{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZTEDMLCN6DR3LLMXAZJCAOEOUL","short_pith_number":"pith:ZTEDMLCN","schema_version":"1.0","canonical_sha256":"ccc8362c4df0e3b5ad97065220388ea2ee94008cb125f3cdcf5c3a320e16c7f7","source":{"kind":"arxiv","id":"2206.09107","version":2},"attestation_state":"computed","paper":{"title":"Tree-Guided Rare Feature Selection and Logic Aggregation with Electronic Health Records Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fei Wang, Jianmin Chen, Kun Chen, Robert H. Aseltine","submitted_at":"2022-06-18T03:52:43Z","abstract_excerpt":"Statistical learning with a large number of rare binary features is commonly encountered in analyzing electronic health records (EHR) data, especially in the modeling of disease onset with prior medical diagnoses and procedures. Dealing with the resulting highly sparse and large-scale binary feature matrix is notoriously challenging as conventional methods may suffer from a lack of power in testing and inconsistency in model fitting while machine learning methods may suffer from the inability of producing interpretable results or clinically-meaningful risk factors. To improve EHR-based modelin"},"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":"2206.09107","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-18T03:52:43Z","cross_cats_sorted":["stat.AP","stat.ME","stat.ML"],"title_canon_sha256":"84c071d73db5f6d6c3417f40205ec166694fa0b3b3e7e5ac181771cc8b396efc","abstract_canon_sha256":"184e46f0c039cdd9fcb53598668a02ab8622df5a778584abd6c44fc608f06fdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:28.439174Z","signature_b64":"3ZZIlhpf7MB0GVwvj22h5Dbj7Xeufsi+gbdbtn9XYZe0+7el03uRRwA2cV3AvS5xPLVg+DwQPgtYjpk/KrL9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccc8362c4df0e3b5ad97065220388ea2ee94008cb125f3cdcf5c3a320e16c7f7","last_reissued_at":"2026-07-05T07:49:28.438704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:28.438704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tree-Guided Rare Feature Selection and Logic Aggregation with Electronic Health Records Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fei Wang, Jianmin Chen, Kun Chen, Robert H. Aseltine","submitted_at":"2022-06-18T03:52:43Z","abstract_excerpt":"Statistical learning with a large number of rare binary features is commonly encountered in analyzing electronic health records (EHR) data, especially in the modeling of disease onset with prior medical diagnoses and procedures. Dealing with the resulting highly sparse and large-scale binary feature matrix is notoriously challenging as conventional methods may suffer from a lack of power in testing and inconsistency in model fitting while machine learning methods may suffer from the inability of producing interpretable results or clinically-meaningful risk factors. To improve EHR-based modelin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09107","kind":"arxiv","version":2},"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/2206.09107/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":"2206.09107","created_at":"2026-07-05T07:49:28.438763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.09107v2","created_at":"2026-07-05T07:49:28.438763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09107","created_at":"2026-07-05T07:49:28.438763+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTEDMLCN6DR3","created_at":"2026-07-05T07:49:28.438763+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTEDMLCN6DR3LLMX","created_at":"2026-07-05T07:49:28.438763+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTEDMLCN","created_at":"2026-07-05T07:49:28.438763+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/ZTEDMLCN6DR3LLMXAZJCAOEOUL","json":"https://pith.science/pith/ZTEDMLCN6DR3LLMXAZJCAOEOUL.json","graph_json":"https://pith.science/api/pith-number/ZTEDMLCN6DR3LLMXAZJCAOEOUL/graph.json","events_json":"https://pith.science/api/pith-number/ZTEDMLCN6DR3LLMXAZJCAOEOUL/events.json","paper":"https://pith.science/paper/ZTEDMLCN"},"agent_actions":{"view_html":"https://pith.science/pith/ZTEDMLCN6DR3LLMXAZJCAOEOUL","download_json":"https://pith.science/pith/ZTEDMLCN6DR3LLMXAZJCAOEOUL.json","view_paper":"https://pith.science/paper/ZTEDMLCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.09107&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTEDMLCN6DR3LLMXAZJCAOEOUL/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTEDMLCN6DR3LLMXAZJCAOEOUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTEDMLCN6DR3LLMXAZJCAOEOUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTEDMLCN6DR3LLMXAZJCAOEOUL/action/storage_attestation","attest_author":"https://pith.science/pith/ZTEDMLCN6DR3LLMXAZJCAOEOUL/action/author_attestation","sign_citation":"https://pith.science/pith/ZTEDMLCN6DR3LLMXAZJCAOEOUL/action/citation_signature","submit_replication":"https://pith.science/pith/ZTEDMLCN6DR3LLMXAZJCAOEOUL/action/replication_record"}},"created_at":"2026-07-05T07:49:28.438763+00:00","updated_at":"2026-07-05T07:49:28.438763+00:00"}