{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OEH4P7RUZTDT7IKFPZU34IPZRV","short_pith_number":"pith:OEH4P7RU","schema_version":"1.0","canonical_sha256":"710fc7fe34ccc73fa1457e69be21f98d6a051f2f88034e243c890feac39c6bf6","source":{"kind":"arxiv","id":"2302.10025","version":2},"attestation_state":"computed","paper":{"title":"DINOISER: Diffused Conditional Sequence Learning by Manipulating Noises","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiasheng Ye, Lihua Qian, Mingxuan Wang, Yu Bao, Zaixiang Zheng","submitted_at":"2023-02-20T15:14:46Z","abstract_excerpt":"While diffusion models have achieved great success in generating continuous signals such as images and audio, it remains elusive for diffusion models in learning discrete sequence data like natural languages. Although recent advances circumvent this challenge of discreteness by embedding discrete tokens as continuous surrogates, they still fall short of satisfactory generation quality. To understand this, we first dive deep into the denoised training protocol of diffusion-based sequence generative models and determine their three severe problems, i.e., 1) failing to learn, 2) lack of scalabili"},"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":"2302.10025","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-20T15:14:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f089acc8ab5dba8995e4d1b7b5044a2ea47437a6bf03e5c59b995d4be0d5bd34","abstract_canon_sha256":"59412897528a5e516496b4140fdce4504628fc00a22378506af8061942eb9530"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:58.530707Z","signature_b64":"AcnBbFE81CBsEapRc4dnvx4UabrCVrelvoH+iHr5u7WzZqjNB9YfvBn5+LRlqZz9DGwyJ/RXC9bpArH9Voz8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"710fc7fe34ccc73fa1457e69be21f98d6a051f2f88034e243c890feac39c6bf6","last_reissued_at":"2026-07-05T08:13:58.530248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:58.530248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DINOISER: Diffused Conditional Sequence Learning by Manipulating Noises","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiasheng Ye, Lihua Qian, Mingxuan Wang, Yu Bao, Zaixiang Zheng","submitted_at":"2023-02-20T15:14:46Z","abstract_excerpt":"While diffusion models have achieved great success in generating continuous signals such as images and audio, it remains elusive for diffusion models in learning discrete sequence data like natural languages. Although recent advances circumvent this challenge of discreteness by embedding discrete tokens as continuous surrogates, they still fall short of satisfactory generation quality. To understand this, we first dive deep into the denoised training protocol of diffusion-based sequence generative models and determine their three severe problems, i.e., 1) failing to learn, 2) lack of scalabili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10025","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/2302.10025/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":"2302.10025","created_at":"2026-07-05T08:13:58.530297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.10025v2","created_at":"2026-07-05T08:13:58.530297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10025","created_at":"2026-07-05T08:13:58.530297+00:00"},{"alias_kind":"pith_short_12","alias_value":"OEH4P7RUZTDT","created_at":"2026-07-05T08:13:58.530297+00:00"},{"alias_kind":"pith_short_16","alias_value":"OEH4P7RUZTDT7IKF","created_at":"2026-07-05T08:13:58.530297+00:00"},{"alias_kind":"pith_short_8","alias_value":"OEH4P7RU","created_at":"2026-07-05T08:13:58.530297+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15531","citing_title":"Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00182","citing_title":"Towards A Generative Protein Evolution Machine with DPLM-Evo","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19726","citing_title":"Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2406.03736","citing_title":"Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16933","citing_title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00182","citing_title":"Towards A Generative Protein Evolution Machine with DPLM-Evo","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00182","citing_title":"Towards A Generative Protein Evolution Machine with DPLM-Evo","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09992","citing_title":"Large Language Diffusion Models","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OEH4P7RUZTDT7IKFPZU34IPZRV","json":"https://pith.science/pith/OEH4P7RUZTDT7IKFPZU34IPZRV.json","graph_json":"https://pith.science/api/pith-number/OEH4P7RUZTDT7IKFPZU34IPZRV/graph.json","events_json":"https://pith.science/api/pith-number/OEH4P7RUZTDT7IKFPZU34IPZRV/events.json","paper":"https://pith.science/paper/OEH4P7RU"},"agent_actions":{"view_html":"https://pith.science/pith/OEH4P7RUZTDT7IKFPZU34IPZRV","download_json":"https://pith.science/pith/OEH4P7RUZTDT7IKFPZU34IPZRV.json","view_paper":"https://pith.science/paper/OEH4P7RU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.10025&json=true","fetch_graph":"https://pith.science/api/pith-number/OEH4P7RUZTDT7IKFPZU34IPZRV/graph.json","fetch_events":"https://pith.science/api/pith-number/OEH4P7RUZTDT7IKFPZU34IPZRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OEH4P7RUZTDT7IKFPZU34IPZRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OEH4P7RUZTDT7IKFPZU34IPZRV/action/storage_attestation","attest_author":"https://pith.science/pith/OEH4P7RUZTDT7IKFPZU34IPZRV/action/author_attestation","sign_citation":"https://pith.science/pith/OEH4P7RUZTDT7IKFPZU34IPZRV/action/citation_signature","submit_replication":"https://pith.science/pith/OEH4P7RUZTDT7IKFPZU34IPZRV/action/replication_record"}},"created_at":"2026-07-05T08:13:58.530297+00:00","updated_at":"2026-07-05T08:13:58.530297+00:00"}