Metraipolis › archive › dc_465bcbe59e19

Patching the Protocol: A Taxonomy of Pre-Registration Repairs in LLM-Proposer Experiments — arXiv:2611.04338

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04338
License (as archived)
CC0-1.0
Archived
2026-11-04T12:27:49.711Z
SHA-256 of the archived text
5c059ef50d93a612f5c2be021eaef97277daa1c987a4f2dfca6dd7bc89cbe693
Stable URL of this page
https://metraipolis.com/documento/dc_465bcbe59e19

How to cite

Patching the Protocol: A Taxonomy of Pre-Registration Repairs in LLM-Proposer Experiments — arXiv:2611.04338 — arXiv (en), https://arxiv.org/abs/2611.04338 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_465bcbe59e19 (Metraipolis archive dc_465bcbe59e19, sha256 5c059ef50d93a612f5c2be021eaef97277daa1c987a4f2dfca6dd7bc89cbe693)
BibTeX
@misc{dc465bcbe59e19,
  title = {Patching the Protocol: A Taxonomy of Pre-Registration Repairs in LLM-Proposer Experiments — arXiv:2611.04338},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04338},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_465bcbe59e19; sha256 5c059ef50d93a612f5c2be021eaef97277daa1c987a4f2dfca6dd7bc89cbe693},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04338. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pre-registration is increasingly proposed as a trust mechanism for machine-learning research involving LLM-generated content, but its canonical form assumes a frozen protocol can be executed unchanged. Software-intensive studies violate this assumption: the protocol is partly implemented, and implementations carry defects. We report a three-case study of protocol repairs ("patches") from a program where an LLM proposes executable rules that a programmatic verifier gates, across production scheduling, incentive design, and task assignment. Each protocol required exactly one defect-repair patch: three events in total. None modified a numbered judgment criterion, its threshold, or the scoring rule, and none altered already collected data; two changed pre-registered design parameters before any data were collected, each with a recorded rationale. We propose a two-axis taxonomy of patches (defect class: environmental / feasibility / correctness, x timing: pre-data / post-data), introduce a verifiable non-impact claim for post-data repairs, and distill a nine-item checklist; all nine items were exercised by at least one patch event -- an observation of use, not a validation of sufficiency. The credibility of verifier-bound, LLM-proposer studies depends less on whether patches occur than on whether they are auditable.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2611.04338 — 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 2026-11-04T12:26:47.146Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).