{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FWHDH2IXUNVMF5TGE3PW4IF2VM","short_pith_number":"pith:FWHDH2IX","schema_version":"1.0","canonical_sha256":"2d8e33e917a36ac2f66626df6e20baab1d601a21c7efa8ecc25eff60947dad36","source":{"kind":"arxiv","id":"2406.19653","version":3},"attestation_state":"computed","paper":{"title":"ACES: Automatic Cohort Extraction System for Event-Stream Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alistair E. W. Johnson, Jack Gallifant, Justin Xu, Matthew B. A. McDermott","submitted_at":"2024-06-28T04:48:05Z","abstract_excerpt":"Reproducibility remains a significant challenge in machine learning (ML) for healthcare. Datasets, model pipelines, and even task or cohort definitions are often private in this field, leading to a significant barrier in sharing, iterating, and understanding ML results on electronic health record (EHR) datasets. We address a significant part of this problem by introducing the Automatic Cohort Extraction System (ACES) for event-stream data. This library is designed to simultaneously simplify the development of tasks and cohorts for ML in healthcare and also enable their reproduction, both at an"},"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":"2406.19653","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-28T04:48:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5ce3c9e7d3349c795510bebbc6e0f046f88c3f22e6940ec9c8925f0ea59202f8","abstract_canon_sha256":"374d2557be7194919c673c73f56c8ed193f67d5b1b2fe1be44ead7891c071ba1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:01.701254Z","signature_b64":"2DnOah2uKZ4hh6pcXUwwdOodFfvo/nYX3nxYSGC2T60o1N6GoidbxzwuymwM5icbGE91/Xgiwx3ua7HHQ6sADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d8e33e917a36ac2f66626df6e20baab1d601a21c7efa8ecc25eff60947dad36","last_reissued_at":"2026-07-05T10:22:01.700663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:01.700663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACES: Automatic Cohort Extraction System for Event-Stream Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alistair E. W. Johnson, Jack Gallifant, Justin Xu, Matthew B. A. McDermott","submitted_at":"2024-06-28T04:48:05Z","abstract_excerpt":"Reproducibility remains a significant challenge in machine learning (ML) for healthcare. Datasets, model pipelines, and even task or cohort definitions are often private in this field, leading to a significant barrier in sharing, iterating, and understanding ML results on electronic health record (EHR) datasets. We address a significant part of this problem by introducing the Automatic Cohort Extraction System (ACES) for event-stream data. This library is designed to simultaneously simplify the development of tasks and cohorts for ML in healthcare and also enable their reproduction, both at an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19653","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/2406.19653/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":"2406.19653","created_at":"2026-07-05T10:22:01.700729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19653v3","created_at":"2026-07-05T10:22:01.700729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19653","created_at":"2026-07-05T10:22:01.700729+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWHDH2IXUNVM","created_at":"2026-07-05T10:22:01.700729+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWHDH2IXUNVMF5TG","created_at":"2026-07-05T10:22:01.700729+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWHDH2IX","created_at":"2026-07-05T10:22:01.700729+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/FWHDH2IXUNVMF5TGE3PW4IF2VM","json":"https://pith.science/pith/FWHDH2IXUNVMF5TGE3PW4IF2VM.json","graph_json":"https://pith.science/api/pith-number/FWHDH2IXUNVMF5TGE3PW4IF2VM/graph.json","events_json":"https://pith.science/api/pith-number/FWHDH2IXUNVMF5TGE3PW4IF2VM/events.json","paper":"https://pith.science/paper/FWHDH2IX"},"agent_actions":{"view_html":"https://pith.science/pith/FWHDH2IXUNVMF5TGE3PW4IF2VM","download_json":"https://pith.science/pith/FWHDH2IXUNVMF5TGE3PW4IF2VM.json","view_paper":"https://pith.science/paper/FWHDH2IX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19653&json=true","fetch_graph":"https://pith.science/api/pith-number/FWHDH2IXUNVMF5TGE3PW4IF2VM/graph.json","fetch_events":"https://pith.science/api/pith-number/FWHDH2IXUNVMF5TGE3PW4IF2VM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWHDH2IXUNVMF5TGE3PW4IF2VM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWHDH2IXUNVMF5TGE3PW4IF2VM/action/storage_attestation","attest_author":"https://pith.science/pith/FWHDH2IXUNVMF5TGE3PW4IF2VM/action/author_attestation","sign_citation":"https://pith.science/pith/FWHDH2IXUNVMF5TGE3PW4IF2VM/action/citation_signature","submit_replication":"https://pith.science/pith/FWHDH2IXUNVMF5TGE3PW4IF2VM/action/replication_record"}},"created_at":"2026-07-05T10:22:01.700729+00:00","updated_at":"2026-07-05T10:22:01.700729+00:00"}