{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DV3CVG43TORLC736O4LPXM45B5","short_pith_number":"pith:DV3CVG43","schema_version":"1.0","canonical_sha256":"1d762a9b9b9ba2b17f7e7716fbb39d0f7fda19d44e61bb99a1407c582ae98fd9","source":{"kind":"arxiv","id":"2304.01429","version":1},"attestation_state":"computed","paper":{"title":"Learning from data with structured missingness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aditi Shenvi, Alisha Davies, Anahid Basiri, Ben D. MacArthur, Brieuc Lehmann, Chris Harbron, Chris Holmes, David Leslie, Eleni-Rosalina Andrinopoulou, Ginestra Bianconi, Jack Noonan, Maxine Mackintosh, Niels Hagenbuch, Robin Mitra, Ruben Sanchez-Garcia, Ryan Copping, Sarah F. McGough, Stefanie Biedermann, Tapabrata Chakraborti, Xuan Vinh Doan","submitted_at":"2023-04-04T00:24:40Z","abstract_excerpt":"Missing data are an unavoidable complication in many machine learning tasks. When data are `missing at random' there exist a range of tools and techniques to deal with the issue. However, as machine learning studies become more ambitious, and seek to learn from ever-larger volumes of heterogeneous data, an increasingly encountered problem arises in which missing values exhibit an association or structure, either explicitly or implicitly. Such `structured missingness' raises a range of challenges that have not yet been systematically addressed, and presents a fundamental hindrance to machine le"},"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":"2304.01429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-04-04T00:24:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1977bbb8dad6cbc962857b9451a2f43589ca7440838f36a4d71771d41752bfd7","abstract_canon_sha256":"6e19bb21cd364712072d26bc145e5533b5ed4531baad95569b8d63fab0f586a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:40.340526Z","signature_b64":"2lzBFbrddFzF3hFfJY0+e+p0ldQ6HKdj5JbXzMPvilK5rr6FAiEU1bvPVYZQBceG1clzjUUydOqJSChMAAl3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d762a9b9b9ba2b17f7e7716fbb39d0f7fda19d44e61bb99a1407c582ae98fd9","last_reissued_at":"2026-07-05T05:57:40.339944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:40.339944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from data with structured missingness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aditi Shenvi, Alisha Davies, Anahid Basiri, Ben D. MacArthur, Brieuc Lehmann, Chris Harbron, Chris Holmes, David Leslie, Eleni-Rosalina Andrinopoulou, Ginestra Bianconi, Jack Noonan, Maxine Mackintosh, Niels Hagenbuch, Robin Mitra, Ruben Sanchez-Garcia, Ryan Copping, Sarah F. McGough, Stefanie Biedermann, Tapabrata Chakraborti, Xuan Vinh Doan","submitted_at":"2023-04-04T00:24:40Z","abstract_excerpt":"Missing data are an unavoidable complication in many machine learning tasks. When data are `missing at random' there exist a range of tools and techniques to deal with the issue. However, as machine learning studies become more ambitious, and seek to learn from ever-larger volumes of heterogeneous data, an increasingly encountered problem arises in which missing values exhibit an association or structure, either explicitly or implicitly. Such `structured missingness' raises a range of challenges that have not yet been systematically addressed, and presents a fundamental hindrance to machine le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01429","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/2304.01429/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":"2304.01429","created_at":"2026-07-05T05:57:40.340009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01429v1","created_at":"2026-07-05T05:57:40.340009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01429","created_at":"2026-07-05T05:57:40.340009+00:00"},{"alias_kind":"pith_short_12","alias_value":"DV3CVG43TORL","created_at":"2026-07-05T05:57:40.340009+00:00"},{"alias_kind":"pith_short_16","alias_value":"DV3CVG43TORLC736","created_at":"2026-07-05T05:57:40.340009+00:00"},{"alias_kind":"pith_short_8","alias_value":"DV3CVG43","created_at":"2026-07-05T05:57:40.340009+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/DV3CVG43TORLC736O4LPXM45B5","json":"https://pith.science/pith/DV3CVG43TORLC736O4LPXM45B5.json","graph_json":"https://pith.science/api/pith-number/DV3CVG43TORLC736O4LPXM45B5/graph.json","events_json":"https://pith.science/api/pith-number/DV3CVG43TORLC736O4LPXM45B5/events.json","paper":"https://pith.science/paper/DV3CVG43"},"agent_actions":{"view_html":"https://pith.science/pith/DV3CVG43TORLC736O4LPXM45B5","download_json":"https://pith.science/pith/DV3CVG43TORLC736O4LPXM45B5.json","view_paper":"https://pith.science/paper/DV3CVG43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01429&json=true","fetch_graph":"https://pith.science/api/pith-number/DV3CVG43TORLC736O4LPXM45B5/graph.json","fetch_events":"https://pith.science/api/pith-number/DV3CVG43TORLC736O4LPXM45B5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DV3CVG43TORLC736O4LPXM45B5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DV3CVG43TORLC736O4LPXM45B5/action/storage_attestation","attest_author":"https://pith.science/pith/DV3CVG43TORLC736O4LPXM45B5/action/author_attestation","sign_citation":"https://pith.science/pith/DV3CVG43TORLC736O4LPXM45B5/action/citation_signature","submit_replication":"https://pith.science/pith/DV3CVG43TORLC736O4LPXM45B5/action/replication_record"}},"created_at":"2026-07-05T05:57:40.340009+00:00","updated_at":"2026-07-05T05:57:40.340009+00:00"}