{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:27EEGQY75F4WH7LAJVTO5PERWT","short_pith_number":"pith:27EEGQY7","schema_version":"1.0","canonical_sha256":"d7c843431fe97963fd604d66eebc91b4edf19149a08b381e10c27c3d7691d60d","source":{"kind":"arxiv","id":"1703.02236","version":2},"attestation_state":"computed","paper":{"title":"Propensity score prediction for electronic healthcare databases using Super Learner and High-dimensional Propensity Score Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.AP","authors_text":"Cheng Ju, Jessica M Franklin, Mark J. van der Laan, Mary Combs, Richard Wyss, Samuel D Lendle, Sebastian Schneeweiss","submitted_at":"2017-03-07T06:38:02Z","abstract_excerpt":"The optimal learner for prediction modeling varies depending on the underlying data-generating distribution. Super Learner (SL) is a generic ensemble learning algorithm that uses cross-validation to select among a \"library\" of candidate prediction models. The SL is not restricted to a single prediction model, but uses the strengths of a variety of learning algorithms to adapt to different databases. While the SL has been shown to perform well in a number of settings, it has not been thoroughly evaluated in large electronic healthcare databases that are common in pharmacoepidemiology and compar"},"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":"1703.02236","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2017-03-07T06:38:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2945e58b357e29767756df1af7ce4045c9521527ee3eb41efdfe340cc252e7fe","abstract_canon_sha256":"0ea2294342204195fe770d7430e5f2be37b6e2a8ac094a78505c5208882b1dc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:41.663430Z","signature_b64":"u5Zhha+Pk0zNIzoMrW8iqyv0jGC8E71gMSIOKwsHW+xXpxYx9RK5dfBROoCs/3rMHVg9y++s5dsUCkBkU5ZLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7c843431fe97963fd604d66eebc91b4edf19149a08b381e10c27c3d7691d60d","last_reissued_at":"2026-05-18T00:48:41.662975Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:41.662975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Propensity score prediction for electronic healthcare databases using Super Learner and High-dimensional Propensity Score Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.AP","authors_text":"Cheng Ju, Jessica M Franklin, Mark J. van der Laan, Mary Combs, Richard Wyss, Samuel D Lendle, Sebastian Schneeweiss","submitted_at":"2017-03-07T06:38:02Z","abstract_excerpt":"The optimal learner for prediction modeling varies depending on the underlying data-generating distribution. Super Learner (SL) is a generic ensemble learning algorithm that uses cross-validation to select among a \"library\" of candidate prediction models. The SL is not restricted to a single prediction model, but uses the strengths of a variety of learning algorithms to adapt to different databases. While the SL has been shown to perform well in a number of settings, it has not been thoroughly evaluated in large electronic healthcare databases that are common in pharmacoepidemiology and compar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.02236","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":""},"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":"1703.02236","created_at":"2026-05-18T00:48:41.663043+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.02236v2","created_at":"2026-05-18T00:48:41.663043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.02236","created_at":"2026-05-18T00:48:41.663043+00:00"},{"alias_kind":"pith_short_12","alias_value":"27EEGQY75F4W","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"27EEGQY75F4WH7LA","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"27EEGQY7","created_at":"2026-05-18T12:30:55.937587+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/27EEGQY75F4WH7LAJVTO5PERWT","json":"https://pith.science/pith/27EEGQY75F4WH7LAJVTO5PERWT.json","graph_json":"https://pith.science/api/pith-number/27EEGQY75F4WH7LAJVTO5PERWT/graph.json","events_json":"https://pith.science/api/pith-number/27EEGQY75F4WH7LAJVTO5PERWT/events.json","paper":"https://pith.science/paper/27EEGQY7"},"agent_actions":{"view_html":"https://pith.science/pith/27EEGQY75F4WH7LAJVTO5PERWT","download_json":"https://pith.science/pith/27EEGQY75F4WH7LAJVTO5PERWT.json","view_paper":"https://pith.science/paper/27EEGQY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.02236&json=true","fetch_graph":"https://pith.science/api/pith-number/27EEGQY75F4WH7LAJVTO5PERWT/graph.json","fetch_events":"https://pith.science/api/pith-number/27EEGQY75F4WH7LAJVTO5PERWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27EEGQY75F4WH7LAJVTO5PERWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27EEGQY75F4WH7LAJVTO5PERWT/action/storage_attestation","attest_author":"https://pith.science/pith/27EEGQY75F4WH7LAJVTO5PERWT/action/author_attestation","sign_citation":"https://pith.science/pith/27EEGQY75F4WH7LAJVTO5PERWT/action/citation_signature","submit_replication":"https://pith.science/pith/27EEGQY75F4WH7LAJVTO5PERWT/action/replication_record"}},"created_at":"2026-05-18T00:48:41.663043+00:00","updated_at":"2026-05-18T00:48:41.663043+00:00"}