SOURCE-LINKED INTELLIGENCE

Between the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebase

arXiv · AI, language, vision and robotics · article · Sep 24, 2026 · UTC

We present: (i) a new dataset consisting of the full development history of a 21,000-line Python tool built entirely by Claude AI, with no human-authored code or tests, (ii) two code-provenance tracing tools, (iii) three taxonomies for instruction intent, commit provenance, and response reliability, (iv) application of these to analyse the dataset. We find that: (i) user coding agent CLI instructions differ in kind from IDE-chat instructions, with a greater focus on comprehension, planning and consultation, (ii) code development is mainly proactive, (iii) 14.3% of AI code-generation events con

Read original source ↗ Open in workspace

recordType

paper

region

Global