{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PWHNURJXIFTYX6Z7YFYLZ4A6NT","short_pith_number":"pith:PWHNURJX","schema_version":"1.0","canonical_sha256":"7d8eda453741678bfb3fc170bcf01e6ce08e2c2512c12b5522fd10411090c909","source":{"kind":"arxiv","id":"2607.23348","version":1},"attestation_state":"computed","paper":{"title":"Logit-Coordinate Generative Models for Mixed Continuous-Categorical Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Xiaotong Shen, Yuefei Shen","submitted_at":"2026-07-25T19:55:04Z","abstract_excerpt":"Mixed continuous--categorical data pose a representation problem for continuous generative models. Flow Matching and Gaussian diffusion operate in Euclidean spaces, whereas categorical laws lie on probability simplices and may be highly imbalanced. We study a logit-coordinate framework that encodes categorical variables as smoothed natural parameters and combines them with transformed numerical variables. This yields common formulations of Logit Flow Matching and Logit Diffusion. We introduce a mixed-distribution discrepancy separating categorical marginal error from conditional continuous Was"},"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":"2607.23348","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-25T19:55:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ff10e014d681fdedb546443c654bf316a9790f1078041a1d8756331eba1868c1","abstract_canon_sha256":"08340f3e063e4fe111ac82984171add799c240d558656fd38d37f160a9710944"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:48.701256Z","signature_b64":"0jPX/JfHcP11aMGn7G5RWU0xwYxFRlGZyQcJ9rR4w6wCb6bIRuz1TzGE7GusObJ/Xu4+1PVP9xDk2uiUHRIrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d8eda453741678bfb3fc170bcf01e6ce08e2c2512c12b5522fd10411090c909","last_reissued_at":"2026-07-28T01:22:48.700491Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:48.700491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logit-Coordinate Generative Models for Mixed Continuous-Categorical Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Xiaotong Shen, Yuefei Shen","submitted_at":"2026-07-25T19:55:04Z","abstract_excerpt":"Mixed continuous--categorical data pose a representation problem for continuous generative models. Flow Matching and Gaussian diffusion operate in Euclidean spaces, whereas categorical laws lie on probability simplices and may be highly imbalanced. We study a logit-coordinate framework that encodes categorical variables as smoothed natural parameters and combines them with transformed numerical variables. This yields common formulations of Logit Flow Matching and Logit Diffusion. We introduce a mixed-distribution discrepancy separating categorical marginal error from conditional continuous Was"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23348","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/2607.23348/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":"2607.23348","created_at":"2026-07-28T01:22:48.700890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23348v1","created_at":"2026-07-28T01:22:48.700890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23348","created_at":"2026-07-28T01:22:48.700890+00:00"},{"alias_kind":"pith_short_12","alias_value":"PWHNURJXIFTY","created_at":"2026-07-28T01:22:48.700890+00:00"},{"alias_kind":"pith_short_16","alias_value":"PWHNURJXIFTYX6Z7","created_at":"2026-07-28T01:22:48.700890+00:00"},{"alias_kind":"pith_short_8","alias_value":"PWHNURJX","created_at":"2026-07-28T01:22:48.700890+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/PWHNURJXIFTYX6Z7YFYLZ4A6NT","json":"https://pith.science/pith/PWHNURJXIFTYX6Z7YFYLZ4A6NT.json","graph_json":"https://pith.science/api/pith-number/PWHNURJXIFTYX6Z7YFYLZ4A6NT/graph.json","events_json":"https://pith.science/api/pith-number/PWHNURJXIFTYX6Z7YFYLZ4A6NT/events.json","paper":"https://pith.science/paper/PWHNURJX"},"agent_actions":{"view_html":"https://pith.science/pith/PWHNURJXIFTYX6Z7YFYLZ4A6NT","download_json":"https://pith.science/pith/PWHNURJXIFTYX6Z7YFYLZ4A6NT.json","view_paper":"https://pith.science/paper/PWHNURJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23348&json=true","fetch_graph":"https://pith.science/api/pith-number/PWHNURJXIFTYX6Z7YFYLZ4A6NT/graph.json","fetch_events":"https://pith.science/api/pith-number/PWHNURJXIFTYX6Z7YFYLZ4A6NT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PWHNURJXIFTYX6Z7YFYLZ4A6NT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PWHNURJXIFTYX6Z7YFYLZ4A6NT/action/storage_attestation","attest_author":"https://pith.science/pith/PWHNURJXIFTYX6Z7YFYLZ4A6NT/action/author_attestation","sign_citation":"https://pith.science/pith/PWHNURJXIFTYX6Z7YFYLZ4A6NT/action/citation_signature","submit_replication":"https://pith.science/pith/PWHNURJXIFTYX6Z7YFYLZ4A6NT/action/replication_record"}},"created_at":"2026-07-28T01:22:48.700890+00:00","updated_at":"2026-07-28T01:22:48.700890+00:00"}