{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KF5H3S3YPXA2ZVHHON4LDFSHR5","short_pith_number":"pith:KF5H3S3Y","schema_version":"1.0","canonical_sha256":"517a7dcb787dc1acd4e77378b196478f53755d7100beea92842f2e640cb4f85c","source":{"kind":"arxiv","id":"2605.20125","version":1},"attestation_state":"computed","paper":{"title":"Federated Learning with Incomplete Data: When to Use Complete Cases and When to Weight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ME","authors_text":"Chad Hochberg, Elizabeth A. Stuart, Jason Akulian, Jesus E. Vazquez, Jiayi Tong, Theodore J. Iwashyna, Yicheng Shen","submitted_at":"2026-05-19T17:12:37Z","abstract_excerpt":"Privacy constraints have driven the rise of federated learning (FL), which enables multi-site analyses without sharing individual participant data. We develop a framework for FL with missing data, identifying conditions under which the complete case (CC) estimator is preferred over the inverse probability weighting (IPW) estimator. For settings where the CC estimator fails, we introduce a calibrated weight estimation approach that combines candidate weighting models across sites and remains consistent if at least one is correctly specified. Consistency conditions are stated at the site level, "},"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":"2605.20125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-05-19T17:12:37Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"716b0e2f49a3d3ff97bf74878ec748710252528f11ebef57b89d20200dbe2016","abstract_canon_sha256":"d911d636a32e03a0cd2bacc9686fa7ac104049800d4a09bfdd4d0b1817d31826"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:06:03.206614Z","signature_b64":"LyssNdGrTlrFR+w8uqqFxnHWJk+/3SIErvKqMXn3/hZwla98LznS2fHMhAewp8c2mLjDEpCWsssI/ZWC+AqoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"517a7dcb787dc1acd4e77378b196478f53755d7100beea92842f2e640cb4f85c","last_reissued_at":"2026-05-20T02:06:03.205859Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:06:03.205859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning with Incomplete Data: When to Use Complete Cases and When to Weight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ME","authors_text":"Chad Hochberg, Elizabeth A. Stuart, Jason Akulian, Jesus E. Vazquez, Jiayi Tong, Theodore J. Iwashyna, Yicheng Shen","submitted_at":"2026-05-19T17:12:37Z","abstract_excerpt":"Privacy constraints have driven the rise of federated learning (FL), which enables multi-site analyses without sharing individual participant data. We develop a framework for FL with missing data, identifying conditions under which the complete case (CC) estimator is preferred over the inverse probability weighting (IPW) estimator. For settings where the CC estimator fails, we introduce a calibrated weight estimation approach that combines candidate weighting models across sites and remains consistent if at least one is correctly specified. Consistency conditions are stated at the site level, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20125","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/2605.20125/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":"2605.20125","created_at":"2026-05-20T02:06:03.205993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20125v1","created_at":"2026-05-20T02:06:03.205993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20125","created_at":"2026-05-20T02:06:03.205993+00:00"},{"alias_kind":"pith_short_12","alias_value":"KF5H3S3YPXA2","created_at":"2026-05-20T02:06:03.205993+00:00"},{"alias_kind":"pith_short_16","alias_value":"KF5H3S3YPXA2ZVHH","created_at":"2026-05-20T02:06:03.205993+00:00"},{"alias_kind":"pith_short_8","alias_value":"KF5H3S3Y","created_at":"2026-05-20T02:06:03.205993+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/KF5H3S3YPXA2ZVHHON4LDFSHR5","json":"https://pith.science/pith/KF5H3S3YPXA2ZVHHON4LDFSHR5.json","graph_json":"https://pith.science/api/pith-number/KF5H3S3YPXA2ZVHHON4LDFSHR5/graph.json","events_json":"https://pith.science/api/pith-number/KF5H3S3YPXA2ZVHHON4LDFSHR5/events.json","paper":"https://pith.science/paper/KF5H3S3Y"},"agent_actions":{"view_html":"https://pith.science/pith/KF5H3S3YPXA2ZVHHON4LDFSHR5","download_json":"https://pith.science/pith/KF5H3S3YPXA2ZVHHON4LDFSHR5.json","view_paper":"https://pith.science/paper/KF5H3S3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20125&json=true","fetch_graph":"https://pith.science/api/pith-number/KF5H3S3YPXA2ZVHHON4LDFSHR5/graph.json","fetch_events":"https://pith.science/api/pith-number/KF5H3S3YPXA2ZVHHON4LDFSHR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KF5H3S3YPXA2ZVHHON4LDFSHR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KF5H3S3YPXA2ZVHHON4LDFSHR5/action/storage_attestation","attest_author":"https://pith.science/pith/KF5H3S3YPXA2ZVHHON4LDFSHR5/action/author_attestation","sign_citation":"https://pith.science/pith/KF5H3S3YPXA2ZVHHON4LDFSHR5/action/citation_signature","submit_replication":"https://pith.science/pith/KF5H3S3YPXA2ZVHHON4LDFSHR5/action/replication_record"}},"created_at":"2026-05-20T02:06:03.205993+00:00","updated_at":"2026-05-20T02:06:03.205993+00:00"}