{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IIIFQLFL5MCQPFKIMYTODWTRKB","short_pith_number":"pith:IIIFQLFL","schema_version":"1.0","canonical_sha256":"4210582cabeb050795486626e1da71507814c388df671324b2a169bb9b74509a","source":{"kind":"arxiv","id":"2211.15029","version":2},"attestation_state":"computed","paper":{"title":"DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Kuanning Wang, Tianxiang Sun, Xipeng Qiu, Xuanjing Huang, Zhengfu He","submitted_at":"2022-11-28T03:25:49Z","abstract_excerpt":"We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the two powerful models and enjoy the best of both worlds. On the one hand, diffusion models offer a promising training strategy that helps improve the generation quality. On the other hand, pre-trained denoising language models (e.g., BERT) can be used as a good initialization that accelerates convergence. We explore training BERT to learn the reverse process o"},"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":"2211.15029","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-28T03:25:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0e0bebdb44ae6ef3bc2510cfce848d80a17ac17822661752cc2d326f5ba10225","abstract_canon_sha256":"591c34123a1ce9f4cb1892585007727ca47760fa1762c70232de0d89988a0d3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:29.152108Z","signature_b64":"UMkDnxfWwrmBWOPNZoRRz3GmMKz1DvuktEEQLAQKagodWQNeKe3VHLrXUWPo49x0my4kwEjrWfp0WV76YV7IAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4210582cabeb050795486626e1da71507814c388df671324b2a169bb9b74509a","last_reissued_at":"2026-07-05T05:21:29.151689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:29.151689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Kuanning Wang, Tianxiang Sun, Xipeng Qiu, Xuanjing Huang, Zhengfu He","submitted_at":"2022-11-28T03:25:49Z","abstract_excerpt":"We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the two powerful models and enjoy the best of both worlds. On the one hand, diffusion models offer a promising training strategy that helps improve the generation quality. On the other hand, pre-trained denoising language models (e.g., BERT) can be used as a good initialization that accelerates convergence. We explore training BERT to learn the reverse process o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15029","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/2211.15029/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":"2211.15029","created_at":"2026-07-05T05:21:29.151742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.15029v2","created_at":"2026-07-05T05:21:29.151742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15029","created_at":"2026-07-05T05:21:29.151742+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIIFQLFL5MCQ","created_at":"2026-07-05T05:21:29.151742+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIIFQLFL5MCQPFKI","created_at":"2026-07-05T05:21:29.151742+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIIFQLFL","created_at":"2026-07-05T05:21:29.151742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05722","citing_title":"Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":255,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01775","citing_title":"Set Diffusion: Interpolating Token Orderings Between Autoregression and Diffusion for Fast and Flexible Decoding","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":255,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18309","citing_title":"GCDance: Genre-Controlled Music-Driven 3D Full Body Dance Generation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17384","citing_title":"Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling","ref_index":5,"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":62,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14148","citing_title":"AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16933","citing_title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14067","citing_title":"Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02340","citing_title":"Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2505.22618","citing_title":"Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23235","citing_title":"Measuring Temporal Linguistic Emergence in Diffusion Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09992","citing_title":"Large Language Diffusion Models","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18471","citing_title":"NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIIFQLFL5MCQPFKIMYTODWTRKB","json":"https://pith.science/pith/IIIFQLFL5MCQPFKIMYTODWTRKB.json","graph_json":"https://pith.science/api/pith-number/IIIFQLFL5MCQPFKIMYTODWTRKB/graph.json","events_json":"https://pith.science/api/pith-number/IIIFQLFL5MCQPFKIMYTODWTRKB/events.json","paper":"https://pith.science/paper/IIIFQLFL"},"agent_actions":{"view_html":"https://pith.science/pith/IIIFQLFL5MCQPFKIMYTODWTRKB","download_json":"https://pith.science/pith/IIIFQLFL5MCQPFKIMYTODWTRKB.json","view_paper":"https://pith.science/paper/IIIFQLFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.15029&json=true","fetch_graph":"https://pith.science/api/pith-number/IIIFQLFL5MCQPFKIMYTODWTRKB/graph.json","fetch_events":"https://pith.science/api/pith-number/IIIFQLFL5MCQPFKIMYTODWTRKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIIFQLFL5MCQPFKIMYTODWTRKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIIFQLFL5MCQPFKIMYTODWTRKB/action/storage_attestation","attest_author":"https://pith.science/pith/IIIFQLFL5MCQPFKIMYTODWTRKB/action/author_attestation","sign_citation":"https://pith.science/pith/IIIFQLFL5MCQPFKIMYTODWTRKB/action/citation_signature","submit_replication":"https://pith.science/pith/IIIFQLFL5MCQPFKIMYTODWTRKB/action/replication_record"}},"created_at":"2026-07-05T05:21:29.151742+00:00","updated_at":"2026-07-05T05:21:29.151742+00:00"}