Model Releases
Evidence-Ledger Adjudication for Claim-Evidence Traceability
arXiv:2607.26512v1 Announce Type: new Abstract: AI agents can draft claims faster than authors can check whether the cited or retrieved evidence supports them. We study evidence-ledger adjudication: a
arXiv:2607.26512v1 Announce Type: new Abstract: AI agents can draft claims faster than authors can check whether the cited or retrieved evidence supports them. We study evidence-ledger adjudication: a claim-evidence traceability workflow that pairs each claim with an evidence packet, assigns a support relation, and routes unsupported, contradicted, or mixed-evidence claims back to the author. The empirical core is a 2,335-row blind benchmark built from independent external labels in AVeriTeC, CLIMATE-FEVER, and SciFact. Gold relations and source evidence labels are hidden during prediction and joined only for scoring. On this benchmark, the agent evidence-ledger condition achieves 0.676 relation accuracy and 0.601 macro-F1, compared with 0.383 accuracy and 0.303 macro-F1 for the best non-agent baseline. It also routes 1270/1435 claims whose gold labels indicate contradiction, missing evidence, or mixed evidence, while routing 295/900 supported claims. These results show that evidence-ledger adjudication can turn heterogeneous evidence packets into an auditable traceability layer for AI-assisted writing.
Related
- DeepSciVerify: Verifying Scientific Claim--Citation Alignment via LLM-Driven Evidence Escalation
- Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking
- FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification
- TRUST Agents: A Collaborative Multi-Agent Framework for Fake News Detection, Explainable Verification, and Logic-Aware Claim Reasoning
Source: arXiv cs.AI | 2026-07-31