# A Multi-Analyst LLM Pipeline for Auditable Rule Discovery Across 68 Public Physiological Corpora

arXiv: https://arxiv.org/abs/2607.06802 · HTML: https://mlsanity.com/paper/2607.06802/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 20 references that are in the map.
- First posted on arXiv 7 Jul 2026.

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

- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [SeizeIT2: Wearable Dataset Of Patients With Focal Epilepsy](https://mlsanity.com/paper/2502.01224/) (2025)

## Abstract (arXiv)

Open physiological corpora are heterogeneous: they use different sensors, labels, sampling rates, recording settings, and clinical endpoints. They can support detector design, but they do not directly specify which detector rules should be built for a new contactless monitoring platform. We report a controlled four-analyst large-language-model (LLM) workflow for converting 68 public physiological corpora, screened for commercial-use compatibility, into an auditable library of candidate rule shapes for prospective validation. Four independent commercial LLM families read the corpus documentation under a controlled prompt and produced 695 candidate rule markers (top-markers). Deduplication retained 649 rule records; a threshold-bounds audit then flagged 51 sanity violations for clamping or curator review. Cross-corpus consolidation produced 436 unique rule shapes. Gate-tagging against two hard invariants, native target-hardware channel availability and no multi-night per-patient personalization, identified 94 build-now detector components across four detector-family buckets. The pipeline does not produce a validated clinical detector. It produces an auditable engineering cascade in which analyst disagreement, threshold checks, curator review, and automated continuous-integration (CI) checks route literature-derived rules toward prospective hardware validation.