{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QX7G5C2JTVAKRCEW7OWCLAAX4N","short_pith_number":"pith:QX7G5C2J","schema_version":"1.0","canonical_sha256":"85fe6e8b499d40a88896fbac258017e3766ab227ea514ab7b8a4fc9749d857f3","source":{"kind":"arxiv","id":"2507.01049","version":1},"attestation_state":"computed","paper":{"title":"Cohort Retrieval using Dense Passage Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Pranav Jadhav","submitted_at":"2025-06-26T18:11:25Z","abstract_excerpt":"Patient cohort retrieval is a pivotal task in medical research and clinical practice, enabling the identification of specific patient groups from extensive electronic health records (EHRs). In this work, we address the challenge of cohort retrieval in the echocardiography domain by applying Dense Passage Retrieval (DPR), a prominent methodology in semantic search. We propose a systematic approach to transform an echocardiographic EHR dataset of unstructured nature into a Query-Passage dataset, framing the problem as a Cohort Retrieval task. Additionally, we design and implement evaluation metr"},"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":"2507.01049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-26T18:11:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"987b0f34aa45c9f35224cfd051ac057d6fb0a1d6902fc32edc1f7d3d3cd6da18","abstract_canon_sha256":"21425512cddd70b306530b1ca2128a3cc49a379ac029de45bd2863942776a626"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:24.240277Z","signature_b64":"z/LHtsCV7ncTXFjL4g1YO+/4dYGesXQrGKV+j4Ct52CBvsxFXNIMgd8yzVca5jqbQeIrh8Th0Ozv7lSLhQ8XDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85fe6e8b499d40a88896fbac258017e3766ab227ea514ab7b8a4fc9749d857f3","last_reissued_at":"2026-07-05T11:30:24.239835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:24.239835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cohort Retrieval using Dense Passage Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Pranav Jadhav","submitted_at":"2025-06-26T18:11:25Z","abstract_excerpt":"Patient cohort retrieval is a pivotal task in medical research and clinical practice, enabling the identification of specific patient groups from extensive electronic health records (EHRs). In this work, we address the challenge of cohort retrieval in the echocardiography domain by applying Dense Passage Retrieval (DPR), a prominent methodology in semantic search. We propose a systematic approach to transform an echocardiographic EHR dataset of unstructured nature into a Query-Passage dataset, framing the problem as a Cohort Retrieval task. Additionally, we design and implement evaluation metr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01049","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/2507.01049/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":"2507.01049","created_at":"2026-07-05T11:30:24.239892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01049v1","created_at":"2026-07-05T11:30:24.239892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01049","created_at":"2026-07-05T11:30:24.239892+00:00"},{"alias_kind":"pith_short_12","alias_value":"QX7G5C2JTVAK","created_at":"2026-07-05T11:30:24.239892+00:00"},{"alias_kind":"pith_short_16","alias_value":"QX7G5C2JTVAKRCEW","created_at":"2026-07-05T11:30:24.239892+00:00"},{"alias_kind":"pith_short_8","alias_value":"QX7G5C2J","created_at":"2026-07-05T11:30:24.239892+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/QX7G5C2JTVAKRCEW7OWCLAAX4N","json":"https://pith.science/pith/QX7G5C2JTVAKRCEW7OWCLAAX4N.json","graph_json":"https://pith.science/api/pith-number/QX7G5C2JTVAKRCEW7OWCLAAX4N/graph.json","events_json":"https://pith.science/api/pith-number/QX7G5C2JTVAKRCEW7OWCLAAX4N/events.json","paper":"https://pith.science/paper/QX7G5C2J"},"agent_actions":{"view_html":"https://pith.science/pith/QX7G5C2JTVAKRCEW7OWCLAAX4N","download_json":"https://pith.science/pith/QX7G5C2JTVAKRCEW7OWCLAAX4N.json","view_paper":"https://pith.science/paper/QX7G5C2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01049&json=true","fetch_graph":"https://pith.science/api/pith-number/QX7G5C2JTVAKRCEW7OWCLAAX4N/graph.json","fetch_events":"https://pith.science/api/pith-number/QX7G5C2JTVAKRCEW7OWCLAAX4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QX7G5C2JTVAKRCEW7OWCLAAX4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QX7G5C2JTVAKRCEW7OWCLAAX4N/action/storage_attestation","attest_author":"https://pith.science/pith/QX7G5C2JTVAKRCEW7OWCLAAX4N/action/author_attestation","sign_citation":"https://pith.science/pith/QX7G5C2JTVAKRCEW7OWCLAAX4N/action/citation_signature","submit_replication":"https://pith.science/pith/QX7G5C2JTVAKRCEW7OWCLAAX4N/action/replication_record"}},"created_at":"2026-07-05T11:30:24.239892+00:00","updated_at":"2026-07-05T11:30:24.239892+00:00"}