{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QCLFSZPCEXKHI4W55JNAOXYCKV","short_pith_number":"pith:QCLFSZPC","schema_version":"1.0","canonical_sha256":"80965965e225d47472ddea5a075f0255423840bec117795df04475b9c93c20c5","source":{"kind":"arxiv","id":"2305.07637","version":3},"attestation_state":"computed","paper":{"title":"Text2Cohort: Facilitating Intuitive Access to Biomedical Data with Natural Language Cohort Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC","cs.IR"],"primary_cat":"cs.LG","authors_text":"Adway Kanhere, Paul H. Yi, Pranav Kulkarni, Vishwa S. Parekh","submitted_at":"2023-05-12T17:46:06Z","abstract_excerpt":"The Imaging Data Commons (IDC) is a cloud-based database that provides researchers with open access to cancer imaging data, with the goal of facilitating collaboration. However, cohort discovery within the IDC database has a significant technical learning curve. Recently, large language models (LLM) have demonstrated exceptional utility for natural language processing tasks. We developed Text2Cohort, a LLM-powered toolkit to facilitate user-friendly natural language cohort discovery in the IDC. Our method translates user input into IDC queries using grounding techniques and returns the query's"},"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":"2305.07637","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-12T17:46:06Z","cross_cats_sorted":["cs.CL","cs.HC","cs.IR"],"title_canon_sha256":"c4806eb694856f8fbdfe7b241d458395fd9f1e07a76905ace7ae3c7edfa936ff","abstract_canon_sha256":"4efcd0001f6476bd9fdf87fb444a47f8585e9722a28196b6ac257f1bc73b3092"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:41.311797Z","signature_b64":"0y1X/bXe2Z0pWe9WFVHxXJK/E30vcc6s4LjF8EZ8L/z0ObHno50Ov745hOqw/iF9NlALd5DABdYRUZ0kZfs+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80965965e225d47472ddea5a075f0255423840bec117795df04475b9c93c20c5","last_reissued_at":"2026-07-05T07:16:41.311434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:41.311434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text2Cohort: Facilitating Intuitive Access to Biomedical Data with Natural Language Cohort Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC","cs.IR"],"primary_cat":"cs.LG","authors_text":"Adway Kanhere, Paul H. Yi, Pranav Kulkarni, Vishwa S. Parekh","submitted_at":"2023-05-12T17:46:06Z","abstract_excerpt":"The Imaging Data Commons (IDC) is a cloud-based database that provides researchers with open access to cancer imaging data, with the goal of facilitating collaboration. However, cohort discovery within the IDC database has a significant technical learning curve. Recently, large language models (LLM) have demonstrated exceptional utility for natural language processing tasks. We developed Text2Cohort, a LLM-powered toolkit to facilitate user-friendly natural language cohort discovery in the IDC. Our method translates user input into IDC queries using grounding techniques and returns the query's"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07637","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/2305.07637/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":"2305.07637","created_at":"2026-07-05T07:16:41.311489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.07637v3","created_at":"2026-07-05T07:16:41.311489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07637","created_at":"2026-07-05T07:16:41.311489+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCLFSZPCEXKH","created_at":"2026-07-05T07:16:41.311489+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCLFSZPCEXKHI4W5","created_at":"2026-07-05T07:16:41.311489+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCLFSZPC","created_at":"2026-07-05T07:16:41.311489+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/QCLFSZPCEXKHI4W55JNAOXYCKV","json":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV.json","graph_json":"https://pith.science/api/pith-number/QCLFSZPCEXKHI4W55JNAOXYCKV/graph.json","events_json":"https://pith.science/api/pith-number/QCLFSZPCEXKHI4W55JNAOXYCKV/events.json","paper":"https://pith.science/paper/QCLFSZPC"},"agent_actions":{"view_html":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV","download_json":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV.json","view_paper":"https://pith.science/paper/QCLFSZPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.07637&json=true","fetch_graph":"https://pith.science/api/pith-number/QCLFSZPCEXKHI4W55JNAOXYCKV/graph.json","fetch_events":"https://pith.science/api/pith-number/QCLFSZPCEXKHI4W55JNAOXYCKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV/action/storage_attestation","attest_author":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV/action/author_attestation","sign_citation":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV/action/citation_signature","submit_replication":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV/action/replication_record"}},"created_at":"2026-07-05T07:16:41.311489+00:00","updated_at":"2026-07-05T07:16:41.311489+00:00"}