{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RQCKRM6OOANYW5WKLJF43UYXAF","short_pith_number":"pith:RQCKRM6O","schema_version":"1.0","canonical_sha256":"8c04a8b3ce701b8b76ca5a4bcdd317014d5a6abe44a2c5268f088449341bd84a","source":{"kind":"arxiv","id":"2505.18581","version":1},"attestation_state":"computed","paper":{"title":"Removal of Hallucination on Hallucination: Debate-Augmented RAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Jason Zhang, Qing Li, Wengyu Zhang, Wentao Hu, Xiaoyong Wei, Yiyang Jiang","submitted_at":"2025-05-24T08:15:22Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) enhances factual accuracy by integrating external knowledge, yet it introduces a critical issue: erroneous or biased retrieval can mislead generation, compounding hallucinations, a phenomenon we term Hallucination on Hallucination. To address this, we propose Debate-Augmented RAG (DRAG), a training-free framework that integrates Multi-Agent Debate (MAD) mechanisms into both retrieval and generation stages. In retrieval, DRAG employs structured debates among proponents, opponents, and judges to refine retrieval quality and ensure factual reliability. In gene"},"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":"2505.18581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T08:15:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"06b92e983db09c4a55825952a5d84029074e1abfd52f0c9c00e37de74c18f231","abstract_canon_sha256":"7b739202d151458f5de915eefa36433a98506926ec64ef0b0318d3697469ad8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:16.002588Z","signature_b64":"sO6e8n+zE//sb0qe9sximj3cbBOaQHw0TGtYoHBz51pyDx5ygXwzw0OO86YkSB04ZwUKNd+qhGpmOIYsGWGDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c04a8b3ce701b8b76ca5a4bcdd317014d5a6abe44a2c5268f088449341bd84a","last_reissued_at":"2026-07-05T11:09:16.002029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:16.002029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Removal of Hallucination on Hallucination: Debate-Augmented RAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Jason Zhang, Qing Li, Wengyu Zhang, Wentao Hu, Xiaoyong Wei, Yiyang Jiang","submitted_at":"2025-05-24T08:15:22Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) enhances factual accuracy by integrating external knowledge, yet it introduces a critical issue: erroneous or biased retrieval can mislead generation, compounding hallucinations, a phenomenon we term Hallucination on Hallucination. To address this, we propose Debate-Augmented RAG (DRAG), a training-free framework that integrates Multi-Agent Debate (MAD) mechanisms into both retrieval and generation stages. In retrieval, DRAG employs structured debates among proponents, opponents, and judges to refine retrieval quality and ensure factual reliability. In gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18581","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.18581/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":"2505.18581","created_at":"2026-07-05T11:09:16.002094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18581v1","created_at":"2026-07-05T11:09:16.002094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18581","created_at":"2026-07-05T11:09:16.002094+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQCKRM6OOANY","created_at":"2026-07-05T11:09:16.002094+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQCKRM6OOANYW5WK","created_at":"2026-07-05T11:09:16.002094+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQCKRM6O","created_at":"2026-07-05T11:09:16.002094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18133","citing_title":"Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQCKRM6OOANYW5WKLJF43UYXAF","json":"https://pith.science/pith/RQCKRM6OOANYW5WKLJF43UYXAF.json","graph_json":"https://pith.science/api/pith-number/RQCKRM6OOANYW5WKLJF43UYXAF/graph.json","events_json":"https://pith.science/api/pith-number/RQCKRM6OOANYW5WKLJF43UYXAF/events.json","paper":"https://pith.science/paper/RQCKRM6O"},"agent_actions":{"view_html":"https://pith.science/pith/RQCKRM6OOANYW5WKLJF43UYXAF","download_json":"https://pith.science/pith/RQCKRM6OOANYW5WKLJF43UYXAF.json","view_paper":"https://pith.science/paper/RQCKRM6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18581&json=true","fetch_graph":"https://pith.science/api/pith-number/RQCKRM6OOANYW5WKLJF43UYXAF/graph.json","fetch_events":"https://pith.science/api/pith-number/RQCKRM6OOANYW5WKLJF43UYXAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQCKRM6OOANYW5WKLJF43UYXAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQCKRM6OOANYW5WKLJF43UYXAF/action/storage_attestation","attest_author":"https://pith.science/pith/RQCKRM6OOANYW5WKLJF43UYXAF/action/author_attestation","sign_citation":"https://pith.science/pith/RQCKRM6OOANYW5WKLJF43UYXAF/action/citation_signature","submit_replication":"https://pith.science/pith/RQCKRM6OOANYW5WKLJF43UYXAF/action/replication_record"}},"created_at":"2026-07-05T11:09:16.002094+00:00","updated_at":"2026-07-05T11:09:16.002094+00:00"}