Metraipolis › archive › dc_3597bbcb40de

From Papers to Mechanisms: An Evidence-Grounded Knowledge Substrate for Scientific Language Models — arXiv:2610.06248

Source: arXiv
Original: https://arxiv.org/abs/2610.06248
License (as archived): CC0-1.0
Archived: 2026-10-06T05:25:29.893Z
SHA-256 of the archived text: 7e676f6cab94d012d3452ffbfc5884048e61b641807f9cab7b79616d68099447
Stable URL of this page: https://metraipolis.com/documento/dc_3597bbcb40de

How to cite

From Papers to Mechanisms: An Evidence-Grounded Knowledge Substrate for Scientific Language Models — arXiv:2610.06248 — arXiv, https://arxiv.org/abs/2610.06248 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3597bbcb40de (Metraipolis archive dc_3597bbcb40de, sha256 7e676f6cab94d012d3452ffbfc5884048e61b641807f9cab7b79616d68099447)

BibTeX

@misc{dc3597bbcb40de,
  title = {From Papers to Mechanisms: An Evidence-Grounded Knowledge Substrate for Scientific Language Models — arXiv:2610.06248},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06248},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3597bbcb40de; sha256 7e676f6cab94d012d3452ffbfc5884048e61b641807f9cab7b79616d68099447},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06248. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scientific language models often access literature through untyped text chunks, which fragment the functional and evidential structure required for mechanism-rich questions. We introduce an evidence-grounded mechanism knowledge substrate that organizes scientific literature into provenance-linked evidence units, role-typed entities, and directed mechanism paths. We instantiate it as MS$^3$, a Material-Sensor-Signal-System schema for conductive-fiber flexible sensors, over 13,689 papers, 131,083 evidence items, and 26,648 mechanism objects. On in-domain and coverage-shift question-answering benchmarks, we compare closed-book generation, Web search, Raw-PDF RAG, and MS$^3$ retrieval across ten language models. MS$^3$ improves macro-averaged scientific correctness. It also improves citation entailment and answer completeness. These results support mechanism substrates as a reliable representation layer for scientific language models and motivate a source-repair workflow in which insufficient MS$^3$ evidence triggers targeted retrieval from its linked papers rather than assuming that a user has already supplied the correct PDFs.

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/2610.06248 — 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 2026-10-06T05:24:05.664Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).