{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PJTKKPO5EXMZOANTIR6COOIGUK","short_pith_number":"pith:PJTKKPO5","schema_version":"1.0","canonical_sha256":"7a66a53ddd25d99701b3447c273906a28e4b06558837f384c91dd266a3cab951","source":{"kind":"arxiv","id":"2107.03006","version":3},"attestation_state":"computed","paper":{"title":"Structured Denoising Diffusion Models in Discrete State-Spaces","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Daniel D. Johnson, Daniel Tarlow, Jacob Austin, Jonathan Ho, Rianne van den Berg","submitted_at":"2021-07-07T04:11:00Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPMs) (Ho et al. 2020) have shown impressive results on image and waveform generation in continuous state spaces. Here, we introduce Discrete Denoising Diffusion Probabilistic Models (D3PMs), diffusion-like generative models for discrete data that generalize the multinomial diffusion model of Hoogeboom et al. 2021, by going beyond corruption processes with uniform transition probabilities. This includes corruption with transition matrices that mimic Gaussian kernels in continuous space, matrices based on nearest neighbors in embedding space, and matri"},"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":"2107.03006","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-07T04:11:00Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"0bebfae2a380eed10894c20e17fe466d3fc13e45cf42fba8c1e336ab055f3cde","abstract_canon_sha256":"98d5cc16d4433d6e4295321b3308bc78862703c4bd2628a113c03263912f2827"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:36.932988Z","signature_b64":"gwLRVtLIvEcJrDEKxSOCPma2R4vnGXLDW+YzvDADnJa4qMAbR0ef4MhfLUwlYdMfVMFMqHWhkaM4dsP4iaZIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a66a53ddd25d99701b3447c273906a28e4b06558837f384c91dd266a3cab951","last_reissued_at":"2026-07-05T05:44:36.932539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:36.932539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Denoising Diffusion Models in Discrete State-Spaces","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Daniel D. Johnson, Daniel Tarlow, Jacob Austin, Jonathan Ho, Rianne van den Berg","submitted_at":"2021-07-07T04:11:00Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPMs) (Ho et al. 2020) have shown impressive results on image and waveform generation in continuous state spaces. Here, we introduce Discrete Denoising Diffusion Probabilistic Models (D3PMs), diffusion-like generative models for discrete data that generalize the multinomial diffusion model of Hoogeboom et al. 2021, by going beyond corruption processes with uniform transition probabilities. This includes corruption with transition matrices that mimic Gaussian kernels in continuous space, matrices based on nearest neighbors in embedding space, and matri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03006","kind":"arxiv","version":3},"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/2107.03006/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":"2107.03006","created_at":"2026-07-05T05:44:36.932601+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.03006v3","created_at":"2026-07-05T05:44:36.932601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03006","created_at":"2026-07-05T05:44:36.932601+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJTKKPO5EXMZ","created_at":"2026-07-05T05:44:36.932601+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJTKKPO5EXMZOANT","created_at":"2026-07-05T05:44:36.932601+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJTKKPO5","created_at":"2026-07-05T05:44:36.932601+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27361","citing_title":"Autoregressive Boltzmann Generators","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23623","citing_title":"dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21395","citing_title":"Atomistic Language Models Understand and Generate Materials","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01436","citing_title":"Discrete Diffusion Language Models for Interactive Radiology Report Drafting","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12841","citing_title":"TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04535","citing_title":"Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27732","citing_title":"Bifocal Diffusion Language Models: Asymmetric Bidirectional Context for Parallel Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25820","citing_title":"Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26566","citing_title":"Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2411.16821","citing_title":"Logit-KL Flow Matching: Non-Autoregressive Text Generation via Sampling-Hybrid Inference","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15676","citing_title":"Dynamic Chunking for Diffusion Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16829","citing_title":"Constrained Code Generation with Discrete Diffusion","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16818","citing_title":"Observation-Aligned Mask Priors for Learning Physical Dynamics from Authentic Occlusions","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2510.18165","citing_title":"Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2511.03015","citing_title":"Discrete Bayesian Sample Inference for Graph Generation","ref_index":2,"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":2,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04749","citing_title":"Mitigating Long-Tail Bias via Prompt-Controlled Diffusion Augmentation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2602.05880","citing_title":"Contour Refinement using Discrete Diffusion in Low Data Regime","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11726","citing_title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03677","citing_title":"Unlocking Prompt Infilling Capability for Diffusion Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11726","citing_title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26985","citing_title":"Simple Self-Conditioning Adaptation for Masked Diffusion Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05689","citing_title":"GCCM: Enhancing Generative Graph Prediction via Contrastive Consistency Model","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00161","citing_title":"Consistent Diffusion Language Models","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJTKKPO5EXMZOANTIR6COOIGUK","json":"https://pith.science/pith/PJTKKPO5EXMZOANTIR6COOIGUK.json","graph_json":"https://pith.science/api/pith-number/PJTKKPO5EXMZOANTIR6COOIGUK/graph.json","events_json":"https://pith.science/api/pith-number/PJTKKPO5EXMZOANTIR6COOIGUK/events.json","paper":"https://pith.science/paper/PJTKKPO5"},"agent_actions":{"view_html":"https://pith.science/pith/PJTKKPO5EXMZOANTIR6COOIGUK","download_json":"https://pith.science/pith/PJTKKPO5EXMZOANTIR6COOIGUK.json","view_paper":"https://pith.science/paper/PJTKKPO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.03006&json=true","fetch_graph":"https://pith.science/api/pith-number/PJTKKPO5EXMZOANTIR6COOIGUK/graph.json","fetch_events":"https://pith.science/api/pith-number/PJTKKPO5EXMZOANTIR6COOIGUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJTKKPO5EXMZOANTIR6COOIGUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJTKKPO5EXMZOANTIR6COOIGUK/action/storage_attestation","attest_author":"https://pith.science/pith/PJTKKPO5EXMZOANTIR6COOIGUK/action/author_attestation","sign_citation":"https://pith.science/pith/PJTKKPO5EXMZOANTIR6COOIGUK/action/citation_signature","submit_replication":"https://pith.science/pith/PJTKKPO5EXMZOANTIR6COOIGUK/action/replication_record"}},"created_at":"2026-07-05T05:44:36.932601+00:00","updated_at":"2026-07-05T05:44:36.932601+00:00"}