Metraipolis › archive › dc_eead76de16ed

RECAST: REconstruction of Chain-of-Thought via Auditable Structured Traces — arXiv:2610.41813

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41813
License (as archived)
CC0-1.0
Archived
2026-11-02T06:59:20.082Z
SHA-256 of the archived text
e1b8096b1ac85b92eb163e0dfce084410638a3cee8b575c443db4f863149d531
Stable URL of this page
https://metraipolis.com/documento/dc_eead76de16ed

How to cite

RECAST: REconstruction of Chain-of-Thought via Auditable Structured Traces — arXiv:2610.41813 — arXiv (en), https://arxiv.org/abs/2610.41813 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eead76de16ed (Metraipolis archive dc_eead76de16ed, sha256 e1b8096b1ac85b92eb163e0dfce084410638a3cee8b575c443db4f863149d531)
BibTeX
@misc{dceead76de16ed,
  title = {RECAST: REconstruction of Chain-of-Thought via Auditable Structured Traces — arXiv:2610.41813},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41813},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eead76de16ed; sha256 e1b8096b1ac85b92eb163e0dfce084410638a3cee8b575c443db4f863149d531},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41813. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large closed-source reasoning models expose only their final answers. The intermediate reasoning that produces those answers is hidden behind API surfaces, tool-call policies, and safety filters. Existing chain-of-thought (CoT) extraction methods assume a side channel: a visible reasoning field, a scratchpad carried through tool calls, or a signed/encrypted reasoning block. We reproduce three representative state-of-the-art extraction methods and find that, on Claude-Sonnet-5.5 accessed through the standard chat-completions interface, all three return zero CoT tokens. The failure is structural rather than a bug: the reasoning field is absent, named tool selection is rejected, free-text scratchpad arguments are filtered, and no replayable reasoning block is exposed. We therefore take a different route. We present RECAST, a reconstruction-based framework that conditions a decoder on the question and the target model's final answer, reconstructs a first-person structured rationale, cleans it, and builds SFT-ready data. To the best of our knowledge, RECAST is the first system to reconstruct CoT from frontier closed models such as Claude-Sonnet-5.5, GPT-6.1, and Gemini 3 without using hidden reasoning channels. We instantiate RECAST on Claude-Sonnet-5.5 and additionally obtain successful qualitative reconstructions on GPT-6.1 and Gemini 3 with the same answer-only protocol. The system is open-source and packaged as an agent skill: one prompt deploys it and runs the complete pipeline to produce SFT-ready CoT data. This preprint describes the system, its threat model, and a controlled artifact validation; it does not claim large-scale benchmark improvements.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41813 — 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 2026-11-02T06:56:58.317Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).