{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3UYLF7KB5UM5PAKH6FTGIBOBEU","short_pith_number":"pith:3UYLF7KB","schema_version":"1.0","canonical_sha256":"dd30b2fd41ed19d78147f1666405c12531637d9ac76672aa4e1fc7c9fb33f6b3","source":{"kind":"arxiv","id":"2210.14784","version":1},"attestation_state":"computed","paper":{"title":"Categorical SDEs with Simplex Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arnaud Doucet, Pierre H. Richemond, Sander Dieleman","submitted_at":"2022-10-26T15:27:43Z","abstract_excerpt":"Diffusion models typically operate in the standard framework of generative modelling by producing continuously-valued datapoints. To this end, they rely on a progressive Gaussian smoothing of the original data distribution, which admits an SDE interpretation involving increments of a standard Brownian motion. However, some applications such as text generation or reinforcement learning might naturally be better served by diffusing categorical-valued data, i.e., lifting the diffusion to a space of probability distributions. To this end, this short theoretical note proposes Simplex Diffusion, a m"},"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":"2210.14784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-26T15:27:43Z","cross_cats_sorted":[],"title_canon_sha256":"133cc1c72dc2077175050b3398178e7158f4a4950e8fa402bf4989bf531f7566","abstract_canon_sha256":"64ce6950f8b8759c98c1591f4bb60bfe8090f9064ef24c543a8c1489962e27c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:49.724589Z","signature_b64":"C5/ZgemDOIGGDl/EchyCOqMt3prVdbamrnDa+h3R6wm+FHgKA4NeNWc+vJguDXdDKeJGbl20B67l/T4FpsTzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd30b2fd41ed19d78147f1666405c12531637d9ac76672aa4e1fc7c9fb33f6b3","last_reissued_at":"2026-07-05T05:10:49.724228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:49.724228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Categorical SDEs with Simplex Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arnaud Doucet, Pierre H. Richemond, Sander Dieleman","submitted_at":"2022-10-26T15:27:43Z","abstract_excerpt":"Diffusion models typically operate in the standard framework of generative modelling by producing continuously-valued datapoints. To this end, they rely on a progressive Gaussian smoothing of the original data distribution, which admits an SDE interpretation involving increments of a standard Brownian motion. However, some applications such as text generation or reinforcement learning might naturally be better served by diffusing categorical-valued data, i.e., lifting the diffusion to a space of probability distributions. To this end, this short theoretical note proposes Simplex Diffusion, a m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14784","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/2210.14784/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":"2210.14784","created_at":"2026-07-05T05:10:49.724283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.14784v1","created_at":"2026-07-05T05:10:49.724283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14784","created_at":"2026-07-05T05:10:49.724283+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UYLF7KB5UM5","created_at":"2026-07-05T05:10:49.724283+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UYLF7KB5UM5PAKH","created_at":"2026-07-05T05:10:49.724283+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UYLF7KB","created_at":"2026-07-05T05:10:49.724283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19391","citing_title":"Tweedie's Formulae and Diffusion Generative Models Beyond Gaussian","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2211.15089","citing_title":"Continuous diffusion for categorical data","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06548","citing_title":"Continuous Latent Diffusion Language Model","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3UYLF7KB5UM5PAKH6FTGIBOBEU","json":"https://pith.science/pith/3UYLF7KB5UM5PAKH6FTGIBOBEU.json","graph_json":"https://pith.science/api/pith-number/3UYLF7KB5UM5PAKH6FTGIBOBEU/graph.json","events_json":"https://pith.science/api/pith-number/3UYLF7KB5UM5PAKH6FTGIBOBEU/events.json","paper":"https://pith.science/paper/3UYLF7KB"},"agent_actions":{"view_html":"https://pith.science/pith/3UYLF7KB5UM5PAKH6FTGIBOBEU","download_json":"https://pith.science/pith/3UYLF7KB5UM5PAKH6FTGIBOBEU.json","view_paper":"https://pith.science/paper/3UYLF7KB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.14784&json=true","fetch_graph":"https://pith.science/api/pith-number/3UYLF7KB5UM5PAKH6FTGIBOBEU/graph.json","fetch_events":"https://pith.science/api/pith-number/3UYLF7KB5UM5PAKH6FTGIBOBEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UYLF7KB5UM5PAKH6FTGIBOBEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UYLF7KB5UM5PAKH6FTGIBOBEU/action/storage_attestation","attest_author":"https://pith.science/pith/3UYLF7KB5UM5PAKH6FTGIBOBEU/action/author_attestation","sign_citation":"https://pith.science/pith/3UYLF7KB5UM5PAKH6FTGIBOBEU/action/citation_signature","submit_replication":"https://pith.science/pith/3UYLF7KB5UM5PAKH6FTGIBOBEU/action/replication_record"}},"created_at":"2026-07-05T05:10:49.724283+00:00","updated_at":"2026-07-05T05:10:49.724283+00:00"}