{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L4MYNWUBAEO2UXM22E3CJWIF35","short_pith_number":"pith:L4MYNWUB","schema_version":"1.0","canonical_sha256":"5f1986da81011daa5d9ad13624d905df6d81425f5df11d71e866162acb0fcb85","source":{"kind":"arxiv","id":"2505.22165","version":1},"attestation_state":"computed","paper":{"title":"Unifying Continuous and Discrete Text Diffusion with Non-simultaneous Diffusion Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bocheng Li, Linli Xu, Zhujin Gao","submitted_at":"2025-05-28T09:28:52Z","abstract_excerpt":"Diffusion models have emerged as a promising approach for text generation, with recent works falling into two main categories: discrete and continuous diffusion models. Discrete diffusion models apply token corruption independently using categorical distributions, allowing for different diffusion progress across tokens but lacking fine-grained control. Continuous diffusion models map tokens to continuous spaces and apply fine-grained noise, but the diffusion progress is uniform across tokens, limiting their ability to capture semantic nuances. To address these limitations, we propose \\textbf{\\"},"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":"2505.22165","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T09:28:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f9157a15c6d7b78c14ad5bd3cc654e779cdcc8062ab9fe9b91ddcc24691901af","abstract_canon_sha256":"06bec2d7d0bfda23e6d401287777fa17a401827c805f3541121689db3c4bb8d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:10.816192Z","signature_b64":"0yDdxvZ2OT9vVBV1D/TGA5+65PjprlVIfvfOgVom+W9bwOMqjfbLCPJ6BNmlb3bzu6YcUGUm0iyM8BqP805GAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f1986da81011daa5d9ad13624d905df6d81425f5df11d71e866162acb0fcb85","last_reissued_at":"2026-07-05T11:11:10.815712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:10.815712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Continuous and Discrete Text Diffusion with Non-simultaneous Diffusion Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bocheng Li, Linli Xu, Zhujin Gao","submitted_at":"2025-05-28T09:28:52Z","abstract_excerpt":"Diffusion models have emerged as a promising approach for text generation, with recent works falling into two main categories: discrete and continuous diffusion models. Discrete diffusion models apply token corruption independently using categorical distributions, allowing for different diffusion progress across tokens but lacking fine-grained control. Continuous diffusion models map tokens to continuous spaces and apply fine-grained noise, but the diffusion progress is uniform across tokens, limiting their ability to capture semantic nuances. To address these limitations, we propose \\textbf{\\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22165","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/2505.22165/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":"2505.22165","created_at":"2026-07-05T11:11:10.815771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22165v1","created_at":"2026-07-05T11:11:10.815771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22165","created_at":"2026-07-05T11:11:10.815771+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4MYNWUBAEO2","created_at":"2026-07-05T11:11:10.815771+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4MYNWUBAEO2UXM2","created_at":"2026-07-05T11:11:10.815771+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4MYNWUB","created_at":"2026-07-05T11:11:10.815771+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/L4MYNWUBAEO2UXM22E3CJWIF35","json":"https://pith.science/pith/L4MYNWUBAEO2UXM22E3CJWIF35.json","graph_json":"https://pith.science/api/pith-number/L4MYNWUBAEO2UXM22E3CJWIF35/graph.json","events_json":"https://pith.science/api/pith-number/L4MYNWUBAEO2UXM22E3CJWIF35/events.json","paper":"https://pith.science/paper/L4MYNWUB"},"agent_actions":{"view_html":"https://pith.science/pith/L4MYNWUBAEO2UXM22E3CJWIF35","download_json":"https://pith.science/pith/L4MYNWUBAEO2UXM22E3CJWIF35.json","view_paper":"https://pith.science/paper/L4MYNWUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22165&json=true","fetch_graph":"https://pith.science/api/pith-number/L4MYNWUBAEO2UXM22E3CJWIF35/graph.json","fetch_events":"https://pith.science/api/pith-number/L4MYNWUBAEO2UXM22E3CJWIF35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4MYNWUBAEO2UXM22E3CJWIF35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4MYNWUBAEO2UXM22E3CJWIF35/action/storage_attestation","attest_author":"https://pith.science/pith/L4MYNWUBAEO2UXM22E3CJWIF35/action/author_attestation","sign_citation":"https://pith.science/pith/L4MYNWUBAEO2UXM22E3CJWIF35/action/citation_signature","submit_replication":"https://pith.science/pith/L4MYNWUBAEO2UXM22E3CJWIF35/action/replication_record"}},"created_at":"2026-07-05T11:11:10.815771+00:00","updated_at":"2026-07-05T11:11:10.815771+00:00"}