handle safety, revocation propagation, policy-enforcement correctness, rollback-service behavior, benchmark performance, or chapter-core support-state promotion.
Context admission/adequacy harness	python3 scripts/validate_context_admission_adequacy.py	Checks synthetic context ABI, packet, semantic-page certificate, transaction, and adequacy scenarios for admission/adequacy separation, conflict blocking, stale certificate rejection, deletion closure, escalation, and mode-confusion gates.	Passing this check proves synthetic context-record gate behavior only; it does not prove VCM resolver behavior, context compiler behavior, memory-store correctness, summary fidelity, model verification bandwidth, or benchmark performance.
Context transaction memory-store harness	python3 scripts/validate_context_transaction_memory_store.py	Checks bounded context-transaction and synthetic memory-event fixtures for committed-read visibility, mount faults, branch isolation, deletion-closure/materialization blocking, taint/declassification, replay boundaries, and support-state non-promotion.	Passing this check proves bounded fixture behavior only; it does not prove deployed memory-store correctness, VCM resolver behavior, runtime branch isolation, mount enforcement outside the fixture, side-channel safety, VCM-Bench performance, or support-state promotion.
Readiness/residual gate harness	python3 scripts/validate_readiness_residual_gates.py	Checks synthetic costed-route, readiness-gate, and replacement-transaction scenarios for promotion gates, residual escrow custody, quarantine, authority bounds, expired-evidence reruns, fallback, and rollback readiness.	Passing this check proves synthetic cross-record gate behavior only; it does not prove routing accuracy, readiness-engine behavior, residual-ledger storage, rollback execution, runtime monitoring, MoECOT replay, or benchmark performance.
Benchmark anti-Goodhart harness	python3 scripts/validate_benchmark_antigoodhart.py	Checks synthetic benchmark-ratchet, policy-optimization, and steward-action scenarios for holdout/contamination/mutation or transfer checks, saturated-benchmark regression floors, blocked-ratchet policy promotion, reward-as-truth confusion, and release approval evidence.	Passing this check proves synthetic cross-record gate behavior only; it does not prove benchmark quality, hidden-holdout integrity, policy-training quality, reward-hacking resistance, steward-agent behavior, release safety, or runtime behavior.
Generation mode baseline harness	python3 scripts/validate_generation_mode_baselines.py	Checks deterministic generation-mode and resource-budget scenarios for run, baseline, and negative-control refs, useful-solution-per-second plus quality and residual metrics, fallback behavior, resource-budget alignment, latency-only proxy rejection, and no-promotion boundaries.	Passing this check proves deterministic fixture-accounting behavior only; it does not prove generation speed, speculative decoding quality, diffusion generation quality, KV-cache throughput, routing quality, model quality, useful-solution-per-second performance, or runtime behavior.
Fast generation task-bundle validation	python3 scripts/validate_fast_generation_task_bundle.py	Recomputes a public-safe local fast-generation task bundle with an autoregressive reference baseline, verified fast-template candidate, latency-only negative control, quality checks, verifier/fallback/residual records, deterministic cost units, output digests, and useful-solution-per-cost accounting.	Passing this check proves deterministic task-bundle accounting and no-promotion boundaries only; it does not prove model generation speed, speculative decoding, MTP, diffusion, KV-cache, serving throughput, route-selector adequacy, model quality, useful-solution-per-second improvement for an AI model, or deployment behavior.
Project Theseus generation-mode import validation	python3 scripts/validate_theseus_generation_mode_import.py	Checks a public-safe static Project Theseus generation-mode gate import with 18 modes, 13 comparisons, zero hard gaps, zero modes with missing report refs, zero promotable comparisons, pinned source/report/tool digests, and expected-invalid controls for hard boundary-gate failure, private-payload copying, missing-report-ref overclaim, support-promotion overclaim, raw-speed promotion, and useful-speed overclaim.	Passing this check proves only the imported report-boundary discipline and negative promotion decision; it does not rerun Theseus, prove generation speed, prove useful-solution-per-second improvement, prove model quality, or promote chapter support states.
Compact GVR synthetic slice	python3 scripts/validate_compact_gvr_slice.py	Recomputes a public-safe compact generate-verify-repair receipt slice with a literal baseline, selected exact compact generator-plus-repair receipt, lossy exactness control, negative-rate/no-fallback control, bounded-search-overrun control, accepted non-core evidence transition, and Lean fixture bridge.	Passing this check proves bounded synthetic receipt discipline only; it does not prove compression utility, codec correctness, semantic utility, model quality, deployed fallback execution, benchmark performance, or chapter-core support-state promotion.
Circle concrete evidence-surface validation	python3 scripts/validate_circle_concrete_evidence_surface.py	Checks that the concrete Circle external receipt facts are visible in the Circle and CoilRA chapters, outline, and manifest test rows while preserving chapter-core, model-quality, context-length, runtime, transfer, deployment, and ASI non-claims.	Passing this check proves only public-surface traceability for an already-recorded structural receipt lane; it does not rerun Circle, vendor contract packs, prove model quality, promote chapter support states, or create a downstream workload result.
Circle cyclic memory receipt-slice validation	python3 scripts/validate_circle_cyclic_memory_receipt_slice.py	Checks that the Circle cyclic-memory receipt slice surfaces CC-AI-CONTRACT-MEMORY-001, theorem IDs, same-residue events, winding fields, alias load, receipt fingerprint, Circle CLI test output, and non-claim boundaries in the Coil chapter, reader manuscript, outline, roadmap, manifest, and result record.	Passing this check proves only structural residue/winding receipt traceability for one local external-project import; it does not rerun Circle from this repo, prove retrieval quality, prove model quality, prove long-context behavior, promote support state, or create a downstream workload result.
RankFold public-safe replay probe	python3 scripts/validate_rankfold_public_safe_probe.py	Checks a fresh local RankFold pack/verify/list/unpack replay over a generated public-safe synthetic text fixture, including RAW0 codec observation, roundtrip-exact digest preservation, no compression advantage, license-disabled NeuralFold boundary, and a single-byte corrupt-archive negative control.	Passing this check proves only one synthetic local replay and public-surface traceability; it does not prove RankFold codec correctness, NeuralFold compression, compression advantage, benchmark performance, downstream utility, fallback execution, deployed compression behavior, or chapter-core support-state promotion.
RankFold artifact import validation	python3 scripts/validate_rankfold_artifact_import.py	Checks a public-safe local RankFold artifact import for three existing .rfa archive observations over a 100,000,000-byte decoded artifact digest, archive ratios up to 2.76634019 decoded/archive, rfa verify summaries of 1 OK, 0 failed, NEURAL0 inspect metadata, and non-claim boundaries.	Passing this check proves only recorded local artifact metadata consistency and public-surface traceability; it does not rerun compression, prove codec correctness, prove benchmark performance, prove downstream utility, prove fallback execution, prove deployed compression behavior, or promote chapter-core support state.
Chapter-review burn-down validation	python3 scripts/validate_chapter_review_burndown.py	Checks that the calibrated 44-chapter review input is represented as roadmap work for every current manifest chapter, without stale IDs, placeholder rows, lost calibration notes, or unverified Circle wording.	Passing this check proves only roadmap coverage for reviewer-input follow-up; it does not prove chapter quality, source interpretation, external review, proof adequacy, test execution, or support-state promotion.
Resource budget ledger harness	python3 scripts/validate_resource_budget_ledgers.py	Checks deterministic Resource Budget Record scenarios for dispatch, high-risk escalation, protected overhead, security-overhead erasure rejection, displaced-cost residualization, review-capacity hoarding, KV-cache/serving-memory accounting separation, throughput-to-quality overclaim rejection, evidence refs, and no-promotion boundaries.	Passing this check proves deterministic budget-ledger fixture behavior only; it does not prove scheduler behavior, load stability, verification-tax optimization, KV-cache behavior, serving throughput, single-request quality, runtime budget enforcement, or economic outcomes.
Capacity smoothing toy harness	python3 scripts/validate_capacity_smoothing.py	Checks deterministic toy capacity traces for bounded regeneration arithmetic, priority deferral under blocked high-risk work, scope reduction, reviewer-capacity accounting, protected-review overhead, displaced-review-cost residualization, overload rejection, Lean bridge coverage, and no-promotion boundaries.	Passing this check proves toy trace consistency only; it does not prove TokenMana behavior, scheduler behavior, load stability, review-queue optimization, reviewer-capacity optimization, protected-overhead adequacy, displaced-cost measurement, runtime behavior, human outcomes, or economic outcomes.
Phase 5 harness registry validation	python3 scripts/validate_phase5_harness_registry.py	Checks that the Phase 5 harness set has commands, scripts, docs, fixture counts, result records, Appendix E rows, public status references, main-validation wiring, primary chapter mappings, and explicit non-claim boundaries.	Passing this check proves harness traceability only; it does not run the harnesses, prove runtime behavior, promote support states, or validate benchmark quality.
Reader continuity audit	python3 scripts/audit_reader_continuity.py --check	Derives the reader edition in a temporary workspace and checks that the tracked Phase 2 continuity audit is current, including reader word counts, overlay counts, density signals, table/code/diagram counts, repeated-opening heuristics, and a priority queue for human review.	Passing this check proves the audit report is current only; it is not a manual reader review, reader release, ebook/document/PDF artifact, audio artifact, or support-state promotion.
Proof-readiness validation	python3 scripts/validate_proof_readiness.py	Checks that proof triage tags, modules, root imports, formal targets, and target statuses stay aligned with the generated proof manifest.	Passing this check proves manifest/triage/import consistency only; theorem status still requires implemented Lean modules and a passing Lean build.
Proof artifact traceability audit	python3 scripts/validate_proof_artifact_audit.py	Checks that implemented proof targets are traceable from manifest and triage to Lean modules, root imports, chapter hooks, limitation prose, and Appendix E coverage.	Passing this check proves traceability and explicit non-claim coverage only; it does not prove semantic adequacy, source interpretation, deployed enforcement, or benchmark performance.
Source evidence traceability audit	python3 scripts/validate_source_evidence_audit.py	Checks that assigned source/chapter pairs, source notes, chapter listings, and claim-source mappings stay aligned, and reports passage-review coverage.	Passing this check proves source-note/mapping consistency only; it does not quote private passages or promote any support state.
Proof target coverage summary	Generated by python3 scripts/sync_scaffold.py from proofs/proof_triage.json; checked by python3 scripts/validate_proof_readiness.py.	Publishes the current count of proof targets by status, triage class, and recommended route.	Passing the validator proves coverage/accounting consistency only; it does not prove broad chapter claims, source interpretation, model quality, deployed enforcement, or benchmark performance.
Repeated prose validation	python3 scripts/validate_repeated_prose.py	Checks chapter files for exact repeated long prose paragraphs and known formulaic chapter phrases that indicate template-shaped drafting.	Passing this check proves only that exact repeated long paragraphs and known formulaic phrases are absent; it is not a full editorial review.
Visual coverage validation	python3 scripts/validate_visual_coverage.py	Checks that every chapter has at least one substantive Mermaid diagram with enough lines, edges, nodes, and labeled transitions, and that the landing page references the hero image asset.	Passing this check proves visual coverage only; it does not prove the diagrams are complete or promote chapter claims.

E.2 Proof Target Coverage Audit

This section is generated from proofs/proof_triage.json. It records coverage and routing state only: it does not prove broad chapter claims, source interpretation, model quality, deployed enforcement, or benchmark performance.

python3 scripts/validate_proof_readiness.py checks that these triage records stay aligned with proofs/proof_manifest.json, imported Lean modules, and implemented target statuses.

Metric	Count
Proof targets covered by triage	340

E.2.1 Coverage by Status

Target status	Count
implemented	330
planned	10

E.2.2 Coverage by Route

Target status	Triage class	Recommended route	Count
implemented	formal-invariant	lean-candidate	330
planned	formal-invariant	lean-candidate	9
planned	process-contract	policy-model-first	1