{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7UBIDBSF4SKPTC32EXZB53PRL2","short_pith_number":"pith:7UBIDBSF","schema_version":"1.0","canonical_sha256":"fd02818645e494f98b7a25f21eedf15e900e0bd38872df4b95ea4593e934ca32","source":{"kind":"arxiv","id":"2606.30918","version":1},"attestation_state":"computed","paper":{"title":"Cross-Fitted Survey-Weighted TMLE with Design-Based Variance for Causal Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"stat.ME","authors_text":"M. Ehsan Karim","submitted_at":"2026-06-29T21:10:02Z","abstract_excerpt":"Cross-fitting is not a refinement of survey-weighted causal machine learning but, once the nuisances are flexible, what restores valid inference. We study the population average treatment effect under a stratified multistage design, estimated by a survey-aware targeted maximum likelihood estimator (TMLE) whose variance is obtained by Taylor-series linearization of the influence function, treating the primary sampling unit as the replication unit. Our central result, established in theory and simulation, is that this validity turns on cross-fitting at the cluster level. Once flexible learners c"},"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":"2606.30918","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-06-29T21:10:02Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"17deecef7c2cb986bdab366338272fce366a7005d126c3f4d77981b7718fcf80","abstract_canon_sha256":"cc810aaa069e663636cbd9fe624343ba8f2a0f47539ab8156874ceb5a4c130af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:21.647968Z","signature_b64":"soGdAlM2ccMS/O/cTNo/6vXCB+qtxPCfekk03g1OMK0Hrd0ACNLf8b1/jKLGLWAA4rNHgcFQ0tHJXcCoWWhvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd02818645e494f98b7a25f21eedf15e900e0bd38872df4b95ea4593e934ca32","last_reissued_at":"2026-07-01T00:17:21.647554Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:21.647554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Fitted Survey-Weighted TMLE with Design-Based Variance for Causal Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"stat.ME","authors_text":"M. Ehsan Karim","submitted_at":"2026-06-29T21:10:02Z","abstract_excerpt":"Cross-fitting is not a refinement of survey-weighted causal machine learning but, once the nuisances are flexible, what restores valid inference. We study the population average treatment effect under a stratified multistage design, estimated by a survey-aware targeted maximum likelihood estimator (TMLE) whose variance is obtained by Taylor-series linearization of the influence function, treating the primary sampling unit as the replication unit. Our central result, established in theory and simulation, is that this validity turns on cross-fitting at the cluster level. Once flexible learners c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30918","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/2606.30918/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":"2606.30918","created_at":"2026-07-01T00:17:21.647623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30918v1","created_at":"2026-07-01T00:17:21.647623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30918","created_at":"2026-07-01T00:17:21.647623+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UBIDBSF4SKP","created_at":"2026-07-01T00:17:21.647623+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UBIDBSF4SKPTC32","created_at":"2026-07-01T00:17:21.647623+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UBIDBSF","created_at":"2026-07-01T00:17:21.647623+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/7UBIDBSF4SKPTC32EXZB53PRL2","json":"https://pith.science/pith/7UBIDBSF4SKPTC32EXZB53PRL2.json","graph_json":"https://pith.science/api/pith-number/7UBIDBSF4SKPTC32EXZB53PRL2/graph.json","events_json":"https://pith.science/api/pith-number/7UBIDBSF4SKPTC32EXZB53PRL2/events.json","paper":"https://pith.science/paper/7UBIDBSF"},"agent_actions":{"view_html":"https://pith.science/pith/7UBIDBSF4SKPTC32EXZB53PRL2","download_json":"https://pith.science/pith/7UBIDBSF4SKPTC32EXZB53PRL2.json","view_paper":"https://pith.science/paper/7UBIDBSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30918&json=true","fetch_graph":"https://pith.science/api/pith-number/7UBIDBSF4SKPTC32EXZB53PRL2/graph.json","fetch_events":"https://pith.science/api/pith-number/7UBIDBSF4SKPTC32EXZB53PRL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UBIDBSF4SKPTC32EXZB53PRL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UBIDBSF4SKPTC32EXZB53PRL2/action/storage_attestation","attest_author":"https://pith.science/pith/7UBIDBSF4SKPTC32EXZB53PRL2/action/author_attestation","sign_citation":"https://pith.science/pith/7UBIDBSF4SKPTC32EXZB53PRL2/action/citation_signature","submit_replication":"https://pith.science/pith/7UBIDBSF4SKPTC32EXZB53PRL2/action/replication_record"}},"created_at":"2026-07-01T00:17:21.647623+00:00","updated_at":"2026-07-01T00:17:21.647623+00:00"}