Metraipolis › archive › dc_54536114fc2a
From Experiments to Decisions: Reusing Evidence in Autonomous Coding Research — arXiv:2609.13299
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13299
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:30:58.936Z
- SHA-256 of the archived text
cb0fc50410400c7e61fcf09e9576dd4af7f233925e7f18f6e9867a8370a540cd- Stable URL of this page
https://metraipolis.com/documento/dc_54536114fc2a
How to cite
From Experiments to Decisions: Reusing Evidence in Autonomous Coding Research — arXiv:2609.13299 — arXiv (en), https://arxiv.org/abs/2609.13299 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_54536114fc2a (Metraipolis archive dc_54536114fc2a, sha256 cb0fc50410400c7e61fcf09e9576dd4af7f233925e7f18f6e9867a8370a540cd)
BibTeX
@misc{dc54536114fc2a,
title = {From Experiments to Decisions: Reusing Evidence in Autonomous Coding Research — arXiv:2609.13299},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13299},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_54536114fc2a; sha256 cb0fc50410400c7e61fcf09e9576dd4af7f233925e7f18f6e9867a8370a540cd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13299. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Autonomous coding agents can remember an experiment yet carry forward a conclusion it does not justify. We reconstruct how evidence is reused in a 400-task NeuroGolf campaign, with selected wellbore-prediction records from the same operator as cross-domain comparisons. A numerical counterexample exposes an overbroad exclusion; other episodes distinguish what failed, incomplete and revised programs justify doing next. The wellbore records reveal an additional weakness: a coordinator correctly acknowledges a novelty-only rejection, then summarizes it as measured closure. Separately, a prefix-based acceptance gate at three thresholds yields worse target scores than ungated adaptation in the retained experiment. These cases motivate an inspectable handoff linking the tested proposition, its scope, candidate and evaluator identity, check statuses, and reopening condition. A dispatch tree separates investigation, repair, reopening and stopping; a promotion predicate requires that each check both passes and has evidence supporting its use for the requested decision. The practical lesson is to preserve not just experimental results, but their limits on subsequent action. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-15 in cs.SE). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2609.13299 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T00:12:31.083Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).