{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3H47CEBQFI7MOXUDSIMHKL4WTH","short_pith_number":"pith:3H47CEBQ","schema_version":"1.0","canonical_sha256":"d9f9f110302a3ec75e839218752f9699e5fa8892fde4274e7935fab3e0434fa1","source":{"kind":"arxiv","id":"2305.08379","version":2},"attestation_state":"computed","paper":{"title":"TESS: Text-to-Text Self-Conditioned Simplex Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Hamish Ivison, Iz Beltagy, Jaesung Tae, James Henderson, Matthew E. Peters, Rabeeh Karimi Mahabadi","submitted_at":"2023-05-15T06:33:45Z","abstract_excerpt":"Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various continuous domains. However, applying continuous diffusion models to natural language remains challenging due to its discrete nature and the need for a large number of diffusion steps to generate text, making diffusion-based generation expensive. In this work, we propose Text-to-text Self-conditioned Simplex Diffusion (TESS), a text diffusion model that is fully non-autoregressive, employs a new form of self-conditioning, and applies the diffusion process on the logit simplex space rath"},"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":"2305.08379","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T06:33:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"299991f1644b17372d537e9887f7e93212034a35d537a087709821d069059f45","abstract_canon_sha256":"539312e9519fd3f8ec415c6304e6b91d130ee4b38b344e299ffc551df883454c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:25.080894Z","signature_b64":"S6HX8BJhMjXRFRel3OIxmmBSu/NqFxtoSge87VU/PGn3QGZnHF35J6FJjpFgQcGaDaaFxfbvxRkIB7Bx+xwtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9f9f110302a3ec75e839218752f9699e5fa8892fde4274e7935fab3e0434fa1","last_reissued_at":"2026-07-05T07:47:25.080439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:25.080439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TESS: Text-to-Text Self-Conditioned Simplex Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Hamish Ivison, Iz Beltagy, Jaesung Tae, James Henderson, Matthew E. Peters, Rabeeh Karimi Mahabadi","submitted_at":"2023-05-15T06:33:45Z","abstract_excerpt":"Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various continuous domains. However, applying continuous diffusion models to natural language remains challenging due to its discrete nature and the need for a large number of diffusion steps to generate text, making diffusion-based generation expensive. In this work, we propose Text-to-text Self-conditioned Simplex Diffusion (TESS), a text diffusion model that is fully non-autoregressive, employs a new form of self-conditioning, and applies the diffusion process on the logit simplex space rath"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08379","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/2305.08379/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":"2305.08379","created_at":"2026-07-05T07:47:25.080497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08379v2","created_at":"2026-07-05T07:47:25.080497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08379","created_at":"2026-07-05T07:47:25.080497+00:00"},{"alias_kind":"pith_short_12","alias_value":"3H47CEBQFI7M","created_at":"2026-07-05T07:47:25.080497+00:00"},{"alias_kind":"pith_short_16","alias_value":"3H47CEBQFI7MOXUD","created_at":"2026-07-05T07:47:25.080497+00:00"},{"alias_kind":"pith_short_8","alias_value":"3H47CEBQ","created_at":"2026-07-05T07:47:25.080497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18204","citing_title":"Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03206","citing_title":"Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2310.16834","citing_title":"Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3H47CEBQFI7MOXUDSIMHKL4WTH","json":"https://pith.science/pith/3H47CEBQFI7MOXUDSIMHKL4WTH.json","graph_json":"https://pith.science/api/pith-number/3H47CEBQFI7MOXUDSIMHKL4WTH/graph.json","events_json":"https://pith.science/api/pith-number/3H47CEBQFI7MOXUDSIMHKL4WTH/events.json","paper":"https://pith.science/paper/3H47CEBQ"},"agent_actions":{"view_html":"https://pith.science/pith/3H47CEBQFI7MOXUDSIMHKL4WTH","download_json":"https://pith.science/pith/3H47CEBQFI7MOXUDSIMHKL4WTH.json","view_paper":"https://pith.science/paper/3H47CEBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08379&json=true","fetch_graph":"https://pith.science/api/pith-number/3H47CEBQFI7MOXUDSIMHKL4WTH/graph.json","fetch_events":"https://pith.science/api/pith-number/3H47CEBQFI7MOXUDSIMHKL4WTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3H47CEBQFI7MOXUDSIMHKL4WTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3H47CEBQFI7MOXUDSIMHKL4WTH/action/storage_attestation","attest_author":"https://pith.science/pith/3H47CEBQFI7MOXUDSIMHKL4WTH/action/author_attestation","sign_citation":"https://pith.science/pith/3H47CEBQFI7MOXUDSIMHKL4WTH/action/citation_signature","submit_replication":"https://pith.science/pith/3H47CEBQFI7MOXUDSIMHKL4WTH/action/replication_record"}},"created_at":"2026-07-05T07:47:25.080497+00:00","updated_at":"2026-07-05T07:47:25.080497+00:00"}