{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LWWTSTD4O7VYLFGX2V43EZILTS","short_pith_number":"pith:LWWTSTD4","schema_version":"1.0","canonical_sha256":"5dad394c7c77eb8594d7d579b2650b9c81f69255ef56bdd34f74a3f5227149f9","source":{"kind":"arxiv","id":"2201.12692","version":1},"attestation_state":"computed","paper":{"title":"Meta-Learners for Estimation of Causal Effects: Finite Sample Cross-Fit Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"econ.EM","authors_text":"Gabriel Okasa","submitted_at":"2022-01-30T00:52:33Z","abstract_excerpt":"Estimation of causal effects using machine learning methods has become an active research field in econometrics. In this paper, we study the finite sample performance of meta-learners for estimation of heterogeneous treatment effects under the usage of sample-splitting and cross-fitting to reduce the overfitting bias. In both synthetic and semi-synthetic simulations we find that the performance of the meta-learners in finite samples greatly depends on the estimation procedure. The results imply that sample-splitting and cross-fitting are beneficial in large samples for bias reduction and effic"},"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":"2201.12692","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2022-01-30T00:52:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c110b8eee3bff0febedc41defa82aca0a734d995738843e4e0eebb16386aaf00","abstract_canon_sha256":"79fc607f1847c5d1dfea98f1fd27a1c49d5f7a898d64e2cbb1de101ce42c6ee1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:39.154941Z","signature_b64":"I55tZdtb5CC9SkGQAcB8HEdt6W6O56IzP5dntiU7+yt/RTCW5lqbkUHPBSxeFhW41Mo3UGsfJPZjVhVTx7kTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dad394c7c77eb8594d7d579b2650b9c81f69255ef56bdd34f74a3f5227149f9","last_reissued_at":"2026-07-05T03:52:39.154547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:39.154547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learners for Estimation of Causal Effects: Finite Sample Cross-Fit Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"econ.EM","authors_text":"Gabriel Okasa","submitted_at":"2022-01-30T00:52:33Z","abstract_excerpt":"Estimation of causal effects using machine learning methods has become an active research field in econometrics. In this paper, we study the finite sample performance of meta-learners for estimation of heterogeneous treatment effects under the usage of sample-splitting and cross-fitting to reduce the overfitting bias. In both synthetic and semi-synthetic simulations we find that the performance of the meta-learners in finite samples greatly depends on the estimation procedure. The results imply that sample-splitting and cross-fitting are beneficial in large samples for bias reduction and effic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12692","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/2201.12692/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":"2201.12692","created_at":"2026-07-05T03:52:39.154602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.12692v1","created_at":"2026-07-05T03:52:39.154602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12692","created_at":"2026-07-05T03:52:39.154602+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWWTSTD4O7VY","created_at":"2026-07-05T03:52:39.154602+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWWTSTD4O7VYLFGX","created_at":"2026-07-05T03:52:39.154602+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWWTSTD4","created_at":"2026-07-05T03:52:39.154602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15856","citing_title":"crossfit: A Graph-Based Cross-Fitting Engine in R","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWWTSTD4O7VYLFGX2V43EZILTS","json":"https://pith.science/pith/LWWTSTD4O7VYLFGX2V43EZILTS.json","graph_json":"https://pith.science/api/pith-number/LWWTSTD4O7VYLFGX2V43EZILTS/graph.json","events_json":"https://pith.science/api/pith-number/LWWTSTD4O7VYLFGX2V43EZILTS/events.json","paper":"https://pith.science/paper/LWWTSTD4"},"agent_actions":{"view_html":"https://pith.science/pith/LWWTSTD4O7VYLFGX2V43EZILTS","download_json":"https://pith.science/pith/LWWTSTD4O7VYLFGX2V43EZILTS.json","view_paper":"https://pith.science/paper/LWWTSTD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.12692&json=true","fetch_graph":"https://pith.science/api/pith-number/LWWTSTD4O7VYLFGX2V43EZILTS/graph.json","fetch_events":"https://pith.science/api/pith-number/LWWTSTD4O7VYLFGX2V43EZILTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWWTSTD4O7VYLFGX2V43EZILTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWWTSTD4O7VYLFGX2V43EZILTS/action/storage_attestation","attest_author":"https://pith.science/pith/LWWTSTD4O7VYLFGX2V43EZILTS/action/author_attestation","sign_citation":"https://pith.science/pith/LWWTSTD4O7VYLFGX2V43EZILTS/action/citation_signature","submit_replication":"https://pith.science/pith/LWWTSTD4O7VYLFGX2V43EZILTS/action/replication_record"}},"created_at":"2026-07-05T03:52:39.154602+00:00","updated_at":"2026-07-05T03:52:39.154602+00:00"}