{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WWBUUCSBFUAEDBOKTR4YLHW2DT","short_pith_number":"pith:WWBUUCSB","schema_version":"1.0","canonical_sha256":"b5834a0a412d004185ca9c79859eda1ce56cdc8992193f13741f372680cbda5a","source":{"kind":"arxiv","id":"2307.00467","version":1},"attestation_state":"computed","paper":{"title":"MissDiff: Training Diffusion Models on Tabular Data with Missing Values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chongxuan Li, Guang Cheng, Liyan Xie, Yidong Ouyang","submitted_at":"2023-07-02T03:49:47Z","abstract_excerpt":"The diffusion model has shown remarkable performance in modeling data distributions and synthesizing data. However, the vanilla diffusion model requires complete or fully observed data for training. Incomplete data is a common issue in various real-world applications, including healthcare and finance, particularly when dealing with tabular datasets. This work presents a unified and principled diffusion-based framework for learning from data with missing values under various missing mechanisms. We first observe that the widely adopted \"impute-then-generate\" pipeline may lead to a biased learnin"},"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":"2307.00467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-02T03:49:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a29c7a72839bb5276a7523e7e865bafd3daa2894ee434df11da9f88f9d0469f1","abstract_canon_sha256":"c07fb7898e7636b729557e58b57a258b48c2d02c1e01c8cb7d184d0d61af007a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:56.606900Z","signature_b64":"zQWaQn6gn/vpea3ZwC8qtiU1JivypyiMuTXJuywh3hHGqrwILc4s/spYmwufeSr6MRoKPL3nc5Ldpod2crxSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5834a0a412d004185ca9c79859eda1ce56cdc8992193f13741f372680cbda5a","last_reissued_at":"2026-07-05T06:26:56.606413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:56.606413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MissDiff: Training Diffusion Models on Tabular Data with Missing Values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chongxuan Li, Guang Cheng, Liyan Xie, Yidong Ouyang","submitted_at":"2023-07-02T03:49:47Z","abstract_excerpt":"The diffusion model has shown remarkable performance in modeling data distributions and synthesizing data. However, the vanilla diffusion model requires complete or fully observed data for training. Incomplete data is a common issue in various real-world applications, including healthcare and finance, particularly when dealing with tabular datasets. This work presents a unified and principled diffusion-based framework for learning from data with missing values under various missing mechanisms. We first observe that the widely adopted \"impute-then-generate\" pipeline may lead to a biased learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00467","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/2307.00467/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":"2307.00467","created_at":"2026-07-05T06:26:56.606471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00467v1","created_at":"2026-07-05T06:26:56.606471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00467","created_at":"2026-07-05T06:26:56.606471+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWBUUCSBFUAE","created_at":"2026-07-05T06:26:56.606471+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWBUUCSBFUAEDBOK","created_at":"2026-07-05T06:26:56.606471+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWBUUCSB","created_at":"2026-07-05T06:26:56.606471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05073","citing_title":"Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03347","citing_title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28427","citing_title":"Latent Diffusion for Missing Data","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03530","citing_title":"How Far Are We from Generating Missing Modalities with Foundation Models?","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20098","citing_title":"Incomplete Data, Complete Dynamics: A Diffusion Approach","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24959","citing_title":"CoreFlow: Low-Rank Matrix Generative Models","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WWBUUCSBFUAEDBOKTR4YLHW2DT","json":"https://pith.science/pith/WWBUUCSBFUAEDBOKTR4YLHW2DT.json","graph_json":"https://pith.science/api/pith-number/WWBUUCSBFUAEDBOKTR4YLHW2DT/graph.json","events_json":"https://pith.science/api/pith-number/WWBUUCSBFUAEDBOKTR4YLHW2DT/events.json","paper":"https://pith.science/paper/WWBUUCSB"},"agent_actions":{"view_html":"https://pith.science/pith/WWBUUCSBFUAEDBOKTR4YLHW2DT","download_json":"https://pith.science/pith/WWBUUCSBFUAEDBOKTR4YLHW2DT.json","view_paper":"https://pith.science/paper/WWBUUCSB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00467&json=true","fetch_graph":"https://pith.science/api/pith-number/WWBUUCSBFUAEDBOKTR4YLHW2DT/graph.json","fetch_events":"https://pith.science/api/pith-number/WWBUUCSBFUAEDBOKTR4YLHW2DT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWBUUCSBFUAEDBOKTR4YLHW2DT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWBUUCSBFUAEDBOKTR4YLHW2DT/action/storage_attestation","attest_author":"https://pith.science/pith/WWBUUCSBFUAEDBOKTR4YLHW2DT/action/author_attestation","sign_citation":"https://pith.science/pith/WWBUUCSBFUAEDBOKTR4YLHW2DT/action/citation_signature","submit_replication":"https://pith.science/pith/WWBUUCSBFUAEDBOKTR4YLHW2DT/action/replication_record"}},"created_at":"2026-07-05T06:26:56.606471+00:00","updated_at":"2026-07-05T06:26:56.606471+00:00"}