{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U53HJKYGWAMFG7KW2S3PUFT4DB","short_pith_number":"pith:U53HJKYG","schema_version":"1.0","canonical_sha256":"a77674ab06b018537d56d4b6fa167c1858fb0a094e1bf9fb5df4cc6affc4575a","source":{"kind":"arxiv","id":"2607.18431","version":1},"attestation_state":"computed","paper":{"title":"Using binary silver labels in electronic health records-based computable phenotyping algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"stat.ME","authors_text":"Brian D. Williamson, Jennifer C. Nelson, Matthew T. Slaughter, Shuhe Wang","submitted_at":"2026-07-20T18:32:41Z","abstract_excerpt":"Gold-standard phenotype labels are often unavailable at scale in electronic health record (EHR) studies because they require manual chart review. Weakly supervised phenotyping methods instead use silver-standard labels, such as diagnosis-code counts, natural language processing (NLP) mentions, medication indicators, or laboratory thresholds. PheNorm is widely used for this purpose, but its original formulation was designed for count-valued silver labels and relies on log transformation, utilization normalization, and Gaussian mixture modeling. These steps are not directly suited to binary silv"},"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":"2607.18431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-07-20T18:32:41Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"889fe314aaa31eddae961a613946590cd3d20db0d675692cc46f8bcf48be5b93","abstract_canon_sha256":"5db4b9cc2340427adcc81ffeced3f738c5cc54c0aa44bbb471d387b7df020e0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:48.226218Z","signature_b64":"t4M0pAUtzxpFmdK4eMYigMpgu/96XE60UejiBioairHfioCxaFlkMWlxyyQ8leQVTT7Ymh/1MJcdHc9wsxwtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a77674ab06b018537d56d4b6fa167c1858fb0a094e1bf9fb5df4cc6affc4575a","last_reissued_at":"2026-07-22T00:22:48.225330Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:48.225330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using binary silver labels in electronic health records-based computable phenotyping algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"stat.ME","authors_text":"Brian D. Williamson, Jennifer C. Nelson, Matthew T. Slaughter, Shuhe Wang","submitted_at":"2026-07-20T18:32:41Z","abstract_excerpt":"Gold-standard phenotype labels are often unavailable at scale in electronic health record (EHR) studies because they require manual chart review. Weakly supervised phenotyping methods instead use silver-standard labels, such as diagnosis-code counts, natural language processing (NLP) mentions, medication indicators, or laboratory thresholds. PheNorm is widely used for this purpose, but its original formulation was designed for count-valued silver labels and relies on log transformation, utilization normalization, and Gaussian mixture modeling. These steps are not directly suited to binary silv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18431","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/2607.18431/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":"2607.18431","created_at":"2026-07-22T00:22:48.225780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18431v1","created_at":"2026-07-22T00:22:48.225780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18431","created_at":"2026-07-22T00:22:48.225780+00:00"},{"alias_kind":"pith_short_12","alias_value":"U53HJKYGWAMF","created_at":"2026-07-22T00:22:48.225780+00:00"},{"alias_kind":"pith_short_16","alias_value":"U53HJKYGWAMFG7KW","created_at":"2026-07-22T00:22:48.225780+00:00"},{"alias_kind":"pith_short_8","alias_value":"U53HJKYG","created_at":"2026-07-22T00:22:48.225780+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/U53HJKYGWAMFG7KW2S3PUFT4DB","json":"https://pith.science/pith/U53HJKYGWAMFG7KW2S3PUFT4DB.json","graph_json":"https://pith.science/api/pith-number/U53HJKYGWAMFG7KW2S3PUFT4DB/graph.json","events_json":"https://pith.science/api/pith-number/U53HJKYGWAMFG7KW2S3PUFT4DB/events.json","paper":"https://pith.science/paper/U53HJKYG"},"agent_actions":{"view_html":"https://pith.science/pith/U53HJKYGWAMFG7KW2S3PUFT4DB","download_json":"https://pith.science/pith/U53HJKYGWAMFG7KW2S3PUFT4DB.json","view_paper":"https://pith.science/paper/U53HJKYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18431&json=true","fetch_graph":"https://pith.science/api/pith-number/U53HJKYGWAMFG7KW2S3PUFT4DB/graph.json","fetch_events":"https://pith.science/api/pith-number/U53HJKYGWAMFG7KW2S3PUFT4DB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U53HJKYGWAMFG7KW2S3PUFT4DB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U53HJKYGWAMFG7KW2S3PUFT4DB/action/storage_attestation","attest_author":"https://pith.science/pith/U53HJKYGWAMFG7KW2S3PUFT4DB/action/author_attestation","sign_citation":"https://pith.science/pith/U53HJKYGWAMFG7KW2S3PUFT4DB/action/citation_signature","submit_replication":"https://pith.science/pith/U53HJKYGWAMFG7KW2S3PUFT4DB/action/replication_record"}},"created_at":"2026-07-22T00:22:48.225780+00:00","updated_at":"2026-07-22T00:22:48.225780+00:00"}