Replication package for "Directing the Machine: A Single-Case Study of Verification When an AI Agent Cannot Reach the Oracle"
收藏资源简介:
Privacy-scrubbed replication package for a single-case study of a non-domain-expert directing an agentic LLM to build a cross-engine game-asset conversion pipeline. Contains the derived interaction event log (5,575 events over 10 sessions; text lengths only, never message text), summary statistics, the coded failure/reversal episode catalogue (13 episodes, 5-dimension codebook) with per-episode verbatim transcript excerpts, the coding scheme, a reproducibility appendix (tool and version inventory), a per-component walkthrough of the net-new code, and the stdlib-only analysis scripts. No raw transcripts and no game assets are included; scrubbing policy in PRIVACY_NOTES.md. Supplements a manuscript under submission at Information and Software Technology.



