Metraipolis › archive › dc_8a2b4cf2cdc2

Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents — arXiv:2609.09219

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.09219
License (as archived): CC0-1.0
Archived: 2026-10-16T07:23:51.816Z
SHA-256 of the archived text: 9e17fcd0ba7e2079e3c098e5beea2f821c5f7b9e7a21ab8edd841ba386c9f1b7
Stable URL of this page: https://metraipolis.com/documento/dc_8a2b4cf2cdc2

How to cite

Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents — arXiv:2609.09219 — arXiv (en), https://arxiv.org/abs/2609.09219 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a2b4cf2cdc2 (Metraipolis archive dc_8a2b4cf2cdc2, sha256 9e17fcd0ba7e2079e3c098e5beea2f821c5f7b9e7a21ab8edd841ba386c9f1b7)

BibTeX

@misc{dc8a2b4cf2cdc2,
  title = {Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents — arXiv:2609.09219},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09219},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a2b4cf2cdc2; sha256 9e17fcd0ba7e2079e3c098e5beea2f821c5f7b9e7a21ab8edd841ba386c9f1b7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09219. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI research agents combine public information and experimental feedback to produce measurable results. The Discovery Certification Protocol (DCP) turns an outcome claim into an executable audit under a registered model, information boundary, and budget. Gate 1 validates useful improvement. Gate 2 tests recovery by matched agents given the starting information and observed Web content, with run history and new measurements withheld. Core requires adequate registered controls, zero recoveries, and a finite-sample recovery bound. Optional Gate 3 compares truthful and neutral feedback from a shared checkpoint; Evidence adds a supported effect and a null-policy equivalence check. Controlled SQLite and virtual catalyst audits pass both decision kernels. On real-data response surfaces, Yacht and Ionosphere pass the Core kernel after zero recoveries in 96 attempts, with an upper bound of 0.0468. Each target combines ten observed utilities and six predictions into a 16-entry data product. Yacht scores 0.7677 on reconstruction of all 32 switch effects, with utility-prediction MAE 0.0315 on its six unmeasured configurations. Fresh truthful continuations recover the target level in 9/30 and 16/30 trials, respectively, separating achieved utility from process repeatability. A deterministic verifier reproduces these local decisions from frozen records.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.09219 — 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 2026-10-16T06:59:55.749Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).