{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:44MRCLGHD34B63GXHRC3MBAICJ","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":"d58ebc0d7db94a5e5f7e4646128bb75dccd336b2eb74a45534ac34e8cde727bf","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2020-01-13T22:58:48Z","title_canon_sha256":"264230e641cf19ad64ff9286daa776cc3eaf0ad793b439458c824697830b76cf"},"schema_version":"1.0","source":{"id":"2001.09765","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.09765","created_at":"2026-07-05T00:36:03Z"},{"alias_kind":"arxiv_version","alias_value":"2001.09765v1","created_at":"2026-07-05T00:36:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.09765","created_at":"2026-07-05T00:36:03Z"},{"alias_kind":"pith_short_12","alias_value":"44MRCLGHD34B","created_at":"2026-07-05T00:36:03Z"},{"alias_kind":"pith_short_16","alias_value":"44MRCLGHD34B63GX","created_at":"2026-07-05T00:36:03Z"},{"alias_kind":"pith_short_8","alias_value":"44MRCLGH","created_at":"2026-07-05T00:36:03Z"}],"graph_snapshots":[{"event_id":"sha256:5637477109a611a8fe43fabf0b111ec4eb21462ad5fd5e23c69c85279c081446","target":"graph","created_at":"2026-07-05T00:36:03Z","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/2001.09765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Objective Electronic health records (EHRs) are a promising source of data for health outcomes research in oncology. A challenge in using EHR data is that selecting cohorts of patients often requires information in unstructured parts of the record. Machine learning has been used to address this, but even high-performing algorithms may select patients in a non-random manner and bias the resulting cohort. To improve the efficiency of cohort selection while measuring potential bias, we introduce a technique called Model-Assisted Cohort Selection (MACS) with Bias Analysis and apply it to the select","authors_text":"Benjamin Birnbaum, Evan Estola, Joshua Haimson, Katharina Seidl-Rathkopf, Lucy He, Melissa Estevez, Monica Agrawal, Nathan Nussbaum, Paul Richardson, Peter Larson","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2020-01-13T22:58:48Z","title":"Model-assisted cohort selection with bias analysis for generating large-scale cohorts from the EHR for oncology research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.09765","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":"sha256:149244699038bbbd698df604b2b35c9e9f612c8dcaad9ae69e8eb33a1b45231a","target":"record","created_at":"2026-07-05T00:36:03Z","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":"d58ebc0d7db94a5e5f7e4646128bb75dccd336b2eb74a45534ac34e8cde727bf","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2020-01-13T22:58:48Z","title_canon_sha256":"264230e641cf19ad64ff9286daa776cc3eaf0ad793b439458c824697830b76cf"},"schema_version":"1.0","source":{"id":"2001.09765","kind":"arxiv","version":1}},"canonical_sha256":"e719112cc71ef81f6cd73c45b604081252189691960a523596942e89a99ff3ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e719112cc71ef81f6cd73c45b604081252189691960a523596942e89a99ff3ba","first_computed_at":"2026-07-05T00:36:03.544997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:36:03.544997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8zB/6ajcs0r4ZO0oU9MZXPFInP5fF9THlsZSA7soUxJ1etRp2Xl3ZdGW5LJ1lt2RrW/eEzzySemmGFdeq+BHDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:36:03.545758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.09765","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:149244699038bbbd698df604b2b35c9e9f612c8dcaad9ae69e8eb33a1b45231a","sha256:5637477109a611a8fe43fabf0b111ec4eb21462ad5fd5e23c69c85279c081446"],"state_sha256":"3e32f3cb296d1e0e5a78ca34bc81322bd24d08fdfe9e333de6bbd99cc72df07c"}