{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LWMOAZKVVEUOOZXF2TCHIVFPH6","short_pith_number":"pith:LWMOAZKV","schema_version":"1.0","canonical_sha256":"5d98e06555a928e766e5d4c47454af3f8f7bc6d33c41181f99a104137b3fe9a5","source":{"kind":"arxiv","id":"2505.00467","version":2},"attestation_state":"computed","paper":{"title":"Red Teaming Large Language Models for Healthcare","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abhishek Jaiswal, Ajay Shah, Allan Pang, Amrit Krishnan, Anirudh Gangadhar, Anshul Pattoo, Atousa Assadi, Aviraj Newatia, Babak Taati, Balagopal Unnikrishnan, Bogdana Rakova, Christopher Khoury, David Pellow, Diana Prepelita, Gabriel Funingana, I\\~nigo Urteaga, Jennifer Bell, Jim Fackler, Kaden McKeen, Kaivalya Deshpande, Khashayar Namdar, Mark Coatsworth, Michael Cooper, Rafael Schulman, Rahul G Krishnan, Randy Lin, Saba Sadatamin, Sameer Peesapati, Sara Naimimohasses, Spencer Gable-Cook, Stephanie Williams, Sumanth Kaja, Syed Ahmar Shah, Syed Azhar Shah, Vahid Balazadeh","submitted_at":"2025-05-01T11:43:27Z","abstract_excerpt":"We present the design process and findings of the pre-conference workshop at the Machine Learning for Healthcare Conference (2024) entitled Red Teaming Large Language Models for Healthcare, which took place on August 15, 2024. Conference participants, comprising a mix of computational and clinical expertise, attempted to discover vulnerabilities -- realistic clinical prompts for which a large language model (LLM) outputs a response that could cause clinical harm. Red-teaming with clinicians enables the identification of LLM vulnerabilities that may not be recognised by LLM developers lacking c"},"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":"2505.00467","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-01T11:43:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8699e291abaf13ea0b0882615620874e53330b20c5c46b487774da23ad05fcc1","abstract_canon_sha256":"ba2082822cb0730992e737b42489e96f5dc2ba83cc0260373fc449c308bd4753"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:34.978173Z","signature_b64":"H0kXgXXXZ50UPp7fjJO4M3MJ4CMyS7FFY9ZUW2eyhUF6TKiePvunYA7MnSJF8MQW+xGIVzQH3fResSrJk9HAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d98e06555a928e766e5d4c47454af3f8f7bc6d33c41181f99a104137b3fe9a5","last_reissued_at":"2026-07-05T11:35:34.977684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:34.977684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Red Teaming Large Language Models for Healthcare","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abhishek Jaiswal, Ajay Shah, Allan Pang, Amrit Krishnan, Anirudh Gangadhar, Anshul Pattoo, Atousa Assadi, Aviraj Newatia, Babak Taati, Balagopal Unnikrishnan, Bogdana Rakova, Christopher Khoury, David Pellow, Diana Prepelita, Gabriel Funingana, I\\~nigo Urteaga, Jennifer Bell, Jim Fackler, Kaden McKeen, Kaivalya Deshpande, Khashayar Namdar, Mark Coatsworth, Michael Cooper, Rafael Schulman, Rahul G Krishnan, Randy Lin, Saba Sadatamin, Sameer Peesapati, Sara Naimimohasses, Spencer Gable-Cook, Stephanie Williams, Sumanth Kaja, Syed Ahmar Shah, Syed Azhar Shah, Vahid Balazadeh","submitted_at":"2025-05-01T11:43:27Z","abstract_excerpt":"We present the design process and findings of the pre-conference workshop at the Machine Learning for Healthcare Conference (2024) entitled Red Teaming Large Language Models for Healthcare, which took place on August 15, 2024. Conference participants, comprising a mix of computational and clinical expertise, attempted to discover vulnerabilities -- realistic clinical prompts for which a large language model (LLM) outputs a response that could cause clinical harm. Red-teaming with clinicians enables the identification of LLM vulnerabilities that may not be recognised by LLM developers lacking c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00467","kind":"arxiv","version":2},"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/2505.00467/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":"2505.00467","created_at":"2026-07-05T11:35:34.977743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00467v2","created_at":"2026-07-05T11:35:34.977743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00467","created_at":"2026-07-05T11:35:34.977743+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWMOAZKVVEUO","created_at":"2026-07-05T11:35:34.977743+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWMOAZKVVEUOOZXF","created_at":"2026-07-05T11:35:34.977743+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWMOAZKV","created_at":"2026-07-05T11:35:34.977743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00923","citing_title":"Addressing Benchmarking Gaps in Large Language Models for Health and Medicine with Dynamic Red-Teaming","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWMOAZKVVEUOOZXF2TCHIVFPH6","json":"https://pith.science/pith/LWMOAZKVVEUOOZXF2TCHIVFPH6.json","graph_json":"https://pith.science/api/pith-number/LWMOAZKVVEUOOZXF2TCHIVFPH6/graph.json","events_json":"https://pith.science/api/pith-number/LWMOAZKVVEUOOZXF2TCHIVFPH6/events.json","paper":"https://pith.science/paper/LWMOAZKV"},"agent_actions":{"view_html":"https://pith.science/pith/LWMOAZKVVEUOOZXF2TCHIVFPH6","download_json":"https://pith.science/pith/LWMOAZKVVEUOOZXF2TCHIVFPH6.json","view_paper":"https://pith.science/paper/LWMOAZKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00467&json=true","fetch_graph":"https://pith.science/api/pith-number/LWMOAZKVVEUOOZXF2TCHIVFPH6/graph.json","fetch_events":"https://pith.science/api/pith-number/LWMOAZKVVEUOOZXF2TCHIVFPH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWMOAZKVVEUOOZXF2TCHIVFPH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWMOAZKVVEUOOZXF2TCHIVFPH6/action/storage_attestation","attest_author":"https://pith.science/pith/LWMOAZKVVEUOOZXF2TCHIVFPH6/action/author_attestation","sign_citation":"https://pith.science/pith/LWMOAZKVVEUOOZXF2TCHIVFPH6/action/citation_signature","submit_replication":"https://pith.science/pith/LWMOAZKVVEUOOZXF2TCHIVFPH6/action/replication_record"}},"created_at":"2026-07-05T11:35:34.977743+00:00","updated_at":"2026-07-05T11:35:34.977743+00:00"}