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