{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YNUHR2Q2SMM6N4UCW36KUR5RCW","short_pith_number":"pith:YNUHR2Q2","canonical_record":{"source":{"id":"2412.11472","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T06:19:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"683821f6bc77287adb3c9e1abb91faa77ba05885b89326da0fc07ee96bebe505","abstract_canon_sha256":"611141e549a1ae189422759af57e1defac2f775eb301f79d2bf74c3fdc6062bb"},"schema_version":"1.0"},"canonical_sha256":"c36878ea1a9319e6f282b6fcaa47b115af005f3267de0863d3a28fdaf7b9b452","source":{"kind":"arxiv","id":"2412.11472","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11472","created_at":"2026-07-05T09:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11472v1","created_at":"2026-07-05T09:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11472","created_at":"2026-07-05T09:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"YNUHR2Q2SMM6","created_at":"2026-07-05T09:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"YNUHR2Q2SMM6N4UC","created_at":"2026-07-05T09:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"YNUHR2Q2","created_at":"2026-07-05T09:49:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YNUHR2Q2SMM6N4UCW36KUR5RCW","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11472","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T06:19:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"683821f6bc77287adb3c9e1abb91faa77ba05885b89326da0fc07ee96bebe505","abstract_canon_sha256":"611141e549a1ae189422759af57e1defac2f775eb301f79d2bf74c3fdc6062bb"},"schema_version":"1.0"},"canonical_sha256":"c36878ea1a9319e6f282b6fcaa47b115af005f3267de0863d3a28fdaf7b9b452","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:33.567769Z","signature_b64":"jx1HZs+nqiSJn/48R1b5SnIpTUzG+ICaa9h6HdGys1b4fCe1WLRvyy892PROgvWt5nGw8rMmUJNGjrqYiu4QAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c36878ea1a9319e6f282b6fcaa47b115af005f3267de0863d3a28fdaf7b9b452","last_reissued_at":"2026-07-05T09:49:33.567397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:33.567397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11472","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z97wVAtUOnErOVIkOlWKQeHhbNgxUAKE7xcGldKwOLCTcGLF2Kz2Ns9e6Tq0psoBk7hNCahFmUB3L/K/zDDkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:56:03.619246Z"},"content_sha256":"68510791fbb69b3190a5840cf7f57c887f5086161c38fac07cd3e4c25580a561","schema_version":"1.0","event_id":"sha256:68510791fbb69b3190a5840cf7f57c887f5086161c38fac07cd3e4c25580a561"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YNUHR2Q2SMM6N4UCW36KUR5RCW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Foundation Language Models (FLMs) for Automated Cohort Extraction from Large EHR Databases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexandra Meliou, Madalina Fiterau, Purity Mugambi","submitted_at":"2024-12-16T06:19:35Z","abstract_excerpt":"A crucial step in cohort studies is to extract the required cohort from one or more study datasets. This step is time-consuming, especially when a researcher is presented with a dataset that they have not previously worked with. When the cohort has to be extracted from multiple datasets, cohort extraction can be extremely laborious. In this study, we present an approach for partially automating cohort extraction from multiple electronic health record (EHR) databases. We formulate the guided multi-dataset cohort extraction problem in which selection criteria are first converted into queries, tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11472","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/2412.11472/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":"2026-07-05T09:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BGzHMjkWF7yMrgTSTMijNzTvT7tnN/U5zVuz8JOOt+ajDmPaoXTVNazbvWFcNDW19z8Lp/Aip5+fN/X6/SiDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:56:03.620230Z"},"content_sha256":"633a21dec4c3b9c758670f3e5f3a7734298759aac09d0edd14df9b7edbc85735","schema_version":"1.0","event_id":"sha256:633a21dec4c3b9c758670f3e5f3a7734298759aac09d0edd14df9b7edbc85735"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YNUHR2Q2SMM6N4UCW36KUR5RCW/bundle.json","state_url":"https://pith.science/pith/YNUHR2Q2SMM6N4UCW36KUR5RCW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YNUHR2Q2SMM6N4UCW36KUR5RCW/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":"2026-08-03T15:56:03Z","links":{"resolver":"https://pith.science/pith/YNUHR2Q2SMM6N4UCW36KUR5RCW","bundle":"https://pith.science/pith/YNUHR2Q2SMM6N4UCW36KUR5RCW/bundle.json","state":"https://pith.science/pith/YNUHR2Q2SMM6N4UCW36KUR5RCW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YNUHR2Q2SMM6N4UCW36KUR5RCW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YNUHR2Q2SMM6N4UCW36KUR5RCW","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":"611141e549a1ae189422759af57e1defac2f775eb301f79d2bf74c3fdc6062bb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T06:19:35Z","title_canon_sha256":"683821f6bc77287adb3c9e1abb91faa77ba05885b89326da0fc07ee96bebe505"},"schema_version":"1.0","source":{"id":"2412.11472","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11472","created_at":"2026-07-05T09:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11472v1","created_at":"2026-07-05T09:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11472","created_at":"2026-07-05T09:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"YNUHR2Q2SMM6","created_at":"2026-07-05T09:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"YNUHR2Q2SMM6N4UC","created_at":"2026-07-05T09:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"YNUHR2Q2","created_at":"2026-07-05T09:49:33Z"}],"graph_snapshots":[{"event_id":"sha256:633a21dec4c3b9c758670f3e5f3a7734298759aac09d0edd14df9b7edbc85735","target":"graph","created_at":"2026-07-05T09:49:33Z","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/2412.11472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A crucial step in cohort studies is to extract the required cohort from one or more study datasets. This step is time-consuming, especially when a researcher is presented with a dataset that they have not previously worked with. When the cohort has to be extracted from multiple datasets, cohort extraction can be extremely laborious. In this study, we present an approach for partially automating cohort extraction from multiple electronic health record (EHR) databases. We formulate the guided multi-dataset cohort extraction problem in which selection criteria are first converted into queries, tr","authors_text":"Alexandra Meliou, Madalina Fiterau, Purity Mugambi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T06:19:35Z","title":"Leveraging Foundation Language Models (FLMs) for Automated Cohort Extraction from Large EHR Databases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11472","kind":"arxiv","version":1},"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":"sha256:68510791fbb69b3190a5840cf7f57c887f5086161c38fac07cd3e4c25580a561","target":"record","created_at":"2026-07-05T09:49:33Z","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":"611141e549a1ae189422759af57e1defac2f775eb301f79d2bf74c3fdc6062bb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T06:19:35Z","title_canon_sha256":"683821f6bc77287adb3c9e1abb91faa77ba05885b89326da0fc07ee96bebe505"},"schema_version":"1.0","source":{"id":"2412.11472","kind":"arxiv","version":1}},"canonical_sha256":"c36878ea1a9319e6f282b6fcaa47b115af005f3267de0863d3a28fdaf7b9b452","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c36878ea1a9319e6f282b6fcaa47b115af005f3267de0863d3a28fdaf7b9b452","first_computed_at":"2026-07-05T09:49:33.567397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:33.567397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jx1HZs+nqiSJn/48R1b5SnIpTUzG+ICaa9h6HdGys1b4fCe1WLRvyy892PROgvWt5nGw8rMmUJNGjrqYiu4QAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:33.567769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11472","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68510791fbb69b3190a5840cf7f57c887f5086161c38fac07cd3e4c25580a561","sha256:633a21dec4c3b9c758670f3e5f3a7734298759aac09d0edd14df9b7edbc85735"],"state_sha256":"179bf9fb47bf3d338e7c1862d6aa76bc71b6f98df74a893a8a124eafc803f88e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c+0I2l2XyxwjxSH3CH0hVdPrFnfFeqM6015nak4P0jQtAfs0xyRxfXndXZIqZxVQrr88c2kC05MxBQp2jRx2DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:56:03.627571Z","bundle_sha256":"26e817287d952e28ec178d7771034dd3298a8be17f01209daf23c838d7dff6d2"}}