{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SX2HOT3C52EXN6KFIUAF3TWEKQ","short_pith_number":"pith:SX2HOT3C","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"},"canonical_sha256":"95f4774f62ee8976f94545005dcec4543005575664b76b1346b01cb146a0a70c","source":{"kind":"arxiv","id":"2603.28488","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SX2HOT3C52EXN6KFIUAF3TWEKQ","target":"record","payload":{"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"},"canonical_sha256":"95f4774f62ee8976f94545005dcec4543005575664b76b1346b01cb146a0a70c","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"},"source_kind":"arxiv","source_id":"2603.28488","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T01:52:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5SgGOP80HzZXkP+gULITdF6LzYa7mZWkAIdaCH6bgWMQdOBO24mMDIGaeoXIlhh4u1N0RlPZPqcjB7abOo1BDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:28:23.191955Z"},"content_sha256":"3ed5127a007484972e889d5d0ee73da4b883cb7399526723c3ba73078b1a29e6","schema_version":"1.0","event_id":"sha256:3ed5127a007484972e889d5d0ee73da4b883cb7399526723c3ba73078b1a29e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SX2HOT3C52EXN6KFIUAF3TWEKQ","target":"graph","payload":{"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"},"verdict_id":"20c5ddb0-5737-497a-8178-c90c6adca83a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T01:52:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WULtQAYqYaDgyHKvE5dQbSVCYgGRA+y2B9Ao4ZC8oDAJni1ZvmBPGzdIOXBrT4COSiqW1b3ndajRcXK/e2XNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:28:23.194312Z"},"content_sha256":"c6531a5ae0066efb5103c9376bd8f333f6068559aeacb3aaa9e225046bd3e006","schema_version":"1.0","event_id":"sha256:c6531a5ae0066efb5103c9376bd8f333f6068559aeacb3aaa9e225046bd3e006"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ/bundle.json","state_url":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T21:28:23Z","links":{"resolver":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ","bundle":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ/bundle.json","state":"https://pith.science/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SX2HOT3C52EXN6KFIUAF3TWEKQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ozl1PEjunenUxtBtztZ79dwNc3CsCjqbODSkX4D1FR6pJOx1FzKGeL/18+RE0NOINbsjU8xNwJDGOwb77wCdAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:28:23.211247Z","bundle_sha256":"2e3978e748053167aa404d1577baa4a7737466cd00e45e87b437da3c2a996aeb"}}