# From Papers to Mechanisms: An Evidence-Grounded Knowledge Substrate for Scientific Language Models

arXiv: https://arxiv.org/abs/2610.06248 · HTML: https://mlsanity.com/paper/2610.06248/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 17 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Builds on (most cited first, 2 of 2)

- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Language agents achieve superhuman synthesis of scientific knowledge](https://mlsanity.com/paper/2409.13740/) (2024)

## Abstract (arXiv)

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 MS3, 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 MS3 retrieval across ten language models. MS3 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 MS3 evidence triggers targeted retrieval from its linked papers rather than assuming that a user has already supplied the correct PDFs.