Standing Framework

Writing index

Research papers

Browse research papers by title, author, date, and abstract.

Thirty-one research papers

  1. 01 Evidence-Bound Evaluation: A Methods and Corpus Report for AI Workflow Artifacts
  2. 02 Metrics Are Not Authority: Control Boundaries for Agentic Evaluation Systems
  3. 03 Evidence Ledger Data Descriptor: A Case-Record Package for AI Workflow Evaluation
  4. 04 From Receipt to Non-Authority Trace: Evidence Transit Without Claim Promotion
  5. 05 From Benchmark Rows to Runtime Invariants: Evidence-to-Fix Promotion for AI Agent Systems
  6. 06 Evidence Packets for Agent Benchmarks: Denominator, Coverage, and Improvement Ownership Across Nine Benchmark Runs
  7. 07 When Governance Context Hurts: Negative Results in Agent Decision Support
  8. 08 Authority Should Expire: Qualification Leases for Agentic Systems
  9. 09 Contraction-Gated Agent Work
  10. 10 From Public Records to Publication Claims: A Human-Reviewed Evidence Promotion Pipeline
  11. 11 Telemetry Without Authority: Roughness and Lacunarity as Scout Signals for Agent Context
  12. 12 Proof-Preserving Ref Drift Recovery: Agentic Worktree Incidents as Evidence Objects
  13. 13 Publishability Control Plane: Separating Local Proof, Evidence Acceptance, and Public Release
  14. 14 A Longitudinal Corpus of Human-Codex Software Work
  15. 15 Proof-Carrying Development: Agentic Code Work as Claims With Attached Evidence
  16. 16 Cached Context Infrastructure: Treating Reused Agent Context as a Governed Development Surface
  17. 17 Tool Calls Are the Medium: Agentic Coding as Human-Agent-Tool Choreography
  18. 18 The Human Prompt as an Operating System for Agentic Development
  19. 19 Failures, Blockers, and Honest Stop Rules in AI Coding Logs
  20. 20 Portfolio-Scale Agentic Development Ecology: A Longitudinal Single-Operator Study
  21. 21 Authority Engineering Language: A Machine-Readable Contract for Legitimate Action
  22. 22 Switchboard Harness DSL: Runtime Lab Scenario Packets as Governed Agent Work Contracts
  23. 23 Harness Search Under Governance: Optimizing Agent Scaffolds Without Losing Proof Boundaries
  24. 24 Lean Acceptance Is Not Semantic Acceptance: Lessons From a Formal Conjectures Internal Run
  25. 26 Signal Box Evidence Ladder: From Dogfood Packets to Benchmark-Style Review Corpora
  26. 27 Plugin Runtime Trust Boundaries for Governed Agent Systems
  27. 28 Local Model Admission as Governed Infrastructure
  28. 29 Graph-Native Manuscript Development: Claim Bundles, Evidence Anchors, and Verification Reports
  29. 30 Shipability as Evidence: Product Release Readiness Without Launch Overclaim
  30. 31 Agentic Temporal Compression: Iteration Density and Retrospective Distance in AI-Assisted Software Development
  31. 32 Operational Graphs for Agentic Work: Context, Evidence, Authority, and Verification
← Back to Writing