{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KPJS6FRMH3C23HSNIX3TMFUU7Z","short_pith_number":"pith:KPJS6FRM","schema_version":"1.0","canonical_sha256":"53d32f162c3ec5ad9e4d45f7361694fe53ca6cceb75bf321603bcc8000903872","source":{"kind":"arxiv","id":"2107.03502","version":2},"attestation_state":"computed","paper":{"title":"CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiaming Song, Stefano Ermon, Yang Song, Yusuke Tashiro","submitted_at":"2021-07-07T22:20:24Z","abstract_excerpt":"The imputation of missing values in time series has many applications in healthcare and finance. While autoregressive models are natural candidates for time series imputation, score-based diffusion models have recently outperformed existing counterparts including autoregressive models in many tasks such as image generation and audio synthesis, and would be promising for time series imputation. In this paper, we propose Conditional Score-based Diffusion models for Imputation (CSDI), a novel time series imputation method that utilizes score-based diffusion models conditioned on observed data. Un"},"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":"2107.03502","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-07T22:20:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"846a3d3dae27d8237344d138d8777fd0b930394529f95950ccac2abd0e8e3226","abstract_canon_sha256":"b782d03dbc0257a16ed0d752512e7455289f42c264c26923e565f1739b574ffb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:19.208843Z","signature_b64":"/oc4qn5rBRd9JDJFEyKqIptdN1g0DKMm4fMp2COjfaavBdMreLf7qrL3Tyi5ddnJqcdTBaY5WODqa7ZtWDqgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53d32f162c3ec5ad9e4d45f7361694fe53ca6cceb75bf321603bcc8000903872","last_reissued_at":"2026-07-05T03:26:19.208373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:19.208373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiaming Song, Stefano Ermon, Yang Song, Yusuke Tashiro","submitted_at":"2021-07-07T22:20:24Z","abstract_excerpt":"The imputation of missing values in time series has many applications in healthcare and finance. While autoregressive models are natural candidates for time series imputation, score-based diffusion models have recently outperformed existing counterparts including autoregressive models in many tasks such as image generation and audio synthesis, and would be promising for time series imputation. In this paper, we propose Conditional Score-based Diffusion models for Imputation (CSDI), a novel time series imputation method that utilizes score-based diffusion models conditioned on observed data. Un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03502","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/2107.03502/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":"2107.03502","created_at":"2026-07-05T03:26:19.208432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.03502v2","created_at":"2026-07-05T03:26:19.208432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03502","created_at":"2026-07-05T03:26:19.208432+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPJS6FRMH3C2","created_at":"2026-07-05T03:26:19.208432+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPJS6FRMH3C23HSN","created_at":"2026-07-05T03:26:19.208432+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPJS6FRM","created_at":"2026-07-05T03:26:19.208432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07250","citing_title":"Flow-PIN: A Two-Stage Power-Flow-Guided Method for System-Wide Multivariate Profile Inpainting in Distribution Networks","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28253","citing_title":"MR-ImagenTime: Multi-Resolution Time Series Generation through Dual Image Representations","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12992","citing_title":"Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Data","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPJS6FRMH3C23HSNIX3TMFUU7Z","json":"https://pith.science/pith/KPJS6FRMH3C23HSNIX3TMFUU7Z.json","graph_json":"https://pith.science/api/pith-number/KPJS6FRMH3C23HSNIX3TMFUU7Z/graph.json","events_json":"https://pith.science/api/pith-number/KPJS6FRMH3C23HSNIX3TMFUU7Z/events.json","paper":"https://pith.science/paper/KPJS6FRM"},"agent_actions":{"view_html":"https://pith.science/pith/KPJS6FRMH3C23HSNIX3TMFUU7Z","download_json":"https://pith.science/pith/KPJS6FRMH3C23HSNIX3TMFUU7Z.json","view_paper":"https://pith.science/paper/KPJS6FRM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.03502&json=true","fetch_graph":"https://pith.science/api/pith-number/KPJS6FRMH3C23HSNIX3TMFUU7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/KPJS6FRMH3C23HSNIX3TMFUU7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPJS6FRMH3C23HSNIX3TMFUU7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPJS6FRMH3C23HSNIX3TMFUU7Z/action/storage_attestation","attest_author":"https://pith.science/pith/KPJS6FRMH3C23HSNIX3TMFUU7Z/action/author_attestation","sign_citation":"https://pith.science/pith/KPJS6FRMH3C23HSNIX3TMFUU7Z/action/citation_signature","submit_replication":"https://pith.science/pith/KPJS6FRMH3C23HSNIX3TMFUU7Z/action/replication_record"}},"created_at":"2026-07-05T03:26:19.208432+00:00","updated_at":"2026-07-05T03:26:19.208432+00:00"}