{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OHFKPDACWGFMCM6VNH2VQYBYIL","short_pith_number":"pith:OHFKPDAC","schema_version":"1.0","canonical_sha256":"71caa78c02b18ac133d569f558603842f713d126f9449d691da5ab2fb35dc777","source":{"kind":"arxiv","id":"2604.10389","version":2},"attestation_state":"computed","paper":{"title":"BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A multi-agent debate system augmented with hybrid retrieval detects terminology substitution errors in clinical notes more accurately than single-agent RAG or debate-only approaches.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanshu Rao, Nguyen Anh Khoa Tran, Qiunan Zhang, Saukun Thika You, Wesley K. Marizane, Xiaolei Huang","submitted_at":"2026-04-12T00:30:31Z","abstract_excerpt":"Terminology substitution errors in clinical notes, where one medical term is replaced by a linguistically valid but clinically different term, pose a persistent challenge for automated error detection in healthcare. We introduce BLUEmed, a multi-agent debate framework augmented with hybrid Retrieval-Augmented Generation (RAG) that combines evidence-grounded reasoning with multi-perspective verification for clinical error detection. BLUEmed decomposes each clinical note into focused sub-queries, retrieves source-partitioned evidence through dense, sparse, and online retrieval, and assigns two d"},"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":true},"canonical_record":{"source":{"id":"2604.10389","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-12T00:30:31Z","cross_cats_sorted":[],"title_canon_sha256":"92f2597d0e1a77b6948f0c95dec79d41b28001950cc23bc8ebf7d2943a1fff5a","abstract_canon_sha256":"df0b16d226b9e8703846c617cea9577bc0fa594669e77312fed5591a66016ef4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:27.658391Z","signature_b64":"2nWUNnSdZ3wYeyOvYE2ogut+Pfb2zo6/SP5ndbeuJbHGclczCM9IvC3IdtH6enipB4ClQ/e8P7mT1TKEEp89BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71caa78c02b18ac133d569f558603842f713d126f9449d691da5ab2fb35dc777","last_reissued_at":"2026-06-12T01:09:27.657935Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:27.657935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A multi-agent debate system augmented with hybrid retrieval detects terminology substitution errors in clinical notes more accurately than single-agent RAG or debate-only approaches.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanshu Rao, Nguyen Anh Khoa Tran, Qiunan Zhang, Saukun Thika You, Wesley K. Marizane, Xiaolei Huang","submitted_at":"2026-04-12T00:30:31Z","abstract_excerpt":"Terminology substitution errors in clinical notes, where one medical term is replaced by a linguistically valid but clinically different term, pose a persistent challenge for automated error detection in healthcare. We introduce BLUEmed, a multi-agent debate framework augmented with hybrid Retrieval-Augmented Generation (RAG) that combines evidence-grounded reasoning with multi-perspective verification for clinical error detection. BLUEmed decomposes each clinical note into focused sub-queries, retrieves source-partitioned evidence through dense, sparse, and online retrieval, and assigns two d"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"BLUEmed achieves the best accuracy (69.13%), ROC-AUC (74.45%), and PR-AUC (72.44%) under few-shot prompting, outperforming both single-agent RAG and debate-only baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The clinical terminology substitution detection benchmark used for evaluation is representative of real-world clinical notes and error distributions, and the two domain-expert agents possess sufficient clinical knowledge to produce reliable independent analyses without introducing new hallucinations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"BLUEmed combines hybrid RAG with structured multi-agent debate and a safety filter to detect terminology substitution errors in clinical notes, reaching 69.13% accuracy under few-shot prompting and outperforming single-agent and debate-only baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A multi-agent debate system augmented with hybrid retrieval detects terminology substitution errors in clinical notes more accurately than single-agent RAG or debate-only approaches.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9ff56a033121866695cfcfd2a53d0f67ff84fa77aa24c09d96cac172f4dc8db2"},"source":{"id":"2604.10389","kind":"arxiv","version":2},"verdict":{"id":"b2517862-decb-4aa0-9ecc-3be15226f03b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:40:22.999045Z","strongest_claim":"BLUEmed achieves the best accuracy (69.13%), ROC-AUC (74.45%), and PR-AUC (72.44%) under few-shot prompting, outperforming both single-agent RAG and debate-only baselines.","one_line_summary":"BLUEmed combines hybrid RAG with structured multi-agent debate and a safety filter to detect terminology substitution errors in clinical notes, reaching 69.13% accuracy under few-shot prompting and outperforming single-agent and debate-only baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The clinical terminology substitution detection benchmark used for evaluation is representative of real-world clinical notes and error distributions, and the two domain-expert agents possess sufficient clinical knowledge to produce reliable independent analyses without introducing new hallucinations.","pith_extraction_headline":"A multi-agent debate system augmented with hybrid retrieval detects terminology substitution errors in clinical notes more accurately than single-agent RAG or debate-only approaches."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.10389/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":1,"snapshot_sha256":"30c4e653028e18e63ca8eb561435ae8b602bfdef229d0f3336392243d998afd0"},"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":"2604.10389","created_at":"2026-06-12T01:09:27.657989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.10389v2","created_at":"2026-06-12T01:09:27.657989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.10389","created_at":"2026-06-12T01:09:27.657989+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHFKPDACWGFM","created_at":"2026-06-12T01:09:27.657989+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHFKPDACWGFMCM6V","created_at":"2026-06-12T01:09:27.657989+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHFKPDAC","created_at":"2026-06-12T01:09:27.657989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL","json":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL.json","graph_json":"https://pith.science/api/pith-number/OHFKPDACWGFMCM6VNH2VQYBYIL/graph.json","events_json":"https://pith.science/api/pith-number/OHFKPDACWGFMCM6VNH2VQYBYIL/events.json","paper":"https://pith.science/paper/OHFKPDAC"},"agent_actions":{"view_html":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL","download_json":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL.json","view_paper":"https://pith.science/paper/OHFKPDAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.10389&json=true","fetch_graph":"https://pith.science/api/pith-number/OHFKPDACWGFMCM6VNH2VQYBYIL/graph.json","fetch_events":"https://pith.science/api/pith-number/OHFKPDACWGFMCM6VNH2VQYBYIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL/action/storage_attestation","attest_author":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL/action/author_attestation","sign_citation":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL/action/citation_signature","submit_replication":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL/action/replication_record"}},"created_at":"2026-06-12T01:09:27.657989+00:00","updated_at":"2026-06-12T01:09:27.657989+00:00"}