{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:USGHH5JN4PIBSYULWOUBLQ5K2P","short_pith_number":"pith:USGHH5JN","schema_version":"1.0","canonical_sha256":"a48c73f52de3d019628bb3a815c3aad3e506d7c6fcdc67cf23c9522616a0cb4a","source":{"kind":"arxiv","id":"2605.28427","version":1},"attestation_state":"computed","paper":{"title":"Latent Diffusion for Missing Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberte Heering Estad, Ignacio Peis, Jes Frellsen","submitted_at":"2026-05-27T12:57:09Z","abstract_excerpt":"Diffusion models have emerged as powerful generative approaches for missing-data imputation, yet most existing methods operate directly in data space and degrade when training data are heavily incomplete. We investigate whether shifting diffusion to a learned latent representation improves robustness under missing-completely-at-random (MCAR) corruption. To this end, we propose a two-stage framework: a robust VAE-based imputer first learns compact semantic features from incomplete observations, and a diffusion model is then trained in the resulting latent space. Across training missing rates, w"},"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":"2605.28427","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T12:57:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f98afd6a2ca2195c94cc88f096f093c6746fbcaf3644dc587b1c99daaa556b15","abstract_canon_sha256":"619bb4265d9fb267485ae2688652f9395db2e4e10aff8a1bfaaeb37ae7eab39e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:17.866093Z","signature_b64":"kq95R/bal0UpXHf7dSVhdWxcAJIKdOXyhGFXxgfJ/Kbb+tOmDTYpNYzXkldCfITMRPAZWAclWBMmk3E9iC2XAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a48c73f52de3d019628bb3a815c3aad3e506d7c6fcdc67cf23c9522616a0cb4a","last_reissued_at":"2026-05-28T01:05:17.865631Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:17.865631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Diffusion for Missing Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberte Heering Estad, Ignacio Peis, Jes Frellsen","submitted_at":"2026-05-27T12:57:09Z","abstract_excerpt":"Diffusion models have emerged as powerful generative approaches for missing-data imputation, yet most existing methods operate directly in data space and degrade when training data are heavily incomplete. We investigate whether shifting diffusion to a learned latent representation improves robustness under missing-completely-at-random (MCAR) corruption. To this end, we propose a two-stage framework: a robust VAE-based imputer first learns compact semantic features from incomplete observations, and a diffusion model is then trained in the resulting latent space. Across training missing rates, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28427","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/2605.28427/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":"2605.28427","created_at":"2026-05-28T01:05:17.865708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28427v1","created_at":"2026-05-28T01:05:17.865708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28427","created_at":"2026-05-28T01:05:17.865708+00:00"},{"alias_kind":"pith_short_12","alias_value":"USGHH5JN4PIB","created_at":"2026-05-28T01:05:17.865708+00:00"},{"alias_kind":"pith_short_16","alias_value":"USGHH5JN4PIBSYUL","created_at":"2026-05-28T01:05:17.865708+00:00"},{"alias_kind":"pith_short_8","alias_value":"USGHH5JN","created_at":"2026-05-28T01:05:17.865708+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/USGHH5JN4PIBSYULWOUBLQ5K2P","json":"https://pith.science/pith/USGHH5JN4PIBSYULWOUBLQ5K2P.json","graph_json":"https://pith.science/api/pith-number/USGHH5JN4PIBSYULWOUBLQ5K2P/graph.json","events_json":"https://pith.science/api/pith-number/USGHH5JN4PIBSYULWOUBLQ5K2P/events.json","paper":"https://pith.science/paper/USGHH5JN"},"agent_actions":{"view_html":"https://pith.science/pith/USGHH5JN4PIBSYULWOUBLQ5K2P","download_json":"https://pith.science/pith/USGHH5JN4PIBSYULWOUBLQ5K2P.json","view_paper":"https://pith.science/paper/USGHH5JN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28427&json=true","fetch_graph":"https://pith.science/api/pith-number/USGHH5JN4PIBSYULWOUBLQ5K2P/graph.json","fetch_events":"https://pith.science/api/pith-number/USGHH5JN4PIBSYULWOUBLQ5K2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USGHH5JN4PIBSYULWOUBLQ5K2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USGHH5JN4PIBSYULWOUBLQ5K2P/action/storage_attestation","attest_author":"https://pith.science/pith/USGHH5JN4PIBSYULWOUBLQ5K2P/action/author_attestation","sign_citation":"https://pith.science/pith/USGHH5JN4PIBSYULWOUBLQ5K2P/action/citation_signature","submit_replication":"https://pith.science/pith/USGHH5JN4PIBSYULWOUBLQ5K2P/action/replication_record"}},"created_at":"2026-05-28T01:05:17.865708+00:00","updated_at":"2026-05-28T01:05:17.865708+00:00"}