{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HQZMPJGHHEXU2BLSEZEEU2UOK3","short_pith_number":"pith:HQZMPJGH","schema_version":"1.0","canonical_sha256":"3c32c7a4c7392f4d057226484a6a8e56fc2ccfbf90f5a6d713a212e76d113635","source":{"kind":"arxiv","id":"2210.17128","version":2},"attestation_state":"computed","paper":{"title":"Diffusion models for missing value imputation in tabular data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Nontawat Charoenphakdee, Shuhan Zheng","submitted_at":"2022-10-31T08:13:26Z","abstract_excerpt":"Missing value imputation in machine learning is the task of estimating the missing values in the dataset accurately using available information. In this task, several deep generative modeling methods have been proposed and demonstrated their usefulness, e.g., generative adversarial imputation networks. Recently, diffusion models have gained popularity because of their effectiveness in the generative modeling task in images, texts, audio, etc. To our knowledge, less attention has been paid to the investigation of the effectiveness of diffusion models for missing value imputation in tabular data"},"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":"2210.17128","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-31T08:13:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"99a8b2a4e3748dc0719430f2fd96f0d062e955e2e0cbdc7296092e012143614c","abstract_canon_sha256":"772b6b61c015d1c99cf4fa2847307c6974f574bfc9e07d9454094c68c761aa7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:10.174224Z","signature_b64":"9vWTF4CWLW+aomWqguV96TT1rrspsbK3ESEpvIp0w6fZMu7Q/gTDL0OEEo2kpb2TFxUXFKnMLff42UG8EhUrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c32c7a4c7392f4d057226484a6a8e56fc2ccfbf90f5a6d713a212e76d113635","last_reissued_at":"2026-07-05T05:50:10.173795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:10.173795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion models for missing value imputation in tabular data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Nontawat Charoenphakdee, Shuhan Zheng","submitted_at":"2022-10-31T08:13:26Z","abstract_excerpt":"Missing value imputation in machine learning is the task of estimating the missing values in the dataset accurately using available information. In this task, several deep generative modeling methods have been proposed and demonstrated their usefulness, e.g., generative adversarial imputation networks. Recently, diffusion models have gained popularity because of their effectiveness in the generative modeling task in images, texts, audio, etc. To our knowledge, less attention has been paid to the investigation of the effectiveness of diffusion models for missing value imputation in tabular data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17128","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/2210.17128/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":"2210.17128","created_at":"2026-07-05T05:50:10.173846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.17128v2","created_at":"2026-07-05T05:50:10.173846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17128","created_at":"2026-07-05T05:50:10.173846+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQZMPJGHHEXU","created_at":"2026-07-05T05:50:10.173846+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQZMPJGHHEXU2BLS","created_at":"2026-07-05T05:50:10.173846+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQZMPJGH","created_at":"2026-07-05T05:50:10.173846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25439","citing_title":"Missing Pattern Recognized Diffusion Imputation Model for Missing Not At Random","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28427","citing_title":"Latent Diffusion for Missing Data","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2503.02161","citing_title":"LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19185","citing_title":"MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24959","citing_title":"CoreFlow: Low-Rank Matrix Generative Models","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01676","citing_title":"Missingness-aware Data Imputation via AI-powered Bayesian Generative Modeling","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18966","citing_title":"Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training","ref_index":93,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HQZMPJGHHEXU2BLSEZEEU2UOK3","json":"https://pith.science/pith/HQZMPJGHHEXU2BLSEZEEU2UOK3.json","graph_json":"https://pith.science/api/pith-number/HQZMPJGHHEXU2BLSEZEEU2UOK3/graph.json","events_json":"https://pith.science/api/pith-number/HQZMPJGHHEXU2BLSEZEEU2UOK3/events.json","paper":"https://pith.science/paper/HQZMPJGH"},"agent_actions":{"view_html":"https://pith.science/pith/HQZMPJGHHEXU2BLSEZEEU2UOK3","download_json":"https://pith.science/pith/HQZMPJGHHEXU2BLSEZEEU2UOK3.json","view_paper":"https://pith.science/paper/HQZMPJGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.17128&json=true","fetch_graph":"https://pith.science/api/pith-number/HQZMPJGHHEXU2BLSEZEEU2UOK3/graph.json","fetch_events":"https://pith.science/api/pith-number/HQZMPJGHHEXU2BLSEZEEU2UOK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQZMPJGHHEXU2BLSEZEEU2UOK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQZMPJGHHEXU2BLSEZEEU2UOK3/action/storage_attestation","attest_author":"https://pith.science/pith/HQZMPJGHHEXU2BLSEZEEU2UOK3/action/author_attestation","sign_citation":"https://pith.science/pith/HQZMPJGHHEXU2BLSEZEEU2UOK3/action/citation_signature","submit_replication":"https://pith.science/pith/HQZMPJGHHEXU2BLSEZEEU2UOK3/action/replication_record"}},"created_at":"2026-07-05T05:50:10.173846+00:00","updated_at":"2026-07-05T05:50:10.173846+00:00"}