{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CCLDPGGZWMHRYUOTDKDI6S3F7N","short_pith_number":"pith:CCLDPGGZ","schema_version":"1.0","canonical_sha256":"10963798d9b30f1c51d31a868f4b65fb53434798e71cbecd1a671f2a618e2840","source":{"kind":"arxiv","id":"2606.05361","version":1},"attestation_state":"computed","paper":{"title":"TabSODA: Tabular Diffusion based Imputation with Skip Pattern Detection and Ordinal Awareness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hai Shu, Taehyo Kim, Yang Feng, Yuyu Chen","submitted_at":"2026-06-03T19:09:40Z","abstract_excerpt":"Missing data imputation in large-scale surveys faces two challenges that are not well handled by current tabular diffusion methods. First, \\emph{structural skips}, cells made inapplicable by questionnaire design, should not be imputed but are often conflated with item nonresponse. Second, \\emph{ordinal} responses encode ordered categories, yet most pipelines treat them as nominal levels through one-hot or analog-bit encodings. We introduce \\textbf{TabSODA} (\\textbf{Tab}ular diffusion with \\textbf{S}kip pattern detection and \\textbf{O}r\\textbf{d}inal \\textbf{A}wareness), an Expectation-Maximiza"},"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":"2606.05361","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-03T19:09:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"16a7febb107e4e83a9b15dd90c093ea3843232aba4e50ac61b7599050decbc38","abstract_canon_sha256":"63f840f95e8c0f3a956e02f566bfd0356a486ae1126a75041a752b72e7eb071c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:55.325520Z","signature_b64":"NNU/n8Y3fgQ3elgWLdDUz9qxv0EDuhPCdVyqZe3eGbhWX7v4uVW93BV1KWIimTlPPEbFpA1a7Q3/faVdg27dCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10963798d9b30f1c51d31a868f4b65fb53434798e71cbecd1a671f2a618e2840","last_reissued_at":"2026-06-05T00:13:55.325086Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:55.325086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabSODA: Tabular Diffusion based Imputation with Skip Pattern Detection and Ordinal Awareness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hai Shu, Taehyo Kim, Yang Feng, Yuyu Chen","submitted_at":"2026-06-03T19:09:40Z","abstract_excerpt":"Missing data imputation in large-scale surveys faces two challenges that are not well handled by current tabular diffusion methods. First, \\emph{structural skips}, cells made inapplicable by questionnaire design, should not be imputed but are often conflated with item nonresponse. Second, \\emph{ordinal} responses encode ordered categories, yet most pipelines treat them as nominal levels through one-hot or analog-bit encodings. We introduce \\textbf{TabSODA} (\\textbf{Tab}ular diffusion with \\textbf{S}kip pattern detection and \\textbf{O}r\\textbf{d}inal \\textbf{A}wareness), an Expectation-Maximiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05361","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/2606.05361/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":"2606.05361","created_at":"2026-06-05T00:13:55.325148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05361v1","created_at":"2026-06-05T00:13:55.325148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05361","created_at":"2026-06-05T00:13:55.325148+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCLDPGGZWMHR","created_at":"2026-06-05T00:13:55.325148+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCLDPGGZWMHRYUOT","created_at":"2026-06-05T00:13:55.325148+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCLDPGGZ","created_at":"2026-06-05T00:13:55.325148+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/CCLDPGGZWMHRYUOTDKDI6S3F7N","json":"https://pith.science/pith/CCLDPGGZWMHRYUOTDKDI6S3F7N.json","graph_json":"https://pith.science/api/pith-number/CCLDPGGZWMHRYUOTDKDI6S3F7N/graph.json","events_json":"https://pith.science/api/pith-number/CCLDPGGZWMHRYUOTDKDI6S3F7N/events.json","paper":"https://pith.science/paper/CCLDPGGZ"},"agent_actions":{"view_html":"https://pith.science/pith/CCLDPGGZWMHRYUOTDKDI6S3F7N","download_json":"https://pith.science/pith/CCLDPGGZWMHRYUOTDKDI6S3F7N.json","view_paper":"https://pith.science/paper/CCLDPGGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05361&json=true","fetch_graph":"https://pith.science/api/pith-number/CCLDPGGZWMHRYUOTDKDI6S3F7N/graph.json","fetch_events":"https://pith.science/api/pith-number/CCLDPGGZWMHRYUOTDKDI6S3F7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCLDPGGZWMHRYUOTDKDI6S3F7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCLDPGGZWMHRYUOTDKDI6S3F7N/action/storage_attestation","attest_author":"https://pith.science/pith/CCLDPGGZWMHRYUOTDKDI6S3F7N/action/author_attestation","sign_citation":"https://pith.science/pith/CCLDPGGZWMHRYUOTDKDI6S3F7N/action/citation_signature","submit_replication":"https://pith.science/pith/CCLDPGGZWMHRYUOTDKDI6S3F7N/action/replication_record"}},"created_at":"2026-06-05T00:13:55.325148+00:00","updated_at":"2026-06-05T00:13:55.325148+00:00"}