{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SEGXEEHRHO7CY5V66MMM4QA6PE","short_pith_number":"pith:SEGXEEHR","schema_version":"1.0","canonical_sha256":"910d7210f13bbe2c76bef318ce401e790876452df6e217fc590e030983241e3c","source":{"kind":"arxiv","id":"2506.21597","version":1},"attestation_state":"computed","paper":{"title":"Overview of the ClinIQLink 2025 Shared Task on Medical Question-Answering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Brandon Colelough, Davis Bartels, Dina Demner-Fushman","submitted_at":"2025-06-18T19:56:32Z","abstract_excerpt":"In this paper, we present an overview of ClinIQLink, a shared task, collocated with the 24th BioNLP workshop at ACL 2025, designed to stress-test large language models (LLMs) on medically-oriented question answering aimed at the level of a General Practitioner. The challenge supplies 4,978 expert-verified, medical source-grounded question-answer pairs that cover seven formats: true/false, multiple choice, unordered list, short answer, short-inverse, multi-hop, and multi-hop-inverse. Participating systems, bundled in Docker or Apptainer images, are executed on the CodaBench platform or the Univ"},"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":"2506.21597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T19:56:32Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"d42301efefb92fbad3b07b866bde112503fe1d786b8b0295f06bef3adda91bd4","abstract_canon_sha256":"03d375b27063b1c94bde6d78dc990f885b8abf85ad5262c044e977d58621b88f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:56.990144Z","signature_b64":"wIDzpVPtxK4FlbKqoSmoY22EFj4ePB0zyl6yVoWUTJoHqh9WBOO42n88q9dFvxtl4Q2pbcML00RPIgZc9yLBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"910d7210f13bbe2c76bef318ce401e790876452df6e217fc590e030983241e3c","last_reissued_at":"2026-07-05T11:27:56.989554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:56.989554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overview of the ClinIQLink 2025 Shared Task on Medical Question-Answering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Brandon Colelough, Davis Bartels, Dina Demner-Fushman","submitted_at":"2025-06-18T19:56:32Z","abstract_excerpt":"In this paper, we present an overview of ClinIQLink, a shared task, collocated with the 24th BioNLP workshop at ACL 2025, designed to stress-test large language models (LLMs) on medically-oriented question answering aimed at the level of a General Practitioner. The challenge supplies 4,978 expert-verified, medical source-grounded question-answer pairs that cover seven formats: true/false, multiple choice, unordered list, short answer, short-inverse, multi-hop, and multi-hop-inverse. Participating systems, bundled in Docker or Apptainer images, are executed on the CodaBench platform or the Univ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21597","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/2506.21597/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":"2506.21597","created_at":"2026-07-05T11:27:56.989626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21597v1","created_at":"2026-07-05T11:27:56.989626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21597","created_at":"2026-07-05T11:27:56.989626+00:00"},{"alias_kind":"pith_short_12","alias_value":"SEGXEEHRHO7C","created_at":"2026-07-05T11:27:56.989626+00:00"},{"alias_kind":"pith_short_16","alias_value":"SEGXEEHRHO7CY5V6","created_at":"2026-07-05T11:27:56.989626+00:00"},{"alias_kind":"pith_short_8","alias_value":"SEGXEEHR","created_at":"2026-07-05T11:27:56.989626+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/SEGXEEHRHO7CY5V66MMM4QA6PE","json":"https://pith.science/pith/SEGXEEHRHO7CY5V66MMM4QA6PE.json","graph_json":"https://pith.science/api/pith-number/SEGXEEHRHO7CY5V66MMM4QA6PE/graph.json","events_json":"https://pith.science/api/pith-number/SEGXEEHRHO7CY5V66MMM4QA6PE/events.json","paper":"https://pith.science/paper/SEGXEEHR"},"agent_actions":{"view_html":"https://pith.science/pith/SEGXEEHRHO7CY5V66MMM4QA6PE","download_json":"https://pith.science/pith/SEGXEEHRHO7CY5V66MMM4QA6PE.json","view_paper":"https://pith.science/paper/SEGXEEHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21597&json=true","fetch_graph":"https://pith.science/api/pith-number/SEGXEEHRHO7CY5V66MMM4QA6PE/graph.json","fetch_events":"https://pith.science/api/pith-number/SEGXEEHRHO7CY5V66MMM4QA6PE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SEGXEEHRHO7CY5V66MMM4QA6PE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SEGXEEHRHO7CY5V66MMM4QA6PE/action/storage_attestation","attest_author":"https://pith.science/pith/SEGXEEHRHO7CY5V66MMM4QA6PE/action/author_attestation","sign_citation":"https://pith.science/pith/SEGXEEHRHO7CY5V66MMM4QA6PE/action/citation_signature","submit_replication":"https://pith.science/pith/SEGXEEHRHO7CY5V66MMM4QA6PE/action/replication_record"}},"created_at":"2026-07-05T11:27:56.989626+00:00","updated_at":"2026-07-05T11:27:56.989626+00:00"}