{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SX2HOT3C52EXN6KFIUAF3TWEKQ","short_pith_number":"pith:SX2HOT3C","schema_version":"1.0","canonical_sha256":"95f4774f62ee8976f94545005dcec4543005575664b76b1346b01cb146a0a70c","source":{"kind":"arxiv","id":"2603.28488","version":3},"attestation_state":"computed","paper":{"title":"Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Courtroom-style debate with progressive retrieval raises claim verification accuracy to 81.7 percent on Check-COVID.","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Hasan Mahmud, Masnun Nuha Chowdhury, Md Kamrul Hasan, Nusrat Jahan Beg, Syed Rifat Raiyan, Umme Hunny Khan","submitted_at":"2026-03-30T14:23:15Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.28488","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-30T14:23:15Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"83ebddbd108167f1ff6cc0aa2d4697d5b20cf24fbe72d957f90dfb3ab0d7fde3","abstract_canon_sha256":"f5bb251b58be3155ba668db596b5c6a3ab7bb233eca244b0ff443ae4844fb98c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:52:42.912346Z","signature_b64":"rX15yb+hSwpkbbRMiDsp1tnR6KuQV9b5MrAxgk9yQD24zzDk6U8alhjSk3R0UjUMqX5/EwItgOFzggV2P5jiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95f4774f62ee8976f94545005dcec4543005575664b76b1346b01cb146a0a70c","last_reissued_at":"2026-08-04T01:52:42.910389Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:52:42.910389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Courtroom-style debate with progressive retrieval raises claim verification accuracy to 81.7 percent on Check-COVID.","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Hasan Mahmud, Masnun Nuha Chowdhury, Md Kamrul Hasan, Nusrat Jahan Beg, Syed Rifat Raiyan, Umme Hunny Khan","submitted_at":"2026-03-30T14:23:15Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Courtroom-style debate with progressive retrieval raises claim verification accuracy to 81.7 percent on Check-COVID.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b01a1d1361af76f11f31edabed60fd06b358c0d26678dee9679e30685acb84d5"},"source":{"id":"2603.28488","kind":"arxiv","version":3},"verdict":{"id":"20c5ddb0-5737-497a-8178-c90c6adca83a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T22:09:54.875625Z","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).","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","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.","pith_extraction_headline":"Courtroom-style debate with progressive retrieval raises claim verification accuracy to 81.7 percent on Check-COVID."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.28488/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.28488","created_at":"2026-08-04T01:52:42.911627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.28488v3","created_at":"2026-08-04T01:52:42.911627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.28488","created_at":"2026-08-04T01:52:42.911627+00:00"},{"alias_kind":"pith_short_12","alias_value":"SX2HOT3C52EX","created_at":"2026-08-04T01:52:42.911627+00:00"},{"alias_kind":"pith_short_16","alias_value":"SX2HOT3C52EXN6KF","created_at":"2026-08-04T01:52:42.911627+00:00"},{"alias_kind":"pith_short_8","alias_value":"SX2HOT3C","created_at":"2026-08-04T01:52:42.911627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ","json":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ.json","graph_json":"https://pith.science/api/pith-number/SX2HOT3C52EXN6KFIUAF3TWEKQ/graph.json","events_json":"https://pith.science/api/pith-number/SX2HOT3C52EXN6KFIUAF3TWEKQ/events.json","paper":"https://pith.science/paper/SX2HOT3C"},"agent_actions":{"view_html":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ","download_json":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ.json","view_paper":"https://pith.science/paper/SX2HOT3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.28488&json=true","fetch_graph":"https://pith.science/api/pith-number/SX2HOT3C52EXN6KFIUAF3TWEKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SX2HOT3C52EXN6KFIUAF3TWEKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ/action/storage_attestation","attest_author":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ/action/author_attestation","sign_citation":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ/action/citation_signature","submit_replication":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ/action/replication_record"}},"created_at":"2026-08-04T01:52:42.911627+00:00","updated_at":"2026-08-04T01:52:42.911627+00:00"}