{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QCLFSZPCEXKHI4W55JNAOXYCKV","short_pith_number":"pith:QCLFSZPC","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"},"canonical_sha256":"80965965e225d47472ddea5a075f0255423840bec117795df04475b9c93c20c5","source":{"kind":"arxiv","id":"2305.07637","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07637","created_at":"2026-07-05T07:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07637v3","created_at":"2026-07-05T07:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07637","created_at":"2026-07-05T07:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"QCLFSZPCEXKH","created_at":"2026-07-05T07:16:41Z"},{"alias_kind":"pith_short_16","alias_value":"QCLFSZPCEXKHI4W5","created_at":"2026-07-05T07:16:41Z"},{"alias_kind":"pith_short_8","alias_value":"QCLFSZPC","created_at":"2026-07-05T07:16:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QCLFSZPCEXKHI4W55JNAOXYCKV","target":"record","payload":{"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"},"canonical_sha256":"80965965e225d47472ddea5a075f0255423840bec117795df04475b9c93c20c5","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"},"source_kind":"arxiv","source_id":"2305.07637","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:16:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CbjnuI8qdSYiFSEW8qGIcuB8A/PvgDb4+qGi9/hrqsgeuInUHqPn21RrXw587Ve3OvOijemDs+60RBFE1kFSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:15:23.286307Z"},"content_sha256":"931eb7ec332ca5b12ad9f260f6c426e5c92edb163e96145b1226d3984ef3d90b","schema_version":"1.0","event_id":"sha256:931eb7ec332ca5b12ad9f260f6c426e5c92edb163e96145b1226d3984ef3d90b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QCLFSZPCEXKHI4W55JNAOXYCKV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:16:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cXFSq4JmA24ULOTBz6yUBagpveau23EORPvaWZ6A/GajY3UVMK7BUKyFKyVH3IC7XkT9IYpsq/m7llR00UkCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:15:23.286706Z"},"content_sha256":"370e66592e8913a1303eccc0f3e64f746c9d136006365435c38ce6969c25850b","schema_version":"1.0","event_id":"sha256:370e66592e8913a1303eccc0f3e64f746c9d136006365435c38ce6969c25850b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV/bundle.json","state_url":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QCLFSZPCEXKHI4W55JNAOXYCKV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-05T13:15:23Z","links":{"resolver":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV","bundle":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV/bundle.json","state":"https://pith.science/pith/QCLFSZPCEXKHI4W55JNAOXYCKV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QCLFSZPCEXKHI4W55JNAOXYCKV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QCLFSZPCEXKHI4W55JNAOXYCKV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4efcd0001f6476bd9fdf87fb444a47f8585e9722a28196b6ac257f1bc73b3092","cross_cats_sorted":["cs.CL","cs.HC","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-12T17:46:06Z","title_canon_sha256":"c4806eb694856f8fbdfe7b241d458395fd9f1e07a76905ace7ae3c7edfa936ff"},"schema_version":"1.0","source":{"id":"2305.07637","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07637","created_at":"2026-07-05T07:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07637v3","created_at":"2026-07-05T07:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07637","created_at":"2026-07-05T07:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"QCLFSZPCEXKH","created_at":"2026-07-05T07:16:41Z"},{"alias_kind":"pith_short_16","alias_value":"QCLFSZPCEXKHI4W5","created_at":"2026-07-05T07:16:41Z"},{"alias_kind":"pith_short_8","alias_value":"QCLFSZPC","created_at":"2026-07-05T07:16:41Z"}],"graph_snapshots":[{"event_id":"sha256:370e66592e8913a1303eccc0f3e64f746c9d136006365435c38ce6969c25850b","target":"graph","created_at":"2026-07-05T07:16:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.07637/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adway Kanhere, Paul H. Yi, Pranav Kulkarni, Vishwa S. Parekh","cross_cats":["cs.CL","cs.HC","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-12T17:46:06Z","title":"Text2Cohort: Facilitating Intuitive Access to Biomedical Data with Natural Language Cohort Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07637","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:931eb7ec332ca5b12ad9f260f6c426e5c92edb163e96145b1226d3984ef3d90b","target":"record","created_at":"2026-07-05T07:16:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4efcd0001f6476bd9fdf87fb444a47f8585e9722a28196b6ac257f1bc73b3092","cross_cats_sorted":["cs.CL","cs.HC","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-12T17:46:06Z","title_canon_sha256":"c4806eb694856f8fbdfe7b241d458395fd9f1e07a76905ace7ae3c7edfa936ff"},"schema_version":"1.0","source":{"id":"2305.07637","kind":"arxiv","version":3}},"canonical_sha256":"80965965e225d47472ddea5a075f0255423840bec117795df04475b9c93c20c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80965965e225d47472ddea5a075f0255423840bec117795df04475b9c93c20c5","first_computed_at":"2026-07-05T07:16:41.311434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:41.311434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0y1X/bXe2Z0pWe9WFVHxXJK/E30vcc6s4LjF8EZ8L/z0ObHno50Ov745hOqw/iF9NlALd5DABdYRUZ0kZfs+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:41.311797Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.07637","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:931eb7ec332ca5b12ad9f260f6c426e5c92edb163e96145b1226d3984ef3d90b","sha256:370e66592e8913a1303eccc0f3e64f746c9d136006365435c38ce6969c25850b"],"state_sha256":"50ff0fc8cfd7f1ba0a483aaffe87cbddca789647819cd60943d9bade2af6e722"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ocHHhWlFrh+fbbMaow9rMn1+6NOUCSYqNA6kR5/plUFnJJTZTfKcKMhoNMoZCtpRfzUsxosNwGTNqcYAkddDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T13:15:23.288738Z","bundle_sha256":"d42369bbc7a6a380dc561504c9d3574aa70bbfea4dd7279b277867490c6292b2"}}