2026-10-10T17:23:59Z https://www.scidb.cn/oai

10.57760/sciencedb.46407 2026-08-21T17:12:34Z

2026-08-21 Agent Approval Laundering: An Approval-to-Action Trace Benchmark and Reproducibility Dataset doi:10.57760/sciencedb.46407 en This dataset supports the study “Agent Approval Laundering: Transitive Effects Beyond the Approved Invocation.” It examines a structural record-coverage failure in AI coding agents: an approval record may accurately identify the surface command or tool call while omitting the transitive effects activated by the underlying workflow. The dataset contains an append-only ledger of 149 execution attempts and 149 corresponding hash-bound run snapshots, including 139 successful runs. Its primary benchmark view comprises 111 deduplicated successful agent-task records. It also provides 78 reproducible analytical views covering captured approval objects, decision-time metadata, post-execution traces and artifact evidence, fixed-commit real-project cases, prospective holdout experiments, independent oracle reconstruction, and effect-bound approval evaluation. Raw evidence is kept immutable and separated from regenerated analyses; manifests and SHA-256 digests support integrity checking and reproduction of the study’s principal results. The dataset can be used to measure approval-record coverage, compare record representations, and evaluate mechanisms that bind predicted transitive effects and provenance before authorization. approval laundering; approval records; transitive effects; systems security 张晋千 RESTRICTED dataset Science Data Bank