TRACE-Chem: Symmetry-Aware Counterfactual Reasoning over Typed Evidence Graphs for Verifiable Multimodal Chemical Record Extraction

Abstract

Automatically extracted chemical records can appear complete even when names, depictions, formulas, masses, and spectra disagree. Because databases consume records rather than evidence, such errors propagate silently. TRACE-Chem (Typed Relational Attestation with Counterfactual Editing for Chemistry) is an inference-time framework for verifying and repairing them. It organizes source-linked observations, candidate fields, and verifier outcomes in a Symmetric–Asymmetric Evidence Graph (SAEG) separating symmetric identity checks from directional scientific derivations. Counterfactual Localization and Dependency-Constrained Re-decoding (CLDR) masks candidate fault nodes to identify the view whose removal most restores coherence, then revises only dependency-affected fields. Executable checks and spectral compatibility feed a calibrated accept, repair, or abstain decision. On 124 open-access synthesis papers containing 1852 compound and 638 reaction records, TRACE-Chem achieved 84.3% canonical-record hard-match F1, 9.7 percentage points above the same extractor without verification. Against a single-pass multimodal baseline, invalid structures fell from 10.8% to 0.8%, unsupported fields from 14.3% to 2.4%, and expected calibration error from 0.281 to 0.052. Removing derivation direction lowered fault-localization accuracy from 91.2% to 82.8%; removing dependency discounting raised the unsafe-edit rate from 2.4% to 4.1%. Explicitly modeling relational symmetry and asymmetry therefore improves verifiability, calibration, and repair safety in multimodal chemical extraction.