Appendix G — Corben’s Own Sources, Papers, and Local Projects
This appendix is generated from sources/source_inventory.json and current chapter assignments in book_structure.json.
This is an independent top-level appendix for Corben’s own papers, Corben-supplied source material, recovered project history, and local project references. It is not a combined “sources used” appendix, and it is not split into internal Corben/external parts. It contains only material on the Corben/local-project side of the corpus: Corben-authored papers, Corben-supplied source material, local-project source routes, recovered architecture notes, implementation references, variants, and public-safe source records that are not marked as third-party external literature.
Corben’s exact published manuscripts are readable inside the live book through Corben Papers and Architecture Sources. Paper titles and paper links in the table open those HTML reader pages. The library preserves original wording and provenance separately from the book’s later synthesis.
It is not a claim that every source has been ingested, summarized, citation-normalized, or independently verified. Source-derived claims should not be promoted until the relevant source has a source note and Appendix C has been updated.
External and third-party sources are not the second half of Appendix G. They live in their own top-level appendix: Appendix H, External Sources by Other Authors.
G.1 Source Ownership Boundary
This page is the Corben-side source appendix. It should be read as Appendix G only; the external-source appendix is Appendix H.
G.2 Appendix Identity
| Field | Boundary |
|---|---|
| This appendix contains | Corben-authored papers, Corben-supplied materials, recovered project records, and local project source records. |
| This appendix excludes | Third-party papers, documentation, outside projects, and other non-Corben references; those live in the separate Appendix H. |
G.3 Appendix Scope
| Field | Boundary |
|---|---|
| Appendix identity | Appendix G: Corben’s own sources, papers, and local projects |
| Ownership rule | If Corben wrote it, supplied it, recovered it from his project history, or built it in a local project, it belongs here; if another author, organization, or outside project produced it, it belongs in Appendix H. |
| Contains | Source material supplied by Corben, including authored ASI Stack papers, local-project source routes, implementation references, recovered notes, variants, and public-safe corpus records. |
| Excludes | Third-party literature records marked external_literature; those belong in Appendix H. |
| Evidence effect | Organizes Corben-side architecture material; it does not promote any claim unless the source note, Appendix C mapping, and evidence transition support that move. |
| Source ID | Title | Priority | Layer | Link | Current use | Bibliographic status |
|---|---|---|---|---|---|---|
viea |
Verified Intent-to-Execution Architecture | must_use |
whole_stack_execution_spine |
source | asi-is-a-stack-not-a-model (ASI Is a Stack, Not a Model); the-efficient-asi-hypothesis (The Efficient ASI Hypothesis); system-boundaries-and-authority (System Boundaries and Authority); failure-modes-of-ungoverned-intelligence (Failure Modes of Ungoverned Intelligence); evidence-states-and-claim-discipline (Evidence States and Claim Discipline); human-intent-as-a-formal-input (Human Intent as a Formal Input); human-factors-and-meaningful-control-in-oversight (Human Factors and Meaningful Control in Oversight); stable-capability-fields (Stable Capability Fields); recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); planning-as-a-control-layer (Planning as a Control Layer: DAGs and Intelligence Arbitrage); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); labor-os-and-typed-jobs (Labor OS and Typed Jobs); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); embodied-agency-real-time-control-and-physical-safety (Embodied Agency, Real-Time Control, and Physical Safety); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); resource-economics-and-token-budgets (Resource Economics and Token Budgets); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope); governed-operations-incident-command-and-graceful-degradation (Governed Operations, Incident Command, and Graceful Degradation); adjudicated-persistence-and-the-adaptive-commit-boundary (Adjudicated Persistence and the Adaptive Commit Boundary); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); integrated-reference-architecture (Integrated Reference Architecture); prototype-roadmap (Prototype Roadmap); living-book-methodology (Living Book Methodology) | source note available; exact author manuscript readable in the live-book paper library |
scf |
Stable Capability Fields | must_use |
governance_recursive_self_improvement |
source | asi-is-a-stack-not-a-model (ASI Is a Stack, Not a Model); system-boundaries-and-authority (System Boundaries and Authority); failure-modes-of-ungoverned-intelligence (Failure Modes of Ungoverned Intelligence); human-factors-and-meaningful-control-in-oversight (Human Factors and Meaningful Control in Oversight); stable-capability-fields (Stable Capability Fields); capability-replacement-and-rollback (Capability Replacement and Rollback); recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); replaceable-cognitive-substrates-beyond-transformer-monoculture (Replaceable Cognitive Substrates: Beyond Transformer Monoculture); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); personal-compute-hives-and-federated-edge-intelligence (Personal Compute Hives and Federated Edge Intelligence); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope); governed-operations-incident-command-and-graceful-degradation (Governed Operations, Incident Command, and Graceful Degradation); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); integrated-reference-architecture (Integrated Reference Architecture); prototype-roadmap (Prototype Roadmap); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
planforge |
PlanForge | must_use |
planning_control |
source | human-intent-as-a-formal-input (Human Intent as a Formal Input); planning-as-a-control-layer (Planning as a Control Layer: DAGs and Intelligence Arbitrage); governed-world-models-and-reality-grounding (Governed World Models and Reality Grounding); personal-compute-hives-and-federated-edge-intelligence (Personal Compute Hives and Federated Edge Intelligence); fast-generation-architectures (Fast Generation Architectures); resource-economics-and-token-budgets (Resource Economics and Token Budgets); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); integrated-reference-architecture (Integrated Reference Architecture); prototype-roadmap (Prototype Roadmap); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
planforge_compiler_arch |
PlanForge: A Compiler Architecture for AI Task Orchestration | must_use_variant |
planning_control |
source | planning-as-a-control-layer (Planning as a Control Layer: DAGs and Intelligence Arbitrage); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR) | source note available; exact author manuscript readable in the live-book paper library |
cognitive_compilation |
Cognitive Compilation | must_use |
planning_semantic_ir |
source | human-intent-as-a-formal-input (Human Intent as a Formal Input); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); planning-as-a-control-layer (Planning as a Control Layer: DAGs and Intelligence Arbitrage); governed-world-models-and-reality-grounding (Governed World Models and Reality Grounding); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); mathematical-and-search-substrates (Mathematical and Search Substrates) | source note available; exact author manuscript readable in the live-book paper library |
talos |
Talos Protocol | must_use |
labor_execution_os |
source | asi-is-a-stack-not-a-model (ASI Is a Stack, Not a Model); system-boundaries-and-authority (System Boundaries and Authority); failure-modes-of-ungoverned-intelligence (Failure Modes of Ungoverned Intelligence); human-intent-as-a-formal-input (Human Intent as a Formal Input); human-factors-and-meaningful-control-in-oversight (Human Factors and Meaningful Control in Oversight); human-ai-communication-persuasion-and-epistemic-security (Human-AI Communication, Persuasion, and Epistemic Security); societal-resilience-and-misuse-defense (Societal Resilience and Misuse Defense); stable-capability-fields (Stable Capability Fields); capability-replacement-and-rollback (Capability Replacement and Rollback); security-kernel-and-digital-scifs (Security Kernel and Digital SCIFs); recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); labor-os-and-typed-jobs (Labor OS and Typed Jobs); human-ai-organizations-delegation-and-accountability (Human-AI Organizations, Delegation, and Accountability); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); inter-stack-protocols-identity-and-economic-exchange (Inter-Stack Protocols, Identity, and Economic Exchange); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); personal-compute-hives-and-federated-edge-intelligence (Personal Compute Hives and Federated Edge Intelligence); fast-generation-architectures (Fast Generation Architectures); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope); governed-operations-incident-command-and-graceful-degradation (Governed Operations, Incident Command, and Graceful Degradation); adjudicated-persistence-and-the-adaptive-commit-boundary (Adjudicated Persistence and the Adaptive Commit Boundary); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); integrated-reference-architecture (Integrated Reference Architecture); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
talos_md |
Talos_Protocol_v1.0.md | must_use_variant |
labor_execution_os |
source | labor-os-and-typed-jobs (Labor OS and Typed Jobs) | source note available; citation not normalized |
vcm_public |
Virtual_Context_Memory_v1 | must_use |
memory_context |
source | failure-modes-of-ungoverned-intelligence (Failure Modes of Ungoverned Intelligence); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); durable-semantic-memory-and-knowledge-lattices (Durable Semantic Memory and Knowledge Lattices); context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint); verification-bandwidth-and-context-adequacy (Verification Bandwidth and Context Adequacy); inter-stack-protocols-identity-and-economic-exchange (Inter-Stack Protocols, Identity, and Economic Exchange); personal-compute-hives-and-federated-edge-intelligence (Personal Compute Hives and Federated Edge Intelligence); fast-generation-architectures (Fast Generation Architectures); coil-attention-cyclic-memory-and-recurrence-contracts (Coil Attention, Cyclic Memory, and Recurrence Contracts); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); integrated-reference-architecture (Integrated Reference Architecture); prototype-roadmap (Prototype Roadmap); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
vcm_editable |
Virtual_Context_Memory_v1.0_Editable | must_use_variant |
memory_context |
source | failure-modes-of-ungoverned-intelligence (Failure Modes of Ungoverned Intelligence); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint); verification-bandwidth-and-context-adequacy (Verification Bandwidth and Context Adequacy); integrated-reference-architecture (Integrated Reference Architecture); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; citation not normalized |
spinoza |
Proof of Belief / The Spinoza Architecture | must_use |
reasoning_epistemology |
source | failure-modes-of-ungoverned-intelligence (Failure Modes of Ungoverned Intelligence); evidence-states-and-claim-discipline (Evidence States and Claim Discipline); constitutional-alignment-substrate (Constitutional Alignment: Agency, Dignity, and Corrigibility); moral-uncertainty-and-value-conflict (Moral Uncertainty, Value Conflict, and Contestable Governance); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); verification-bandwidth-and-context-adequacy (Verification Bandwidth and Context Adequacy); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); fast-generation-architectures (Fast Generation Architectures); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); integrated-reference-architecture (Integrated Reference Architecture); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
spinoza_composer |
Spinoza Composer / Spinoza Trinity | supporting |
reasoning_media_compliance |
source | artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay) | source note available; exact author manuscript readable in the live-book paper library |
moecot |
MoECOT-Agent Architecture Whitepaper | must_use |
implementation_reference |
source | asi-is-a-stack-not-a-model (ASI Is a Stack, Not a Model); the-efficient-asi-hypothesis (The Efficient ASI Hypothesis); system-boundaries-and-authority (System Boundaries and Authority); failure-modes-of-ungoverned-intelligence (Failure Modes of Ungoverned Intelligence); stable-capability-fields (Stable Capability Fields); capability-replacement-and-rollback (Capability Replacement and Rollback); recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); planning-as-a-control-layer (Planning as a Control Layer: DAGs and Intelligence Arbitrage); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); labor-os-and-typed-jobs (Labor OS and Typed Jobs); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); integrated-reference-architecture (Integrated Reference Architecture); prototype-roadmap (Prototype Roadmap); living-book-methodology (Living Book Methodology); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; citation not normalized |
moecot_md |
moecot_agent_whitepaper.md | must_use_variant |
implementation_reference |
source | routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); prototype-roadmap (Prototype Roadmap); living-book-methodology (Living Book Methodology) | source note available; citation not normalized |
octopus_router |
Octopus Router Architecture | must_use |
routing_modular_intelligence |
source | routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); personal-compute-hives-and-federated-edge-intelligence (Personal Compute Hives and Federated Edge Intelligence); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); integrated-reference-architecture (Integrated Reference Architecture) | source note available; exact author manuscript readable in the live-book paper library |
rmi |
Ratcheting Modular Intelligence | must_use |
capability_ratchet |
source | the-efficient-asi-hypothesis (The Efficient ASI Hypothesis); capability-replacement-and-rollback (Capability Replacement and Rollback); recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); open-ended-improvement-engines (Open-Ended Improvement Engines); embodied-agency-real-time-control-and-physical-safety (Embodied Agency, Real-Time Control, and Physical Safety); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); replaceable-cognitive-substrates-beyond-transformer-monoculture (Replaceable Cognitive Substrates: Beyond Transformer Monoculture); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); personal-compute-hives-and-federated-edge-intelligence (Personal Compute Hives and Federated Edge Intelligence); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); fast-generation-architectures (Fast Generation Architectures); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); adversarial-evaluation-sandbagging-and-training-time-deception (Adversarial Evaluation, Sandbagging, and Training-Time Deception); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); integrated-reference-architecture (Integrated Reference Architecture); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
cognitive_loop_closure |
Cognitive Loop Closure | must_use |
procedural_memory |
source | capability-replacement-and-rollback (Capability Replacement and Rollback); open-ended-improvement-engines (Open-Ended Improvement Engines); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); embodied-agency-real-time-control-and-physical-safety (Embodied Agency, Real-Time Control, and Physical Safety); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); fast-generation-architectures (Fast Generation Architectures); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); adjudicated-persistence-and-the-adaptive-commit-boundary (Adjudicated Persistence and the Adaptive Commit Boundary); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); integrated-reference-architecture (Integrated Reference Architecture); living-book-methodology (Living Book Methodology) | source note available; exact author manuscript readable in the live-book paper library |
benchmaxxing |
Benchmaxxing: The Performance Ratchet | must_use |
benchmarks_evidence |
source | dangerous-capability-domains-and-misuse-uplift (Dangerous Capability Domains and Misuse Uplift); evidence-states-and-claim-discipline (Evidence States and Claim Discipline); capability-replacement-and-rollback (Capability Replacement and Rollback); recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); open-ended-improvement-engines (Open-Ended Improvement Engines); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); replaceable-cognitive-substrates-beyond-transformer-monoculture (Replaceable Cognitive Substrates: Beyond Transformer Monoculture); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); fast-generation-architectures (Fast Generation Architectures); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); capability-thresholds-and-deployment-commitments (Capability Thresholds and Deployment Commitments); adversarial-evaluation-sandbagging-and-training-time-deception (Adversarial Evaluation, Sandbagging, and Training-Time Deception); safety-cases-and-structured-assurance (Safety Cases and Structured Assurance); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); integrated-reference-architecture (Integrated Reference Architecture); prototype-roadmap (Prototype Roadmap); living-book-methodology (Living Book Methodology); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
cgs |
Compact Generative Systems | must_use |
compression_representation |
source | the-efficient-asi-hypothesis (The Efficient ASI Hypothesis); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); fast-generation-architectures (Fast Generation Architectures); rankfold-neuralfold-and-artifact-compression (RankFold, NeuralFold, and Artifact Compression); resource-economics-and-token-budgets (Resource Economics and Token Budgets); integrated-reference-architecture (Integrated Reference Architecture); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
rgs |
Ratcheting Generative Systems | supporting |
compression_capability_growth |
source | procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence) | source note available; exact author manuscript readable in the live-book paper library |
rankfold_neuralfold |
RankFold + NeuralFold | must_use |
compression_representation |
source | the-efficient-asi-hypothesis (The Efficient ASI Hypothesis); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); rankfold-neuralfold-and-artifact-compression (RankFold, NeuralFold, and Artifact Compression); resource-economics-and-token-budgets (Resource Economics and Token Budgets) | source note available; exact author manuscript readable in the live-book paper library |
rankfold_compressor |
rankFold compressor | must_use_variant |
compression_representation |
source | rankfold-neuralfold-and-artifact-compression (RankFold, NeuralFold, and Artifact Compression) | source note available; exact author manuscript readable in the live-book paper library |
bbvca_v9 |
BBVCA_v9_final_public_release | must_use |
compression_representation |
source | the-efficient-asi-hypothesis (The Efficient ASI Hypothesis); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); rankfold-neuralfold-and-artifact-compression (RankFold, NeuralFold, and Artifact Compression) | source note available; exact author manuscript readable in the live-book paper library |
bbvca_main |
Big Bang Volumetric Compression Architecture | must_use_variant |
compression_representation |
source | compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty) | source note available; exact author manuscript readable in the live-book paper library |
genesiscode |
GenesisCode | must_use |
executable_specification |
source | system-boundaries-and-authority (System Boundaries and Authority); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); labor-os-and-typed-jobs (Labor OS and Typed Jobs); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); mathematical-and-search-substrates (Mathematical and Search Substrates); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
alignment_field |
Field of God / Alignment Field family | must_use |
alignment_constitution |
source | constitutional-alignment-substrate (Constitutional Alignment: Agency, Dignity, and Corrigibility); inner-alignment-mesa-optimization-and-learned-objective-integrity (Inner Alignment, Mesa-Optimization, and Learned-Objective Integrity); moral-uncertainty-and-value-conflict (Moral Uncertainty, Value Conflict, and Contestable Governance); governed-objective-formation-value-learning-and-goal-integrity (Governed Objective Formation, Value Learning, and Goal Integrity); security-kernel-and-digital-scifs (Security Kernel and Digital SCIFs); recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); resource-economics-and-token-budgets (Resource Economics and Token Budgets); integrated-reference-architecture (Integrated Reference Architecture); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
field_of_god |
The Field of God | must_use_variant |
alignment_constitution |
source | failure-modes-of-ungoverned-intelligence (Failure Modes of Ungoverned Intelligence); constitutional-alignment-substrate (Constitutional Alignment: Agency, Dignity, and Corrigibility) | source note available; exact author manuscript readable in the live-book paper library |
field_of_god_ai_constitution |
Field of God AI Constitution | core_alignment_source |
constitutional_alignment_runtime_governance |
source | constitutional-alignment-substrate (Constitutional Alignment: Agency, Dignity, and Corrigibility); moral-uncertainty-and-value-conflict (Moral Uncertainty, Value Conflict, and Contestable Governance); recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); personal-compute-hives-and-federated-edge-intelligence (Personal Compute Hives and Federated Edge Intelligence); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; citation not normalized |
ethica_mechanica |
Ethica Mechanica | must_use_variant |
alignment_constitution |
source | constitutional-alignment-substrate (Constitutional Alignment: Agency, Dignity, and Corrigibility); moral-uncertainty-and-value-conflict (Moral Uncertainty, Value Conflict, and Contestable Governance) | source note available; exact author manuscript readable in the live-book paper library |
eternal_code |
The Eternal Code / unified God, reality, conscious, alignment | must_use_variant |
alignment_constitution |
source | constitutional-alignment-substrate (Constitutional Alignment: Agency, Dignity, and Corrigibility) | source note available; exact author manuscript readable in the live-book paper library |
coherence_exchange |
The Coherence Exchange | strong_support |
epistemic_market_synthesis |
source | evidence-states-and-claim-discipline (Evidence States and Claim Discipline); constitutional-alignment-substrate (Constitutional Alignment: Agency, Dignity, and Corrigibility); moral-uncertainty-and-value-conflict (Moral Uncertainty, Value Conflict, and Contestable Governance); institutions-international-coordination-and-public-legitimacy (Institutions, International Coordination, and Public Legitimacy); security-kernel-and-digital-scifs (Security Kernel and Digital SCIFs); planning-as-a-control-layer (Planning as a Control Layer: DAGs and Intelligence Arbitrage); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); ai-deployment-transition-distribution-and-human-agency (AI Deployment, Transition, Distribution, and Human Agency); multi-agent-dynamics-collective-intelligence-and-systemic-risk (Multi-Agent Dynamics, Collective Intelligence, and Systemic Risk); resource-economics-and-token-budgets (Resource Economics and Token Budgets); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); prototype-roadmap (Prototype Roadmap) | source note available; citation not normalized |
verification_bandwidth |
Verification Bandwidth in Bounded Contexts | strong_support |
context_verification_theory |
source | evidence-states-and-claim-discipline (Evidence States and Claim Discipline); scalable-oversight-and-adversarial-ai-control (Scalable Oversight and Adversarial AI Control); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); verification-bandwidth-and-context-adequacy (Verification Bandwidth and Context Adequacy); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); fast-generation-architectures (Fast Generation Architectures); governed-deliberation-and-test-time-scaling (Governed Deliberation and Test-Time Scaling); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
beastbrain |
BeastBrain Cognitive Architecture | supporting_lineage |
whole_stack_lineage |
source | asi-is-a-stack-not-a-model (ASI Is a Stack, Not a Model); the-efficient-asi-hypothesis (The Efficient ASI Hypothesis); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); governed-model-training-distributed-optimization-and-scaling (Governed Model Training, Distributed Optimization, and Scaling); personal-compute-hives-and-federated-edge-intelligence (Personal Compute Hives and Federated Edge Intelligence); prototype-roadmap (Prototype Roadmap) | source note available; exact author manuscript readable in the live-book paper library |
beastbrain_timeless |
BeastBrain Architecture: Timeless Edition | supporting_lineage |
whole_stack_lineage |
source | the-efficient-asi-hypothesis (The Efficient ASI Hypothesis); prototype-roadmap (Prototype Roadmap) | source note available; exact author manuscript readable in the live-book paper library |
aletheia |
Aletheia / Proof-Carrying Workbench Lineage | supporting_lineage |
safe_general_intelligence_lineage |
source | asi-is-a-stack-not-a-model (ASI Is a Stack, Not a Model); the-efficient-asi-hypothesis (The Efficient ASI Hypothesis); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); scientific-discovery-and-experimental-governance (Scientific Discovery and Experimental Governance) | source note available; exact author manuscript readable in the live-book paper library |
context_engineer |
Context Engineer / Manhattan Protocol | supporting_lineage |
memory_context_lineage |
source | security-kernel-and-digital-scifs (Security Kernel and Digital SCIFs); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint) | source note available; exact author manuscript readable in the live-book paper library |
black_hole_context_manager |
Black Hole Context Manager | supporting_lineage |
memory_context_lineage |
source | context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint) | source note available; exact author manuscript readable in the live-book paper library |
ladon_manhattan |
Ladon & The Manhattan Protocol | supporting_lineage |
security_governance |
source | system-boundaries-and-authority (System Boundaries and Authority); moral-uncertainty-and-value-conflict (Moral Uncertainty, Value Conflict, and Contestable Governance); stable-capability-fields (Stable Capability Fields); security-kernel-and-digital-scifs (Security Kernel and Digital SCIFs); context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); personal-compute-hives-and-federated-edge-intelligence (Personal Compute Hives and Federated Edge Intelligence) | source note available; exact author manuscript readable in the live-book paper library |
uat |
Unified Adaptive Tribunal | supporting_lineage |
evaluation_refinement |
source | evidence-states-and-claim-discipline (Evidence States and Claim Discipline); moral-uncertainty-and-value-conflict (Moral Uncertainty, Value Conflict, and Contestable Governance); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence) | source note available; exact author manuscript readable in the live-book paper library |
treellm |
TreeLLM | supporting_lineage |
semantic_representation |
source | cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); durable-semantic-memory-and-knowledge-lattices (Durable Semantic Memory and Knowledge Lattices); verification-bandwidth-and-context-adequacy (Verification Bandwidth and Context Adequacy); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); mathematical-and-search-substrates (Mathematical and Search Substrates) | source note available; exact author manuscript readable in the live-book paper library |
software_magic_grimoire |
The Grimoire of Software Magic Words: Operative Vocabulary, Prompt-Spells, and Stacked Workflows | supporting_lineage |
command_contracts_promptcraft |
source | human-intent-as-a-formal-input (Human Intent as a Formal Input); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); planning-as-a-control-layer (Planning as a Control Layer: DAGs and Intelligence Arbitrage); labor-os-and-typed-jobs (Labor OS and Typed Jobs); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval) | source note available; exact author manuscript readable in the live-book paper library |
road_to_agi |
Road To AGI | supporting_lineage |
strategic_roadmap |
source | benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); prototype-roadmap (Prototype Roadmap); living-book-methodology (Living Book Methodology); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; citation not normalized |
simulation_scaling |
The Simulation Scaling Law: Resource Constraints on Scope, Clockspeed, and Effective Fidelity in Nested Physical Simulations | optional_support |
compute_fidelity_constraints |
source | the-efficient-asi-hypothesis (The Efficient ASI Hypothesis); failure-modes-of-ungoverned-intelligence (Failure Modes of Ungoverned Intelligence); governed-world-models-and-reality-grounding (Governed World Models and Reality Grounding); learning-theory-generalization-and-scaling-science (Learning Theory, Generalization, and Scaling Science); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); resource-economics-and-token-budgets (Resource Economics and Token Budgets); mathematical-and-search-substrates (Mathematical and Search Substrates); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
tokenmana |
TokenMana | optional_support |
resource_economics |
source | planning-as-a-control-layer (Planning as a Control Layer: DAGs and Intelligence Arbitrage); inter-stack-protocols-identity-and-economic-exchange (Inter-Stack Protocols, Identity, and Economic Exchange); personal-compute-hives-and-federated-edge-intelligence (Personal Compute Hives and Federated Edge Intelligence); fast-generation-architectures (Fast Generation Architectures); resource-economics-and-token-budgets (Resource Economics and Token Budgets); physical-compute-infrastructure-energy-and-environmental-constraints (Physical Compute Infrastructure, Energy, and Environmental Constraints); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance) | source note available; exact author manuscript readable in the live-book paper library |
coilmoecot |
CoilMoECOT Whitepaper v2.0 | optional_technical_appendix |
mathematical_search_substrate |
source | routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); mathematical-and-search-substrates (Mathematical and Search Substrates); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; citation not normalized |
temporal_coil_research |
Temporal Coil Research | optional_technical_appendix |
mathematical_search_substrate |
source | mathematical-and-search-substrates (Mathematical and Search Substrates); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence) | source note available; citation not normalized |
bugbrain |
BugBrain / Project Genesis: Neuro-Symbolic Bare-Metal Edge Intelligence Paper Lineage | optional_support |
edge_efficiency_lineage |
source | compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); rankfold-neuralfold-and-artifact-compression (RankFold, NeuralFold, and Artifact Compression); prototype-roadmap (Prototype Roadmap); living-book-methodology (Living Book Methodology) | source note available; exact author manuscript readable in the live-book paper library |
cca_project |
Compiled Cognitive Architecture project | implementation_reference |
compiled_cognitive_architecture |
local project reference (not publicly linked) | system-boundaries-and-authority (System Boundaries and Authority); evidence-states-and-claim-discipline (Evidence States and Claim Discipline); model-weight-custody-and-hardware-roots-of-trust (Model-Weight Custody and Hardware Roots of Trust); ai-supply-chain-integrity-and-lifecycle-provenance (AI Supply-Chain Integrity and Lifecycle Provenance); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); integrated-reference-architecture (Integrated Reference Architecture) | source note available; citation not normalized |
moecot_manifest_project |
MoECOT Manifest compiler-era project | implementation_reference |
compiler_first_ai_systems |
local project reference (not publicly linked) | system-boundaries-and-authority (System Boundaries and Authority); evidence-states-and-claim-discipline (Evidence States and Claim Discipline); security-kernel-and-digital-scifs (Security Kernel and Digital SCIFs); ai-supply-chain-integrity-and-lifecycle-provenance (AI Supply-Chain Integrity and Lifecycle Provenance); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); integrated-reference-architecture (Integrated Reference Architecture) | source note available; citation not normalized |
beastbrain_project |
BeastBrain historical AI system project | implementation_reference |
durable_semantic_memory_and_system_architecture |
local project reference (not publicly linked) | system-boundaries-and-authority (System Boundaries and Authority); evidence-states-and-claim-discipline (Evidence States and Claim Discipline); security-kernel-and-digital-scifs (Security Kernel and Digital SCIFs); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence) | source note available; citation not normalized |
bugbrain_project |
BugBrain bare-metal neuro-symbolic intelligence project | implementation_reference |
hardware_explicit_governed_cognition |
local project reference (not publicly linked) | system-boundaries-and-authority (System Boundaries and Authority); evidence-states-and-claim-discipline (Evidence States and Claim Discipline); security-kernel-and-digital-scifs (Security Kernel and Digital SCIFs); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); integrated-reference-architecture (Integrated Reference Architecture) | source note available; citation not normalized |
corbens_trainer_project |
Corben’s Trainer epistemic training and evaluation control plane | implementation_reference |
epistemic_training_and_evaluation_control_plane |
local project reference (not publicly linked) | system-boundaries-and-authority (System Boundaries and Authority); evidence-states-and-claim-discipline (Evidence States and Claim Discipline); security-kernel-and-digital-scifs (Security Kernel and Digital SCIFs); ai-supply-chain-integrity-and-lifecycle-provenance (AI Supply-Chain Integrity and Lifecycle Provenance); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); governed-model-training-distributed-optimization-and-scaling (Governed Model Training, Distributed Optimization, and Scaling); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); integrated-reference-architecture (Integrated Reference Architecture) | source note available; citation not normalized |
corbens_best_model_possible_project |
Corben’s Best Model Possible recurrent-model and mechanism laboratory | implementation_reference |
recurrent_model_mechanisms_and_capability_evidence |
local project reference (not publicly linked) | system-boundaries-and-authority (System Boundaries and Authority); evidence-states-and-claim-discipline (Evidence States and Claim Discipline); security-kernel-and-digital-scifs (Security Kernel and Digital SCIFs); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); integrated-reference-architecture (Integrated Reference Architecture) | source note available; citation not normalized |
project_theseus_whitepaper |
Project Theseus Whitepaper | implementation_reference |
report_first_rmi_prototype |
source | procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); personal-compute-hives-and-federated-edge-intelligence (Personal Compute Hives and Federated Edge Intelligence); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); resource-economics-and-token-budgets (Resource Economics and Token Budgets); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); integrated-reference-architecture (Integrated Reference Architecture); project-theseus-as-report-first-implementation-reference (Project Theseus as Report-First Implementation Reference); prototype-roadmap (Prototype Roadmap); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; citation not normalized |
theseus_plan_compiler |
Theseus Plan Compiler | implementation_reference |
planning_control |
source | integrated-reference-architecture (Integrated Reference Architecture); project-theseus-as-report-first-implementation-reference (Project Theseus as Report-First Implementation Reference); prototype-roadmap (Prototype Roadmap) | source note available; citation not normalized |
theseus_self_evolution_system |
Theseus Self-Evolution System | implementation_reference |
recursive_self_improvement_governance |
source | recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); integrated-reference-architecture (Integrated Reference Architecture); project-theseus-as-report-first-implementation-reference (Project Theseus as Report-First Implementation Reference); prototype-roadmap (Prototype Roadmap) | source note available; citation not normalized |
theseus_architecture_gate |
Theseus Architecture Gate | implementation_reference |
readiness_gate_governance |
source | recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); capability-thresholds-and-deployment-commitments (Capability Thresholds and Deployment Commitments); integrated-reference-architecture (Integrated Reference Architecture); project-theseus-as-report-first-implementation-reference (Project Theseus as Report-First Implementation Reference); prototype-roadmap (Prototype Roadmap) | source note available; citation not normalized |
theseus_operator_os |
Hive Operator OS and Work Board | implementation_reference |
labor_os_operator_surface |
source | human-factors-and-meaningful-control-in-oversight (Human Factors and Meaningful Control in Oversight); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); personal-compute-hives-and-federated-edge-intelligence (Personal Compute Hives and Federated Edge Intelligence); governed-operations-incident-command-and-graceful-degradation (Governed Operations, Incident Command, and Graceful Degradation); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance); integrated-reference-architecture (Integrated Reference Architecture); project-theseus-as-report-first-implementation-reference (Project Theseus as Report-First Implementation Reference); prototype-roadmap (Prototype Roadmap) | source note available; citation not normalized |
theseus_circle_transfer |
Theseus Circle Calculus Transfer Lane | implementation_reference |
proof_contract_transfer |
source | mathematical-and-search-substrates (Mathematical and Search Substrates); coil-attention-cyclic-memory-and-recurrence-contracts (Coil Attention, Cyclic Memory, and Recurrence Contracts); coilra-multicoil-rope-and-cyclic-mixers (CoilRA, MultiCoil RoPE, and Cyclic Mixers); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); integrated-reference-architecture (Integrated Reference Architecture); project-theseus-as-report-first-implementation-reference (Project Theseus as Report-First Implementation Reference); prototype-roadmap (Prototype Roadmap); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; citation not normalized |
circle_calculus_core |
Circle Calculus | core_technical_source |
proof_carrying_mathematical_substrate |
source | mathematical-and-search-substrates (Mathematical and Search Substrates); circle-calculus-and-proof-carrying-ai-contracts (Circle Calculus and Proof-Carrying AI Contracts); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; citation not normalized |
circle_ai_contract_suite |
Circle Calculus AI Contract Suite | core_technical_source |
proof_carrying_ai_contracts |
source | circle-calculus-and-proof-carrying-ai-contracts (Circle Calculus and Proof-Carrying AI Contracts); coil-attention-cyclic-memory-and-recurrence-contracts (Coil Attention, Cyclic Memory, and Recurrence Contracts); coilra-multicoil-rope-and-cyclic-mixers (CoilRA, MultiCoil RoPE, and Cyclic Mixers); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope); prototype-roadmap (Prototype Roadmap); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; citation not normalized |
circle_ai_architectures |
Circle AI Architectures | core_technical_source |
cyclic_ai_architecture |
source | compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); mathematical-and-search-substrates (Mathematical and Search Substrates); circle-calculus-and-proof-carrying-ai-contracts (Circle Calculus and Proof-Carrying AI Contracts); coilra-multicoil-rope-and-cyclic-mixers (CoilRA, MultiCoil RoPE, and Cyclic Mixers) | source note available; citation not normalized |
coil_attention_memory |
Coil Attention and Memory | core_technical_source |
cyclic_attention_memory |
source | coil-attention-cyclic-memory-and-recurrence-contracts (Coil Attention, Cyclic Memory, and Recurrence Contracts) | source note available; citation not normalized |
coilra_multicoil_rope |
CoilRA and MultiCoil RoPE | core_technical_source |
cyclic_mixers_position_encoding |
source | compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); resource-economics-and-token-budgets (Resource Economics and Token Budgets); coilra-multicoil-rope-and-cyclic-mixers (CoilRA, MultiCoil RoPE, and Cyclic Mixers) | source note available; citation not normalized |
rope_position_certifier |
Proof-Carrying RoPE Position Distinguishability | core_technical_source |
proof_carrying_position_contract |
source | circle-calculus-and-proof-carrying-ai-contracts (Circle Calculus and Proof-Carrying AI Contracts); coilra-multicoil-rope-and-cyclic-mixers (CoilRA, MultiCoil RoPE, and Cyclic Mixers); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope) | source note available; citation not normalized |
proof_carrying_circular_computation |
Proof-Carrying Circular Computation | supporting_technical_source |
proof_carrying_compute_substrate |
source | mathematical-and-search-substrates (Mathematical and Search Substrates); circle-calculus-and-proof-carrying-ai-contracts (Circle Calculus and Proof-Carrying AI Contracts); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope) | source note available; citation not normalized |
theseus_synthetic_data_curation |
Theseus Synthetic Data Curation | implementation_reference |
governed_synthetic_data_admission |
local project reference (not publicly linked) | privacy-data-rights-and-information-flow-governance (Privacy, Data Rights, and Information-Flow Governance); data-engines-continual-learning-and-unlearning (Data Engines, Continual Learning, and Unlearning) | source note available; citation not normalized |
qcsa_whitepaper |
Question-Compiled Semantic Addressing | must_use |
semantic_addressing_control_plane |
source | governed-world-models-and-reality-grounding (Governed World Models and Reality Grounding); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); durable-semantic-memory-and-knowledge-lattices (Durable Semantic Memory and Knowledge Lattices); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); inter-stack-protocols-identity-and-economic-exchange (Inter-Stack Protocols, Identity, and Economic Exchange); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); white-box-evidence-interpretability-and-activation-governance (White-Box Evidence, Interpretability, and Activation Governance); data-engines-continual-learning-and-unlearning (Data Engines, Continual Learning, and Unlearning); integrated-reference-architecture (Integrated Reference Architecture) | source note available; exact author manuscript readable in the live-book paper library |
reflexive_router_whitepaper |
The Reflexive Router: A Pre-Deliberative Architecture for Fast, Governed, Tool-Native Intelligence | must_use |
pre_deliberative_reflexive_routing_control_plane |
source | stable-capability-fields (Stable Capability Fields); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); planning-as-a-control-layer (Planning as a Control Layer: DAGs and Intelligence Arbitrage); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); resource-economics-and-token-budgets (Resource Economics and Token Budgets); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); integrated-reference-architecture (Integrated Reference Architecture) | source note available; exact author manuscript readable in the live-book paper library |
corben_chatgpt_kiss_irreducible_intelligence_2026 |
KISS versus Irreducible Intelligence (author-supplied design conversation) | supporting |
author_intent_replaceable_cognitive_substrates |
source | replaceable-cognitive-substrates-beyond-transformer-monoculture (Replaceable Cognitive Substrates: Beyond Transformer Monoculture) | source note available; citation not normalized |
corben_chatgpt_onecell_theseus_2026 |
OneCell and Theseus Architecture Handoff (author-supplied design conversation) | supporting |
author_intent_onecell_and_architectural_rsi |
source | replaceable-cognitive-substrates-beyond-transformer-monoculture (Replaceable Cognitive Substrates: Beyond Transformer Monoculture) | source note available; citation not normalized |
kernel_english_residual_compiler |
Kernel English with Hierarchical, Interaction-Amortized Residuals: A Dual-Vocabulary Cognitive Compiler for Efficient Language-Model Reasoning | must_use |
canonical_cognitive_compilation_and_hierarchical_residual_runtime |
source | security-kernel-and-digital-scifs (Security Kernel and Digital SCIFs); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint); verification-bandwidth-and-context-adequacy (Verification Bandwidth and Context Adequacy); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); replaceable-cognitive-substrates-beyond-transformer-monoculture (Replaceable Cognitive Substrates: Beyond Transformer Monoculture); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); fast-generation-architectures (Fast Generation Architectures); resource-economics-and-token-budgets (Resource Economics and Token Budgets); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); white-box-evidence-interpretability-and-activation-governance (White-Box Evidence, Interpretability, and Activation Governance); integrated-reference-architecture (Integrated Reference Architecture) | source note available; exact author manuscript readable in the live-book paper library |
deterministic_capability_compilation |
Deterministic Capability Compilation: A Capability-Preserving Ladder from Executable Scaffolds to Governed Adaptive Agents | must_use |
capability_compilation_neural_linking_and_governed_adaptation |
source | stable-capability-fields (Stable Capability Fields); capability-replacement-and-rollback (Capability Replacement and Rollback); adversarial-machine-learning-and-model-attack-surface (Adversarial Machine Learning and the Model Attack Surface); ai-supply-chain-integrity-and-lifecycle-provenance (AI Supply-Chain Integrity and Lifecycle Provenance); recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); autonomous-replication-proliferation-and-containment (Autonomous Replication, Proliferation, and Containment); intent-to-execution-contracts (Command Contracts: From Intent to Executable Work); governed-world-models-and-reality-grounding (Governed World Models and Reality Grounding); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); labor-os-and-typed-jobs (Labor OS and Typed Jobs); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); replaceable-cognitive-substrates-beyond-transformer-monoculture (Replaceable Cognitive Substrates: Beyond Transformer Monoculture); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); white-box-evidence-interpretability-and-activation-governance (White-Box Evidence, Interpretability, and Activation Governance); content-authenticity-watermarking-and-synthetic-media-integrity (Content Authenticity, Watermarking, and Synthetic Media Integrity); governed-operations-incident-command-and-graceful-degradation (Governed Operations, Incident Command, and Graceful Degradation); adjudicated-persistence-and-the-adaptive-commit-boundary (Adjudicated Persistence and the Adaptive Commit Boundary); data-engines-continual-learning-and-unlearning (Data Engines, Continual Learning, and Unlearning); integrated-reference-architecture (Integrated Reference Architecture); project-theseus-as-report-first-implementation-reference (Project Theseus as Report-First Implementation Reference); prototype-roadmap (Prototype Roadmap); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
platonic_world_model |
The Platonic World Model: A Semantic Constitution for Grounded, Proof-Carrying, Self-Editing Artificial Intelligence | must_use |
semantic_continuity_grounded_world_model_and_governed_self_editing |
source | moral-uncertainty-and-value-conflict (Moral Uncertainty, Value Conflict, and Contestable Governance); security-kernel-and-digital-scifs (Security Kernel and Digital SCIFs); ai-supply-chain-integrity-and-lifecycle-provenance (AI Supply-Chain Integrity and Lifecycle Provenance); recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); perception-sensor-fusion-and-observation-trust (Perception, Sensor Fusion, and Observation Trust); planning-as-a-control-layer (Planning as a Control Layer: DAGs and Intelligence Arbitrage); governed-world-models-and-reality-grounding (Governed World Models and Reality Grounding); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); virtual-context-abi (The Virtual Context ABI: Typed Pages, Cells, and Certificates); context-transactions-snapshots-mounts-and-taint (Context Transactions, Snapshots, Mounts, and Taint); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); spinoza-verification-and-proof-carrying-claims (Proof-Carrying Claims and Adversarial Review); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); runtime-adapters-tool-permissions-and-human-approval (Runtime Adapters, Tool Permissions, and Human Approval); inter-stack-protocols-identity-and-economic-exchange (Inter-Stack Protocols, Identity, and Economic Exchange); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); white-box-evidence-interpretability-and-activation-governance (White-Box Evidence, Interpretability, and Activation Governance); governed-operations-incident-command-and-graceful-degradation (Governed Operations, Incident Command, and Graceful Degradation); adjudicated-persistence-and-the-adaptive-commit-boundary (Adjudicated Persistence and the Adaptive Commit Boundary); data-engines-continual-learning-and-unlearning (Data Engines, Continual Learning, and Unlearning); integrated-reference-architecture (Integrated Reference Architecture); prototype-roadmap (Prototype Roadmap); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
relational_dimension_compiler |
The Relational Dimension Compiler: Adaptive Polyadic Cognition with Bounded Computational Arity and Unbounded Semantic Structure | must_use |
typed_relational_ir_adaptive_polyadic_routing_and_reversible_abstraction |
source | governed-world-models-and-reality-grounding (Governed World Models and Reality Grounding); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); replaceable-cognitive-substrates-beyond-transformer-monoculture (Replaceable Cognitive Substrates: Beyond Transformer Monoculture); relational-dimension-compilation-and-polyadic-cognition (Relational Dimension Compilation and Polyadic Cognition); resource-economics-and-token-budgets (Resource Economics and Token Budgets); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); integrated-reference-architecture (Integrated Reference Architecture); open-research-agenda-and-bibliography-plan (Open Research Agenda and Bibliography Plan) | source note available; exact author manuscript readable in the live-book paper library |
precision_contract |
The Precision Contract: A Functional Rate–Distortion Theory for Behavior-Preserving Neural Computation | must_use |
functional_precision_behavior_preserving_compression_and_certification |
source | the-efficient-asi-hypothesis (The Efficient ASI Hypothesis); model-weight-custody-and-hardware-roots-of-trust (Model-Weight Custody and Hardware Roots of Trust); open-weight-release-and-post-release-control (Open-Weight Release and Post-Release Control); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty); fast-generation-architectures (Fast Generation Architectures); rankfold-neuralfold-and-artifact-compression (RankFold, NeuralFold, and Artifact Compression); resource-economics-and-token-budgets (Resource Economics and Token Budgets); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope) | source note available; exact author manuscript readable in the live-book paper library |
portia_synapse |
PortiaSynapse: A Cognitive Spider Architecture for DKL Navigation | supporting_lineage |
routing_training_and_dkl_navigation |
source | durable-semantic-memory-and-knowledge-lattices (Durable Semantic Memory and Knowledge Lattices); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); governed-deliberation-and-test-time-scaling (Governed Deliberation and Test-Time Scaling); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback) | source note available; exact author manuscript readable in the live-book paper library |
spider_synapse |
SpiderSynapse: A Multi-Hypothesis Reasoning Architecture | supporting_lineage |
routing_training_and_dkl_navigation |
source | routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); governed-deliberation-and-test-time-scaling (Governed Deliberation and Test-Time Scaling); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback) | source note available; exact author manuscript readable in the live-book paper library |
capability_ratchet_whitepaper |
The Capability Ratchet | supporting_lineage |
capability_ratchet |
source | capability-replacement-and-rollback (Capability Replacement and Rollback); recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence) | source note available; citation not normalized |
attd |
Assembly-Theoretic Technical Debt: A Deterministic Outer Loop for Self-Improving Codebases | supporting |
living_project_governance |
source | recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); artifact-steward-agents-and-living-project-governance (Artifact Steward Agents and Living Project Governance) | source note available; citation not normalized |
orcp_moecot |
ORCP–MoECOT: A Governed Oscillating Rail Cascade Codec | supporting |
deterministic_compression |
source | compact-generative-systems-and-residual-honesty (Compact Generative Systems: Generate, Verify, Repair, and Residual Honesty) | source note available; citation not normalized |
regret_engine |
The Regret Engine: Governed Counterfactual Learning Signals for Continual Adaptation, Prospective Risk Control, and Self-Correction in Artificial Agents | must_use |
governed_counterfactual_learning_and_self_correction |
source | planning-as-a-control-layer (Planning as a Control Layer: DAGs and Intelligence Arbitrage); claim-ledgers-and-belief-revision (Claim Ledgers and Belief Revision); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); governed-operations-incident-command-and-graceful-degradation (Governed Operations, Incident Command, and Graceful Degradation); adjudicated-persistence-and-the-adaptive-commit-boundary (Adjudicated Persistence and the Adaptive Commit Boundary); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); data-engines-continual-learning-and-unlearning (Data Engines, Continual Learning, and Unlearning); integrated-reference-architecture (Integrated Reference Architecture) | source note available; exact author manuscript readable in the live-book paper library |
learning_compute_topology |
Learning–Compute Topology: Formalizing the Causal Organization of Adaptive Systems | must_use |
adaptive_process_architecture_and_learning_topology |
source | open-ended-improvement-engines (Open-Ended Improvement Engines); multi-agent-dynamics-collective-intelligence-and-systemic-risk (Multi-Agent Dynamics, Collective Intelligence, and Systemic Risk); routing-heads-and-specialist-cores (Routing Heads and Specialist Cores); replaceable-cognitive-substrates-beyond-transformer-monoculture (Replaceable Cognitive Substrates: Beyond Transformer Monoculture); governed-model-training-distributed-optimization-and-scaling (Governed Model Training, Distributed Optimization, and Scaling); learning-compute-topology-and-adaptive-process-architecture (Learning–Compute Topology and Adaptive Process Architecture); resource-economics-and-token-budgets (Resource Economics and Token Budgets); adversarial-evaluation-sandbagging-and-training-time-deception (Adversarial Evaluation, Sandbagging, and Training-Time Deception); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); data-engines-continual-learning-and-unlearning (Data Engines, Continual Learning, and Unlearning); integrated-reference-architecture (Integrated Reference Architecture) | source note available; exact author manuscript readable in the live-book paper library |
assurance_shift_learning |
When Success Stops Teaching: Assurance-Shift Learning and Governed Residual Boundary Learning for Mature AI Systems | must_use |
competence_dependent_assurance_shift_and_residual_boundary_learning |
source | evidence-states-and-claim-discipline (Evidence States and Claim Discipline); stable-capability-fields (Stable Capability Fields); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); learning-compute-topology-and-adaptive-process-architecture (Learning–Compute Topology and Adaptive Process Architecture); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); resource-economics-and-token-budgets (Resource Economics and Token Budgets); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); adversarial-evaluation-sandbagging-and-training-time-deception (Adversarial Evaluation, Sandbagging, and Training-Time Deception); governed-operations-incident-command-and-graceful-degradation (Governed Operations, Incident Command, and Graceful Degradation); adjudicated-persistence-and-the-adaptive-commit-boundary (Adjudicated Persistence and the Adaptive Commit Boundary); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); data-engines-continual-learning-and-unlearning (Data Engines, Continual Learning, and Unlearning); integrated-reference-architecture (Integrated Reference Architecture) | source note available; exact author manuscript readable in the live-book paper library |
adjudicated_persistence |
Adjudicated Persistence: Governing the Transition from Experience to Durable Structure in Adaptive Systems | must_use |
governed_cross_surface_persistence_and_adaptive_commit_boundary |
source | evidence-states-and-claim-discipline (Evidence States and Claim Discipline); stable-capability-fields (Stable Capability Fields); recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); cognitive-compilation-and-semantic-ir (Cognitive Compilation and Semantic IR); durable-semantic-memory-and-knowledge-lattices (Durable Semantic Memory and Knowledge Lattices); human-ai-organizations-delegation-and-accountability (Human-AI Organizations, Delegation, and Accountability); artifact-graphs-audit-logs-and-replay (Artifact Graphs, Audit Logs, and Replay); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); readiness-gates-residual-escrow-and-quarantine (Readiness Gates, Residual Escrow, and Quarantine); resource-economics-and-token-budgets (Resource Economics and Token Budgets); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); governed-operations-incident-command-and-graceful-degradation (Governed Operations, Incident Command, and Graceful Degradation); adjudicated-persistence-and-the-adaptive-commit-boundary (Adjudicated Persistence and the Adaptive Commit Boundary); policy-optimization-and-learning-from-feedback (Policy Optimization and Learning from Feedback); data-engines-continual-learning-and-unlearning (Data Engines, Continual Learning, and Unlearning); integrated-reference-architecture (Integrated Reference Architecture) | source note available; exact author manuscript readable in the live-book paper library |
forward_transfer_program_synthesis |
From Compression to Forward Transfer: Evaluating Reusable Knowledge in Program Synthesis | must_use |
verified_forward_transfer_and_reusable_knowledge_evaluation |
source | recursive-self-improvement-boundaries (Recursive Self-Improvement Boundaries); procedural-memory-and-cognitive-loop-closure (Procedural Memory and Cognitive Loop Closure); learning-theory-generalization-and-scaling-science (Learning Theory, Generalization, and Scaling Science); rankfold-neuralfold-and-artifact-compression (RankFold, NeuralFold, and Artifact Compression); resource-economics-and-token-budgets (Resource Economics and Token Budgets); executable-specifications-and-lean-proof-envelope (Executable Specifications and Lean Proof Envelope); benchmark-ratchets-and-anti-goodhart-evidence (Benchmark Ratchets and Anti-Goodhart Evidence); adjudicated-persistence-and-the-adaptive-commit-boundary (Adjudicated Persistence and the Adaptive Commit Boundary) | source note available; exact author manuscript readable in the live-book paper library |
G.4 Citation Policy
- Use stable source IDs for supplied corpus references until full citation metadata exists.
- Do not infer authors, dates, venues, versions, or publication status from titles alone.
- Do not cite a source as supporting a claim until its text has been ingested and a source note exists.
- Keep speculative or design-synthesis claims labeled as
argumentuntil source, prototype, or test evidence justifies promotion.