{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OHFKPDACWGFMCM6VNH2VQYBYIL","short_pith_number":"pith:OHFKPDAC","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"},"canonical_sha256":"71caa78c02b18ac133d569f558603842f713d126f9449d691da5ab2fb35dc777","source":{"kind":"arxiv","id":"2604.10389","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.10389","created_at":"2026-06-12T01:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2604.10389v2","created_at":"2026-06-12T01:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.10389","created_at":"2026-06-12T01:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"OHFKPDACWGFM","created_at":"2026-06-12T01:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"OHFKPDACWGFMCM6V","created_at":"2026-06-12T01:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"OHFKPDAC","created_at":"2026-06-12T01:09:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OHFKPDACWGFMCM6VNH2VQYBYIL","target":"record","payload":{"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"},"canonical_sha256":"71caa78c02b18ac133d569f558603842f713d126f9449d691da5ab2fb35dc777","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"},"source_kind":"arxiv","source_id":"2604.10389","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-12T01:09:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3rPAA2FOg0vt2Jrgg9nNzf3i1RqzrD6vN630nMO64v92nU2yKN7n4+YbhJgp/SYcZaqOVrP2vd8BCgx11P83Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T03:33:06.148007Z"},"content_sha256":"8343a6a6ab95f1491b6f2bca1146f4e537ed572b1cef1339ff6ec1f68da9da58","schema_version":"1.0","event_id":"sha256:8343a6a6ab95f1491b6f2bca1146f4e537ed572b1cef1339ff6ec1f68da9da58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OHFKPDACWGFMCM6VNH2VQYBYIL","target":"graph","payload":{"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"},"verdict_id":"b2517862-decb-4aa0-9ecc-3be15226f03b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-12T01:09:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0b+fetY+lhf8uNMC4YAOA5ssAhUC0TqgSdv/cGwRFO6Gh6DOYD+isy6tqTLsTUbobbVHIYB9O7gDdqlCXzF8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T03:33:06.148507Z"},"content_sha256":"143439a77a8b5deb88eaddabe2b520d060963674a5c020cbeed094e028530af5","schema_version":"1.0","event_id":"sha256:143439a77a8b5deb88eaddabe2b520d060963674a5c020cbeed094e028530af5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL/bundle.json","state_url":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OHFKPDACWGFMCM6VNH2VQYBYIL/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":"2026-06-20T03:33:06Z","links":{"resolver":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL","bundle":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL/bundle.json","state":"https://pith.science/pith/OHFKPDACWGFMCM6VNH2VQYBYIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OHFKPDACWGFMCM6VNH2VQYBYIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OHFKPDACWGFMCM6VNH2VQYBYIL","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":"df0b16d226b9e8703846c617cea9577bc0fa594669e77312fed5591a66016ef4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-12T00:30:31Z","title_canon_sha256":"92f2597d0e1a77b6948f0c95dec79d41b28001950cc23bc8ebf7d2943a1fff5a"},"schema_version":"1.0","source":{"id":"2604.10389","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.10389","created_at":"2026-06-12T01:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2604.10389v2","created_at":"2026-06-12T01:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.10389","created_at":"2026-06-12T01:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"OHFKPDACWGFM","created_at":"2026-06-12T01:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"OHFKPDACWGFMCM6V","created_at":"2026-06-12T01:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"OHFKPDAC","created_at":"2026-06-12T01:09:27Z"}],"graph_snapshots":[{"event_id":"sha256:143439a77a8b5deb88eaddabe2b520d060963674a5c020cbeed094e028530af5","target":"graph","created_at":"2026-06-12T01:09:27Z","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":"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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"9ff56a033121866695cfcfd2a53d0f67ff84fa77aa24c09d96cac172f4dc8db2"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"30c4e653028e18e63ca8eb561435ae8b602bfdef229d0f3336392243d998afd0"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.10389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hanshu Rao, Nguyen Anh Khoa Tran, Qiunan Zhang, Saukun Thika You, Wesley K. Marizane, Xiaolei Huang","cross_cats":[],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-12T00:30:31Z","title":"BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.10389","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T16:40:22.999045Z","id":"b2517862-decb-4aa0-9ecc-3be15226f03b","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"b2517862-decb-4aa0-9ecc-3be15226f03b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8343a6a6ab95f1491b6f2bca1146f4e537ed572b1cef1339ff6ec1f68da9da58","target":"record","created_at":"2026-06-12T01:09:27Z","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":"df0b16d226b9e8703846c617cea9577bc0fa594669e77312fed5591a66016ef4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-12T00:30:31Z","title_canon_sha256":"92f2597d0e1a77b6948f0c95dec79d41b28001950cc23bc8ebf7d2943a1fff5a"},"schema_version":"1.0","source":{"id":"2604.10389","kind":"arxiv","version":2}},"canonical_sha256":"71caa78c02b18ac133d569f558603842f713d126f9449d691da5ab2fb35dc777","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71caa78c02b18ac133d569f558603842f713d126f9449d691da5ab2fb35dc777","first_computed_at":"2026-06-12T01:09:27.657935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:09:27.657935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2nWUNnSdZ3wYeyOvYE2ogut+Pfb2zo6/SP5ndbeuJbHGclczCM9IvC3IdtH6enipB4ClQ/e8P7mT1TKEEp89BQ==","signature_status":"signed_v1","signed_at":"2026-06-12T01:09:27.658391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.10389","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8343a6a6ab95f1491b6f2bca1146f4e537ed572b1cef1339ff6ec1f68da9da58","sha256:143439a77a8b5deb88eaddabe2b520d060963674a5c020cbeed094e028530af5"],"state_sha256":"146029d5f84a7a492d09ed5ea8b50a32da3ed319fac8ad677fce4447801a263a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rFcU8lSmYnGkTAm+EJkvrJBaBrigCjYsllE2tBu2DYGjyD1FfKlmoHnnX16ZEW3zWl0HXNMm6tpgXuimMpqSBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T03:33:06.150771Z","bundle_sha256":"d46f8e95fd8043148da6db080d8971b35738645071a8896cee40f63df1a19f27"}}