{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2CNLIB554DMLXZI7AQAQC5APDK","short_pith_number":"pith:2CNLIB55","schema_version":"1.0","canonical_sha256":"d09ab407bde0d8bbe51f040101740f1a9e94f577f39b4d5a70fbe003b21b89b1","source":{"kind":"arxiv","id":"2406.14780","version":2},"attestation_state":"computed","paper":{"title":"ACR: A Benchmark for Automatic Cohort Retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dung Ngoc Thai, Gleb Erofeev, Jose Ulises Mena, Karim Tarabishy, Ramy Eskander, Ravi B Parikh, Simran Tiwari, Victor Ardulov, Wael Salloum","submitted_at":"2024-06-20T23:04:06Z","abstract_excerpt":"Identifying patient cohorts is fundamental to numerous healthcare tasks, including clinical trial recruitment and retrospective studies. Current cohort retrieval methods in healthcare organizations rely on automated queries of structured data combined with manual curation, which are time-consuming, labor-intensive, and often yield low-quality results. Recent advancements in large language models (LLMs) and information retrieval (IR) offer promising avenues to revolutionize these systems. Major challenges include managing extensive eligibility criteria and handling the longitudinal nature of un"},"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":"2406.14780","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-20T23:04:06Z","cross_cats_sorted":[],"title_canon_sha256":"df249230e4eac58919896e5dc7e9c3808d5fc37bb57544fe4855235544d0093b","abstract_canon_sha256":"b03d70ebc1a355cdf39062133e3b2e199a70fa6b7d09b79d2a2885947bacbc89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:00.728754Z","signature_b64":"Uat4bgl1IjchWMEsejzzcxFO8oRePCw10fiIiFwpGdz7y9qzBflawnGrSnzhSS2ZiSw0dKO1Cu1MFr1OczxODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d09ab407bde0d8bbe51f040101740f1a9e94f577f39b4d5a70fbe003b21b89b1","last_reissued_at":"2026-07-05T08:39:00.728253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:00.728253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACR: A Benchmark for Automatic Cohort Retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dung Ngoc Thai, Gleb Erofeev, Jose Ulises Mena, Karim Tarabishy, Ramy Eskander, Ravi B Parikh, Simran Tiwari, Victor Ardulov, Wael Salloum","submitted_at":"2024-06-20T23:04:06Z","abstract_excerpt":"Identifying patient cohorts is fundamental to numerous healthcare tasks, including clinical trial recruitment and retrospective studies. Current cohort retrieval methods in healthcare organizations rely on automated queries of structured data combined with manual curation, which are time-consuming, labor-intensive, and often yield low-quality results. Recent advancements in large language models (LLMs) and information retrieval (IR) offer promising avenues to revolutionize these systems. Major challenges include managing extensive eligibility criteria and handling the longitudinal nature of un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14780","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/2406.14780/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":"2406.14780","created_at":"2026-07-05T08:39:00.728312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14780v2","created_at":"2026-07-05T08:39:00.728312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14780","created_at":"2026-07-05T08:39:00.728312+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CNLIB554DML","created_at":"2026-07-05T08:39:00.728312+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CNLIB554DMLXZI7","created_at":"2026-07-05T08:39:00.728312+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CNLIB55","created_at":"2026-07-05T08:39:00.728312+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10777","citing_title":"The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language Inference","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CNLIB554DMLXZI7AQAQC5APDK","json":"https://pith.science/pith/2CNLIB554DMLXZI7AQAQC5APDK.json","graph_json":"https://pith.science/api/pith-number/2CNLIB554DMLXZI7AQAQC5APDK/graph.json","events_json":"https://pith.science/api/pith-number/2CNLIB554DMLXZI7AQAQC5APDK/events.json","paper":"https://pith.science/paper/2CNLIB55"},"agent_actions":{"view_html":"https://pith.science/pith/2CNLIB554DMLXZI7AQAQC5APDK","download_json":"https://pith.science/pith/2CNLIB554DMLXZI7AQAQC5APDK.json","view_paper":"https://pith.science/paper/2CNLIB55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14780&json=true","fetch_graph":"https://pith.science/api/pith-number/2CNLIB554DMLXZI7AQAQC5APDK/graph.json","fetch_events":"https://pith.science/api/pith-number/2CNLIB554DMLXZI7AQAQC5APDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CNLIB554DMLXZI7AQAQC5APDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CNLIB554DMLXZI7AQAQC5APDK/action/storage_attestation","attest_author":"https://pith.science/pith/2CNLIB554DMLXZI7AQAQC5APDK/action/author_attestation","sign_citation":"https://pith.science/pith/2CNLIB554DMLXZI7AQAQC5APDK/action/citation_signature","submit_replication":"https://pith.science/pith/2CNLIB554DMLXZI7AQAQC5APDK/action/replication_record"}},"created_at":"2026-07-05T08:39:00.728312+00:00","updated_at":"2026-07-05T08:39:00.728312+00:00"}