{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XJOBI4YC622R3EWMC7WOPT4IYS","short_pith_number":"pith:XJOBI4YC","schema_version":"1.0","canonical_sha256":"ba5c147302f6b51d92cc17ece7cf88c48263d359b7e109d9d27445a1bcaf6aa9","source":{"kind":"arxiv","id":"2211.01939","version":3},"attestation_state":"computed","paper":{"title":"Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ME"],"primary_cat":"cs.LG","authors_text":"Brady Neal, Divyat Mahajan, Ioannis Mitliagkas, Vasilis Syrgkanis","submitted_at":"2022-11-03T16:26:06Z","abstract_excerpt":"We study the problem of model selection in causal inference, specifically for conditional average treatment effect (CATE) estimation. Unlike machine learning, there is no perfect analogue of cross-validation for model selection as we do not observe the counterfactual potential outcomes. Towards this, a variety of surrogate metrics have been proposed for CATE model selection that use only observed data. However, we do not have a good understanding regarding their effectiveness due to limited comparisons in prior studies. We conduct an extensive empirical analysis to benchmark the surrogate mode"},"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":"2211.01939","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T16:26:06Z","cross_cats_sorted":["cs.AI","stat.ME"],"title_canon_sha256":"70cde9c5cb763f8cbac10ca2dea8eaaf11e8e42b71cf188690e9d94954170f94","abstract_canon_sha256":"e4acbaa0c67ccc74c92121a5df7e479746b03dd2a2c604a0ce22c744081ed297"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:07.074713Z","signature_b64":"V9HRoJ5p99kPlNonKtKWhO+m+Ybt1gNS/cEmi7/cpbAXdcLky4SHVm77DqRYoGbkRpRlpL/OkoQJSYnQwfkAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba5c147302f6b51d92cc17ece7cf88c48263d359b7e109d9d27445a1bcaf6aa9","last_reissued_at":"2026-07-05T08:13:07.074277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:07.074277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ME"],"primary_cat":"cs.LG","authors_text":"Brady Neal, Divyat Mahajan, Ioannis Mitliagkas, Vasilis Syrgkanis","submitted_at":"2022-11-03T16:26:06Z","abstract_excerpt":"We study the problem of model selection in causal inference, specifically for conditional average treatment effect (CATE) estimation. Unlike machine learning, there is no perfect analogue of cross-validation for model selection as we do not observe the counterfactual potential outcomes. Towards this, a variety of surrogate metrics have been proposed for CATE model selection that use only observed data. However, we do not have a good understanding regarding their effectiveness due to limited comparisons in prior studies. We conduct an extensive empirical analysis to benchmark the surrogate mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01939","kind":"arxiv","version":3},"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/2211.01939/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":"2211.01939","created_at":"2026-07-05T08:13:07.074337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01939v3","created_at":"2026-07-05T08:13:07.074337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01939","created_at":"2026-07-05T08:13:07.074337+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJOBI4YC622R","created_at":"2026-07-05T08:13:07.074337+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJOBI4YC622R3EWM","created_at":"2026-07-05T08:13:07.074337+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJOBI4YC","created_at":"2026-07-05T08:13:07.074337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10430","citing_title":"Real vs. Semi-Simulated: Rethinking Evaluation for Treatment Effect Estimation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10430","citing_title":"Real vs. Semi-Simulated: Rethinking Evaluation for Treatment Effect Estimation","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJOBI4YC622R3EWMC7WOPT4IYS","json":"https://pith.science/pith/XJOBI4YC622R3EWMC7WOPT4IYS.json","graph_json":"https://pith.science/api/pith-number/XJOBI4YC622R3EWMC7WOPT4IYS/graph.json","events_json":"https://pith.science/api/pith-number/XJOBI4YC622R3EWMC7WOPT4IYS/events.json","paper":"https://pith.science/paper/XJOBI4YC"},"agent_actions":{"view_html":"https://pith.science/pith/XJOBI4YC622R3EWMC7WOPT4IYS","download_json":"https://pith.science/pith/XJOBI4YC622R3EWMC7WOPT4IYS.json","view_paper":"https://pith.science/paper/XJOBI4YC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01939&json=true","fetch_graph":"https://pith.science/api/pith-number/XJOBI4YC622R3EWMC7WOPT4IYS/graph.json","fetch_events":"https://pith.science/api/pith-number/XJOBI4YC622R3EWMC7WOPT4IYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJOBI4YC622R3EWMC7WOPT4IYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJOBI4YC622R3EWMC7WOPT4IYS/action/storage_attestation","attest_author":"https://pith.science/pith/XJOBI4YC622R3EWMC7WOPT4IYS/action/author_attestation","sign_citation":"https://pith.science/pith/XJOBI4YC622R3EWMC7WOPT4IYS/action/citation_signature","submit_replication":"https://pith.science/pith/XJOBI4YC622R3EWMC7WOPT4IYS/action/replication_record"}},"created_at":"2026-07-05T08:13:07.074337+00:00","updated_at":"2026-07-05T08:13:07.074337+00:00"}