{"slug": "evidence-ledger-adjudication-for-claim-evidence-traceability", "title": "Evidence-Ledger Adjudication for Claim-Evidence Traceability", "summary": "A new arXiv paper (2607.26512v1) introduces evidence-ledger adjudication, a workflow that pairs AI-generated claims with evidence packets and routes unsupported or contradicted claims back to authors. On a 2,335-row blind benchmark built from AVeriTeC, CLIMATE-FEVER, and SciFact, the agent condition achieved 0.676 relation accuracy and 0.601 macro-F1, outperforming the best non-agent baseline (0.383 accuracy, 0.303 macro-F1). The method routed 1270/1435 claims with contradiction or missing evidence, while routing 295/900 supported claims.", "body_md": "arXiv:2607.26512v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/evidence-ledger-adjudication-for-claim-evidence-traceability", "canonical_source": "https://arxiv.org/abs/2607.26512", "published_at": "2026-07-31 04:00:00+00:00", "updated_at": "2026-07-31 04:29:13.111665+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-research", "ai-agents"], "entities": ["arXiv", "AVeriTeC", "CLIMATE-FEVER", "SciFact"], "alternates": {"html": "https://wpnews.pro/news/evidence-ledger-adjudication-for-claim-evidence-traceability", "markdown": "https://wpnews.pro/news/evidence-ledger-adjudication-for-claim-evidence-traceability.md", "text": "https://wpnews.pro/news/evidence-ledger-adjudication-for-claim-evidence-traceability.txt", "jsonld": "https://wpnews.pro/news/evidence-ledger-adjudication-for-claim-evidence-traceability.jsonld"}}