{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K5VDXBM5AYSENPQ2PF2BYWZRTF","short_pith_number":"pith:K5VDXBM5","schema_version":"1.0","canonical_sha256":"576a3b859d062446be1a79741c5b3199406807b7645cd144a06eedafed82823d","source":{"kind":"arxiv","id":"2410.16543","version":3},"attestation_state":"computed","paper":{"title":"Large Language Models Powered Multiagent Ensemble for Mitigating Hallucination and Efficient Atrial Fibrillation Annotation of ECG Reports","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ann Marie Navar, Bo Yao, Donghan M. Yang, Eric D. Peterson, Guanghua Xiao, Ismael Villanueva-Miranda, Jingwei Huang, Kuroush Nezafati, Qin Zhou, Ruichen Rong, Tingyi Wanyan, Wenqi Shi, Xiaowei Zhan, Yang Xie, Yueshuang Xu, Zifan Gu","submitted_at":"2024-10-21T22:12:00Z","abstract_excerpt":"This study introduces a LLMs powered multiagent ensemble method to address challenges in hallucination and data labeling, particularly in large-scale EHR datasets. Manual labeling of such datasets requires domain expertise and is labor-intensive, time-consuming, expensive, and error-prone. To overcome this bottleneck, we developed an ensemble LLMs method and demonstrated its effectiveness in two real-world tasks: (1) labeling a large-scale unlabeled ECG dataset in MIMIC-IV; (2) identifying social determinants of health (SDOH) from the clinical notes of EHR. Trading off benefits and cost, we se"},"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":"2410.16543","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-21T22:12:00Z","cross_cats_sorted":[],"title_canon_sha256":"4dc27852eeebec0d0ec156ed3b634d2f227fc6430bd4b81edcf93c29020deae4","abstract_canon_sha256":"e210610be8ffe2b80319d6be3338891390572630493caa4263473212834a5b3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:44.266716Z","signature_b64":"S+FqefxAfNWYPDA2HP1GADOi7Xx86QHye/HCDqYL7DZfqw8OqmUJx2JG/CT3GAD6/dJ3OcQNp3XXIRyvnlL4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"576a3b859d062446be1a79741c5b3199406807b7645cd144a06eedafed82823d","last_reissued_at":"2026-07-05T11:39:44.266197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:44.266197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models Powered Multiagent Ensemble for Mitigating Hallucination and Efficient Atrial Fibrillation Annotation of ECG Reports","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ann Marie Navar, Bo Yao, Donghan M. Yang, Eric D. Peterson, Guanghua Xiao, Ismael Villanueva-Miranda, Jingwei Huang, Kuroush Nezafati, Qin Zhou, Ruichen Rong, Tingyi Wanyan, Wenqi Shi, Xiaowei Zhan, Yang Xie, Yueshuang Xu, Zifan Gu","submitted_at":"2024-10-21T22:12:00Z","abstract_excerpt":"This study introduces a LLMs powered multiagent ensemble method to address challenges in hallucination and data labeling, particularly in large-scale EHR datasets. Manual labeling of such datasets requires domain expertise and is labor-intensive, time-consuming, expensive, and error-prone. To overcome this bottleneck, we developed an ensemble LLMs method and demonstrated its effectiveness in two real-world tasks: (1) labeling a large-scale unlabeled ECG dataset in MIMIC-IV; (2) identifying social determinants of health (SDOH) from the clinical notes of EHR. Trading off benefits and cost, we se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16543","kind":"arxiv","version":3},"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/2410.16543/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":"2410.16543","created_at":"2026-07-05T11:39:44.266255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16543v3","created_at":"2026-07-05T11:39:44.266255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16543","created_at":"2026-07-05T11:39:44.266255+00:00"},{"alias_kind":"pith_short_12","alias_value":"K5VDXBM5AYSE","created_at":"2026-07-05T11:39:44.266255+00:00"},{"alias_kind":"pith_short_16","alias_value":"K5VDXBM5AYSENPQ2","created_at":"2026-07-05T11:39:44.266255+00:00"},{"alias_kind":"pith_short_8","alias_value":"K5VDXBM5","created_at":"2026-07-05T11:39:44.266255+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/K5VDXBM5AYSENPQ2PF2BYWZRTF","json":"https://pith.science/pith/K5VDXBM5AYSENPQ2PF2BYWZRTF.json","graph_json":"https://pith.science/api/pith-number/K5VDXBM5AYSENPQ2PF2BYWZRTF/graph.json","events_json":"https://pith.science/api/pith-number/K5VDXBM5AYSENPQ2PF2BYWZRTF/events.json","paper":"https://pith.science/paper/K5VDXBM5"},"agent_actions":{"view_html":"https://pith.science/pith/K5VDXBM5AYSENPQ2PF2BYWZRTF","download_json":"https://pith.science/pith/K5VDXBM5AYSENPQ2PF2BYWZRTF.json","view_paper":"https://pith.science/paper/K5VDXBM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16543&json=true","fetch_graph":"https://pith.science/api/pith-number/K5VDXBM5AYSENPQ2PF2BYWZRTF/graph.json","fetch_events":"https://pith.science/api/pith-number/K5VDXBM5AYSENPQ2PF2BYWZRTF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K5VDXBM5AYSENPQ2PF2BYWZRTF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K5VDXBM5AYSENPQ2PF2BYWZRTF/action/storage_attestation","attest_author":"https://pith.science/pith/K5VDXBM5AYSENPQ2PF2BYWZRTF/action/author_attestation","sign_citation":"https://pith.science/pith/K5VDXBM5AYSENPQ2PF2BYWZRTF/action/citation_signature","submit_replication":"https://pith.science/pith/K5VDXBM5AYSENPQ2PF2BYWZRTF/action/replication_record"}},"created_at":"2026-07-05T11:39:44.266255+00:00","updated_at":"2026-07-05T11:39:44.266255+00:00"}