{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3ELZWFXM4H27DUB5NKXJM3MZFW","short_pith_number":"pith:3ELZWFXM","schema_version":"1.0","canonical_sha256":"d9179b16ece1f5f1d03d6aae966d992db187b9a25503c2b25697c0329b357103","source":{"kind":"arxiv","id":"2211.01221","version":1},"attestation_state":"computed","paper":{"title":"Propensity score models are better when post-calibrated","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.ME","authors_text":"Ehud Karavani, Rom Gutman, Yishai Shimoni","submitted_at":"2022-11-02T16:01:03Z","abstract_excerpt":"Theoretical guarantees for causal inference using propensity scores are partly based on the scores behaving like conditional probabilities. However, scores between zero and one, especially when outputted by flexible statistical estimators, do not necessarily behave like probabilities. We perform a simulation study to assess the error in estimating the average treatment effect before and after applying a simple and well-established post-processing method to calibrate the propensity scores. We find that post-calibration reduces the error in effect estimation for expressive uncalibrated statistic"},"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":"2211.01221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ME","submitted_at":"2022-11-02T16:01:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"71b97fc75ba1c26905ce9c399e1716b9adabe81be4011ca3497f3e0e64271b40","abstract_canon_sha256":"69469093c5c0fd7fc3eaf54d120a056ebccc2a38873ab4ebbba036855d0350ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:23.618711Z","signature_b64":"BkRoXxP+tfXafUgJbiUmUFZttWXzbNiVI5Um87UNB+s4kMo6qE+aukdlT3Sf/MXGLRo6WEPZpuqAvC/HnLZjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9179b16ece1f5f1d03d6aae966d992db187b9a25503c2b25697c0329b357103","last_reissued_at":"2026-07-05T09:33:23.618294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:23.618294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Propensity score models are better when post-calibrated","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.ME","authors_text":"Ehud Karavani, Rom Gutman, Yishai Shimoni","submitted_at":"2022-11-02T16:01:03Z","abstract_excerpt":"Theoretical guarantees for causal inference using propensity scores are partly based on the scores behaving like conditional probabilities. However, scores between zero and one, especially when outputted by flexible statistical estimators, do not necessarily behave like probabilities. We perform a simulation study to assess the error in estimating the average treatment effect before and after applying a simple and well-established post-processing method to calibrate the propensity scores. We find that post-calibration reduces the error in effect estimation for expressive uncalibrated statistic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01221","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/2211.01221/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":"2211.01221","created_at":"2026-07-05T09:33:23.618357+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01221v1","created_at":"2026-07-05T09:33:23.618357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01221","created_at":"2026-07-05T09:33:23.618357+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ELZWFXM4H27","created_at":"2026-07-05T09:33:23.618357+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ELZWFXM4H27DUB5","created_at":"2026-07-05T09:33:23.618357+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ELZWFXM","created_at":"2026-07-05T09:33:23.618357+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21260","citing_title":"Calibeating Prediction-Powered Inference","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ELZWFXM4H27DUB5NKXJM3MZFW","json":"https://pith.science/pith/3ELZWFXM4H27DUB5NKXJM3MZFW.json","graph_json":"https://pith.science/api/pith-number/3ELZWFXM4H27DUB5NKXJM3MZFW/graph.json","events_json":"https://pith.science/api/pith-number/3ELZWFXM4H27DUB5NKXJM3MZFW/events.json","paper":"https://pith.science/paper/3ELZWFXM"},"agent_actions":{"view_html":"https://pith.science/pith/3ELZWFXM4H27DUB5NKXJM3MZFW","download_json":"https://pith.science/pith/3ELZWFXM4H27DUB5NKXJM3MZFW.json","view_paper":"https://pith.science/paper/3ELZWFXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01221&json=true","fetch_graph":"https://pith.science/api/pith-number/3ELZWFXM4H27DUB5NKXJM3MZFW/graph.json","fetch_events":"https://pith.science/api/pith-number/3ELZWFXM4H27DUB5NKXJM3MZFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ELZWFXM4H27DUB5NKXJM3MZFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ELZWFXM4H27DUB5NKXJM3MZFW/action/storage_attestation","attest_author":"https://pith.science/pith/3ELZWFXM4H27DUB5NKXJM3MZFW/action/author_attestation","sign_citation":"https://pith.science/pith/3ELZWFXM4H27DUB5NKXJM3MZFW/action/citation_signature","submit_replication":"https://pith.science/pith/3ELZWFXM4H27DUB5NKXJM3MZFW/action/replication_record"}},"created_at":"2026-07-05T09:33:23.618357+00:00","updated_at":"2026-07-05T09:33:23.618357+00:00"}