{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ETKX74RUWGIUSO5TZHAXCNYIOE","short_pith_number":"pith:ETKX74RU","schema_version":"1.0","canonical_sha256":"24d57ff234b191493bb3c9c1713708713ab23c2ac3fb96b7d2f4429415e80b4b","source":{"kind":"arxiv","id":"2402.15255","version":2},"attestation_state":"computed","paper":{"title":"Optimal Transport for Structure Learning Under Missing Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dinh Phung, Edwin V. Bonilla, He Zhao, Trung Le, Vy Vo","submitted_at":"2024-02-23T10:49:04Z","abstract_excerpt":"Causal discovery in the presence of missing data introduces a chicken-and-egg dilemma. While the goal is to recover the true causal structure, robust imputation requires considering the dependencies or, preferably, causal relations among variables. Merely filling in missing values with existing imputation methods and subsequently applying structure learning on the complete data is empirically shown to be sub-optimal. To address this problem, we propose a score-based algorithm for learning causal structures from missing data based on optimal transport. This optimal transport viewpoint diverges "},"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":"2402.15255","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T10:49:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ace4f4bc2fddc2315bcdef2b607dc7d2c3d3b4861eb8b67cfb1ac33ee9daaec5","abstract_canon_sha256":"e535e5e31e6a36cd8c487ee9abbd4543ac6788aa16b3599b9e713087af13faa2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:52.766838Z","signature_b64":"xPhPSyTyghtDm1HxoS7JJJrByalegNy9CDzGIBc6lTAE8P3acQ7cGsmwy7kgOUWFZHSFMNqfPQplUqsTC4wkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24d57ff234b191493bb3c9c1713708713ab23c2ac3fb96b7d2f4429415e80b4b","last_reissued_at":"2026-07-05T08:25:52.766324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:52.766324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Transport for Structure Learning Under Missing Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dinh Phung, Edwin V. Bonilla, He Zhao, Trung Le, Vy Vo","submitted_at":"2024-02-23T10:49:04Z","abstract_excerpt":"Causal discovery in the presence of missing data introduces a chicken-and-egg dilemma. While the goal is to recover the true causal structure, robust imputation requires considering the dependencies or, preferably, causal relations among variables. Merely filling in missing values with existing imputation methods and subsequently applying structure learning on the complete data is empirically shown to be sub-optimal. To address this problem, we propose a score-based algorithm for learning causal structures from missing data based on optimal transport. This optimal transport viewpoint diverges "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15255","kind":"arxiv","version":2},"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/2402.15255/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":"2402.15255","created_at":"2026-07-05T08:25:52.766386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15255v2","created_at":"2026-07-05T08:25:52.766386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15255","created_at":"2026-07-05T08:25:52.766386+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETKX74RUWGIU","created_at":"2026-07-05T08:25:52.766386+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETKX74RUWGIUSO5T","created_at":"2026-07-05T08:25:52.766386+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETKX74RU","created_at":"2026-07-05T08:25:52.766386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13786","citing_title":"Handling Missing Data in Downstream Tasks With Distribution-Preserving Guarantees","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETKX74RUWGIUSO5TZHAXCNYIOE","json":"https://pith.science/pith/ETKX74RUWGIUSO5TZHAXCNYIOE.json","graph_json":"https://pith.science/api/pith-number/ETKX74RUWGIUSO5TZHAXCNYIOE/graph.json","events_json":"https://pith.science/api/pith-number/ETKX74RUWGIUSO5TZHAXCNYIOE/events.json","paper":"https://pith.science/paper/ETKX74RU"},"agent_actions":{"view_html":"https://pith.science/pith/ETKX74RUWGIUSO5TZHAXCNYIOE","download_json":"https://pith.science/pith/ETKX74RUWGIUSO5TZHAXCNYIOE.json","view_paper":"https://pith.science/paper/ETKX74RU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15255&json=true","fetch_graph":"https://pith.science/api/pith-number/ETKX74RUWGIUSO5TZHAXCNYIOE/graph.json","fetch_events":"https://pith.science/api/pith-number/ETKX74RUWGIUSO5TZHAXCNYIOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETKX74RUWGIUSO5TZHAXCNYIOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETKX74RUWGIUSO5TZHAXCNYIOE/action/storage_attestation","attest_author":"https://pith.science/pith/ETKX74RUWGIUSO5TZHAXCNYIOE/action/author_attestation","sign_citation":"https://pith.science/pith/ETKX74RUWGIUSO5TZHAXCNYIOE/action/citation_signature","submit_replication":"https://pith.science/pith/ETKX74RUWGIUSO5TZHAXCNYIOE/action/replication_record"}},"created_at":"2026-07-05T08:25:52.766386+00:00","updated_at":"2026-07-05T08:25:52.766386+00:00"}