{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SX2HOT3C52EXN6KFIUAF3TWEKQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f5bb251b58be3155ba668db596b5c6a3ab7bb233eca244b0ff443ae4844fb98c","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-30T14:23:15Z","title_canon_sha256":"83ebddbd108167f1ff6cc0aa2d4697d5b20cf24fbe72d957f90dfb3ab0d7fde3"},"schema_version":"1.0","source":{"id":"2603.28488","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.28488","created_at":"2026-08-04T01:52:42Z"},{"alias_kind":"arxiv_version","alias_value":"2603.28488v3","created_at":"2026-08-04T01:52:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.28488","created_at":"2026-08-04T01:52:42Z"},{"alias_kind":"pith_short_12","alias_value":"SX2HOT3C52EX","created_at":"2026-08-04T01:52:42Z"},{"alias_kind":"pith_short_16","alias_value":"SX2HOT3C52EXN6KF","created_at":"2026-08-04T01:52:42Z"},{"alias_kind":"pith_short_8","alias_value":"SX2HOT3C","created_at":"2026-08-04T01:52:42Z"}],"graph_snapshots":[{"event_id":"sha256:c6531a5ae0066efb5103c9376bd8f333f6068559aeacb3aaa9e225046bd3e006","target":"graph","created_at":"2026-08-04T01:52:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"In zero-shot evaluations on the Check-COVID benchmark, PROClaim achieves 81.7% accuracy, outperforming standard multi-agent debate by 10.0 percentage points, with P-RAG driving the primary performance gains (+7.5 pp)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the courtroom structure and progressive evidence retrieval provide genuine robustness against hallucinations and biases, rather than overfitting to the specific Check-COVID dataset or the models used in the evaluation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PROClaim achieves 81.7% accuracy on Check-COVID claim verification by combining courtroom roles, progressive RAG, and multi-judge aggregation, outperforming standard multi-agent debate by 10 percentage points."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Courtroom-style debate with progressive retrieval raises claim verification accuracy to 81.7 percent on Check-COVID."}],"snapshot_sha256":"b01a1d1361af76f11f31edabed60fd06b358c0d26678dee9679e30685acb84d5"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.28488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) remain unreliable for high-stakes claim verification due to hallucinations and shallow reasoning. While retrieval-augmented generation (RAG) and multi-agent debate (MAD) address this, they are limited by one-pass retrieval and unstructured debate dynamics. We propose a courtroom-style multi-agent framework, PROClaim, that reformulates verification as a structured, adversarial deliberation. Our approach integrates specialized roles (e.g., Plaintiff, Defense, Judge) with Progressive RAG (P-RAG) to dynamically expand and refine the evidence pool during the debate. Fur","authors_text":"Hasan Mahmud, Masnun Nuha Chowdhury, Md Kamrul Hasan, Nusrat Jahan Beg, Syed Rifat Raiyan, Umme Hunny Khan","cross_cats":["cs.AI","cs.MA"],"headline":"Courtroom-style debate with progressive retrieval raises claim verification accuracy to 81.7 percent on Check-COVID.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-30T14:23:15Z","title":"Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.28488","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-14T22:09:54.875625Z","id":"20c5ddb0-5737-497a-8178-c90c6adca83a","model_set":{"reader":"grok-4.3"},"one_line_summary":"PROClaim achieves 81.7% accuracy on Check-COVID claim verification by combining courtroom roles, progressive RAG, and multi-judge aggregation, outperforming standard multi-agent debate by 10 percentage points.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Courtroom-style debate with progressive retrieval raises claim verification accuracy to 81.7 percent on Check-COVID.","strongest_claim":"In zero-shot evaluations on the Check-COVID benchmark, PROClaim achieves 81.7% accuracy, outperforming standard multi-agent debate by 10.0 percentage points, with P-RAG driving the primary performance gains (+7.5 pp).","weakest_assumption":"The assumption that the courtroom structure and progressive evidence retrieval provide genuine robustness against hallucinations and biases, rather than overfitting to the specific Check-COVID dataset or the models used in the evaluation."}},"verdict_id":"20c5ddb0-5737-497a-8178-c90c6adca83a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3ed5127a007484972e889d5d0ee73da4b883cb7399526723c3ba73078b1a29e6","target":"record","created_at":"2026-08-04T01:52:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f5bb251b58be3155ba668db596b5c6a3ab7bb233eca244b0ff443ae4844fb98c","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-30T14:23:15Z","title_canon_sha256":"83ebddbd108167f1ff6cc0aa2d4697d5b20cf24fbe72d957f90dfb3ab0d7fde3"},"schema_version":"1.0","source":{"id":"2603.28488","kind":"arxiv","version":3}},"canonical_sha256":"95f4774f62ee8976f94545005dcec4543005575664b76b1346b01cb146a0a70c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95f4774f62ee8976f94545005dcec4543005575664b76b1346b01cb146a0a70c","first_computed_at":"2026-08-04T01:52:42.910389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:52:42.910389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rX15yb+hSwpkbbRMiDsp1tnR6KuQV9b5MrAxgk9yQD24zzDk6U8alhjSk3R0UjUMqX5/EwItgOFzggV2P5jiAA==","signature_status":"signed_v1","signed_at":"2026-08-04T01:52:42.912346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.28488","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ed5127a007484972e889d5d0ee73da4b883cb7399526723c3ba73078b1a29e6","sha256:c6531a5ae0066efb5103c9376bd8f333f6068559aeacb3aaa9e225046bd3e006"],"state_sha256":"0ee764e9ff9fa4a5224a04061c3bddf24f88850463b344e6d409635b642ee33c"}