{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GFAP6GWTMI2KRCL3FF2DXYWBTR","short_pith_number":"pith:GFAP6GWT","schema_version":"1.0","canonical_sha256":"3140ff1ad36234a8897b29743be2c19c488dd0b35dd5a88eb3fd4be7b562d7f4","source":{"kind":"arxiv","id":"2506.00557","version":1},"attestation_state":"computed","paper":{"title":"Score Matching With Missing Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Henry W J Reeve, Josh Givens, Song Liu","submitted_at":"2025-05-31T13:26:51Z","abstract_excerpt":"Score matching is a vital tool for learning the distribution of data with applications across many areas including diffusion processes, energy based modelling, and graphical model estimation. Despite all these applications, little work explores its use when data is incomplete. We address this by adapting score matching (and its major extensions) to work with missing data in a flexible setting where data can be partially missing over any subset of the coordinates. We provide two separate score matching variations for general use, an importance weighting (IW) approach, and a variational approach"},"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":"2506.00557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-31T13:26:51Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"5662a0d540ce92b00dbf1494863f1697abe5711fe2bd64561a4bf9f664f4763b","abstract_canon_sha256":"a7e2eb8ce93b7b0c6a346afe02a29aa1248c8fb25aac3381f58f47298047a2a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:36.911704Z","signature_b64":"YqgOUMgFf/MXcW1FJ/eeMsQ2hFHBdt7Jh6RUQUjKxTw8j2TqM4yA0rji19eXqg6x5AhQ7g107MAME0JqNcO8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3140ff1ad36234a8897b29743be2c19c488dd0b35dd5a88eb3fd4be7b562d7f4","last_reissued_at":"2026-07-05T11:13:36.911235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:36.911235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Score Matching With Missing Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Henry W J Reeve, Josh Givens, Song Liu","submitted_at":"2025-05-31T13:26:51Z","abstract_excerpt":"Score matching is a vital tool for learning the distribution of data with applications across many areas including diffusion processes, energy based modelling, and graphical model estimation. Despite all these applications, little work explores its use when data is incomplete. We address this by adapting score matching (and its major extensions) to work with missing data in a flexible setting where data can be partially missing over any subset of the coordinates. We provide two separate score matching variations for general use, an importance weighting (IW) approach, and a variational approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00557","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/2506.00557/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":"2506.00557","created_at":"2026-07-05T11:13:36.911292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00557v1","created_at":"2026-07-05T11:13:36.911292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00557","created_at":"2026-07-05T11:13:36.911292+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFAP6GWTMI2K","created_at":"2026-07-05T11:13:36.911292+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFAP6GWTMI2KRCL3","created_at":"2026-07-05T11:13:36.911292+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFAP6GWT","created_at":"2026-07-05T11:13:36.911292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16616","citing_title":"MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20098","citing_title":"Incomplete Data, Complete Dynamics: A Diffusion Approach","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFAP6GWTMI2KRCL3FF2DXYWBTR","json":"https://pith.science/pith/GFAP6GWTMI2KRCL3FF2DXYWBTR.json","graph_json":"https://pith.science/api/pith-number/GFAP6GWTMI2KRCL3FF2DXYWBTR/graph.json","events_json":"https://pith.science/api/pith-number/GFAP6GWTMI2KRCL3FF2DXYWBTR/events.json","paper":"https://pith.science/paper/GFAP6GWT"},"agent_actions":{"view_html":"https://pith.science/pith/GFAP6GWTMI2KRCL3FF2DXYWBTR","download_json":"https://pith.science/pith/GFAP6GWTMI2KRCL3FF2DXYWBTR.json","view_paper":"https://pith.science/paper/GFAP6GWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00557&json=true","fetch_graph":"https://pith.science/api/pith-number/GFAP6GWTMI2KRCL3FF2DXYWBTR/graph.json","fetch_events":"https://pith.science/api/pith-number/GFAP6GWTMI2KRCL3FF2DXYWBTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFAP6GWTMI2KRCL3FF2DXYWBTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFAP6GWTMI2KRCL3FF2DXYWBTR/action/storage_attestation","attest_author":"https://pith.science/pith/GFAP6GWTMI2KRCL3FF2DXYWBTR/action/author_attestation","sign_citation":"https://pith.science/pith/GFAP6GWTMI2KRCL3FF2DXYWBTR/action/citation_signature","submit_replication":"https://pith.science/pith/GFAP6GWTMI2KRCL3FF2DXYWBTR/action/replication_record"}},"created_at":"2026-07-05T11:13:36.911292+00:00","updated_at":"2026-07-05T11:13:36.911292+00:00"}