{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3QP4PMIGYIF7JGYMGIDDEEVDGM","short_pith_number":"pith:3QP4PMIG","schema_version":"1.0","canonical_sha256":"dc1fc7b106c20bf49b0c32063212a33311026744f0ad74c314b17cfdf2387902","source":{"kind":"arxiv","id":"1807.09462","version":1},"attestation_state":"computed","paper":{"title":"Propensity score estimation using classification and regression trees in the presence of missing covariate data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bas B.L. Penning de Vries, Maarten van Smeden, Rolf H.H. Groenwold","submitted_at":"2018-07-25T07:46:43Z","abstract_excerpt":"Data mining and machine learning techniques such as classification and regression trees (CART) represent a promising alternative to conventional logistic regression for propensity score estimation. Whereas incomplete data preclude the fitting of a logistic regression on all subjects, CART is appealing in part because some implementations allow for incomplete records to be incorporated in the tree fitting and provide propensity score estimates for all subjects. Based on theoretical considerations, we argue that the automatic handling of missing data by CART may however not be appropriate. Using"},"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":"1807.09462","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2018-07-25T07:46:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8db4bad8fa1d34c82f898e166c2c753932f6099715df9bfe293fc08c5e249a42","abstract_canon_sha256":"8aa35c6f120828639947dd178e40d245ca4c0e967407dbf438243e80fea2e4ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:51.278451Z","signature_b64":"LYugK92ZtyQXRetJTHHhW6q0O5qMtGJVOkFqpoZgbLGst07P+aHAzSrBz63/O4YduBwOqOHzA1D8vBJLn2FZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc1fc7b106c20bf49b0c32063212a33311026744f0ad74c314b17cfdf2387902","last_reissued_at":"2026-05-18T00:09:51.277972Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:51.277972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Propensity score estimation using classification and regression trees in the presence of missing covariate data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bas B.L. Penning de Vries, Maarten van Smeden, Rolf H.H. Groenwold","submitted_at":"2018-07-25T07:46:43Z","abstract_excerpt":"Data mining and machine learning techniques such as classification and regression trees (CART) represent a promising alternative to conventional logistic regression for propensity score estimation. Whereas incomplete data preclude the fitting of a logistic regression on all subjects, CART is appealing in part because some implementations allow for incomplete records to be incorporated in the tree fitting and provide propensity score estimates for all subjects. Based on theoretical considerations, we argue that the automatic handling of missing data by CART may however not be appropriate. Using"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09462","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":""},"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":"1807.09462","created_at":"2026-05-18T00:09:51.278040+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.09462v1","created_at":"2026-05-18T00:09:51.278040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09462","created_at":"2026-05-18T00:09:51.278040+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QP4PMIGYIF7","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QP4PMIGYIF7JGYM","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QP4PMIG","created_at":"2026-05-18T12:32:02.567920+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/3QP4PMIGYIF7JGYMGIDDEEVDGM","json":"https://pith.science/pith/3QP4PMIGYIF7JGYMGIDDEEVDGM.json","graph_json":"https://pith.science/api/pith-number/3QP4PMIGYIF7JGYMGIDDEEVDGM/graph.json","events_json":"https://pith.science/api/pith-number/3QP4PMIGYIF7JGYMGIDDEEVDGM/events.json","paper":"https://pith.science/paper/3QP4PMIG"},"agent_actions":{"view_html":"https://pith.science/pith/3QP4PMIGYIF7JGYMGIDDEEVDGM","download_json":"https://pith.science/pith/3QP4PMIGYIF7JGYMGIDDEEVDGM.json","view_paper":"https://pith.science/paper/3QP4PMIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.09462&json=true","fetch_graph":"https://pith.science/api/pith-number/3QP4PMIGYIF7JGYMGIDDEEVDGM/graph.json","fetch_events":"https://pith.science/api/pith-number/3QP4PMIGYIF7JGYMGIDDEEVDGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QP4PMIGYIF7JGYMGIDDEEVDGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QP4PMIGYIF7JGYMGIDDEEVDGM/action/storage_attestation","attest_author":"https://pith.science/pith/3QP4PMIGYIF7JGYMGIDDEEVDGM/action/author_attestation","sign_citation":"https://pith.science/pith/3QP4PMIGYIF7JGYMGIDDEEVDGM/action/citation_signature","submit_replication":"https://pith.science/pith/3QP4PMIGYIF7JGYMGIDDEEVDGM/action/replication_record"}},"created_at":"2026-05-18T00:09:51.278040+00:00","updated_at":"2026-05-18T00:09:51.278040+00:00"}