PhysioSkeptic: Skeptical Reasoning Grounded in Signal Quality for Multimodal Rhythm Analysis

Anonymous (ICLR 2027 double-blind)

ICLR 2027 submission· 2026
PPGECG

Summary

PhysioPatch encoder aligns waveform patches to cardiac landmarks and emits heartbeat-level tokens plus a Patch Report (rhythm cues, confidence, signal quality), so an LLM can run conflict checks and quality-conditioned belief revision instead of reasoning over lossy waveform-to-text summaries. On MIMIC-III-Ext-PPG: 0.886 Macro-F1, +6.2 pp over generic Debate and +4.1 pp over an encoder-matched control; lowest observed ECE among GPT-5.2 methods; anchor-trap retention 56.6%→16.8%. Removing SQI anchoring gives the largest drop among reasoning controls.

Key facts

Form Factor
finger

Reported benchmarks

AFib / arrhythmia

MIMIC-III-Ext-PPG · Macro-F1 ↑

#1 of 1
0.886

ECG–PPG multi-class rhythm; SQI-anchored LLM (GPT-5.2); not AF-only

Updated: Oct 6, 2026