{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KGYZNOSBG5RQEEDWU3CXYOPI2U","short_pith_number":"pith:KGYZNOSB","schema_version":"1.0","canonical_sha256":"51b196ba413763021076a6c57c39e8d5368193b02ac70dbab7a5bae0e0fad838","source":{"kind":"arxiv","id":"2502.05319","version":1},"attestation_state":"computed","paper":{"title":"Semiparametric Inference for Partially Identifiable Data Fusion Estimands via Double Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Lucas Janson, Yicong Jiang","submitted_at":"2025-02-07T20:37:57Z","abstract_excerpt":"Many statistical estimands of interest (e.g., in regression or causality) are functions of the joint distribution of multiple random variables. But in some applications, data is not available that measures all random variables on each subject, and instead the only possible approach is one of data fusion, where multiple independent data sets, each measuring a subset of the random variables of interest, are combined for inference. In general, since all random variables are never observed jointly, their joint distribution, and hence also the estimand which is a function of it, is only partially i"},"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":"2502.05319","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-02-07T20:37:57Z","cross_cats_sorted":[],"title_canon_sha256":"a3b7a1931e28a73241783ab167f5e9e910b96b62ac5d3bb6e0453f734eabe531","abstract_canon_sha256":"17a575170b40c2ddcb1225916042af7f7a344c07a5a430a1b09239abe1defd86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:35.863547Z","signature_b64":"AYTxEGNsGYHQrVBnrEj+q8oLWvProNXEyn48OfZb+siIPGGlqWCarSiAnwcCXcpLixfqmTjL5vI6+CEcOyjeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51b196ba413763021076a6c57c39e8d5368193b02ac70dbab7a5bae0e0fad838","last_reissued_at":"2026-07-05T10:11:35.863155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:35.863155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semiparametric Inference for Partially Identifiable Data Fusion Estimands via Double Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Lucas Janson, Yicong Jiang","submitted_at":"2025-02-07T20:37:57Z","abstract_excerpt":"Many statistical estimands of interest (e.g., in regression or causality) are functions of the joint distribution of multiple random variables. But in some applications, data is not available that measures all random variables on each subject, and instead the only possible approach is one of data fusion, where multiple independent data sets, each measuring a subset of the random variables of interest, are combined for inference. In general, since all random variables are never observed jointly, their joint distribution, and hence also the estimand which is a function of it, is only partially i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05319","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/2502.05319/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":"2502.05319","created_at":"2026-07-05T10:11:35.863207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05319v1","created_at":"2026-07-05T10:11:35.863207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05319","created_at":"2026-07-05T10:11:35.863207+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGYZNOSBG5RQ","created_at":"2026-07-05T10:11:35.863207+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGYZNOSBG5RQEEDW","created_at":"2026-07-05T10:11:35.863207+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGYZNOSB","created_at":"2026-07-05T10:11:35.863207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12215","citing_title":"Partial identification via conditional linear programs: estimation and policy learning","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KGYZNOSBG5RQEEDWU3CXYOPI2U","json":"https://pith.science/pith/KGYZNOSBG5RQEEDWU3CXYOPI2U.json","graph_json":"https://pith.science/api/pith-number/KGYZNOSBG5RQEEDWU3CXYOPI2U/graph.json","events_json":"https://pith.science/api/pith-number/KGYZNOSBG5RQEEDWU3CXYOPI2U/events.json","paper":"https://pith.science/paper/KGYZNOSB"},"agent_actions":{"view_html":"https://pith.science/pith/KGYZNOSBG5RQEEDWU3CXYOPI2U","download_json":"https://pith.science/pith/KGYZNOSBG5RQEEDWU3CXYOPI2U.json","view_paper":"https://pith.science/paper/KGYZNOSB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05319&json=true","fetch_graph":"https://pith.science/api/pith-number/KGYZNOSBG5RQEEDWU3CXYOPI2U/graph.json","fetch_events":"https://pith.science/api/pith-number/KGYZNOSBG5RQEEDWU3CXYOPI2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGYZNOSBG5RQEEDWU3CXYOPI2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGYZNOSBG5RQEEDWU3CXYOPI2U/action/storage_attestation","attest_author":"https://pith.science/pith/KGYZNOSBG5RQEEDWU3CXYOPI2U/action/author_attestation","sign_citation":"https://pith.science/pith/KGYZNOSBG5RQEEDWU3CXYOPI2U/action/citation_signature","submit_replication":"https://pith.science/pith/KGYZNOSBG5RQEEDWU3CXYOPI2U/action/replication_record"}},"created_at":"2026-07-05T10:11:35.863207+00:00","updated_at":"2026-07-05T10:11:35.863207+00:00"}