{"as_of":"2026-08-06T10:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:30f4eb78d65c1d2ffb2f00103e1cd0592575e901e52ec5265c71f4b445740ec2","coverage":[{"denominator":212,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T05:17:37.697168Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.13431/citation-record","integrity":"/paper/2607.13431/integrity","json":"/paper/2607.13431/citation-record.json","paper":"/paper/2607.13431"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.18085","last_updated":"2026-06-11T00:26:51Z","snapshot_observed_at":"2026-08-04T15:57:57.655593Z","submitted_at":"2025-09-22T17:58:21Z","title":"Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.18085","snapshot_observed_at":"2026-08-02T05:17:24.166456Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:24.166456Z"},"links":{"cited_paper":"/paper/2509.18085","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:1916f336bdfda3debba9098a13be854b7d1ad374286891781cb279c05572d594","observation_id":"c0851ba2-ccb4-4cbb-a955-609241c9dbd6","resolution":{"observed_at":"2026-08-02T05:17:24.166456Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:24.414031Z","title":"Multi- conditioned graph diffusion for neural architecture search.Trans","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:24.414031Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:0f7ed59b55286d2bac016b498b982a88272c81fd72009617aab64f65a0562256","observation_id":"f4e80de6-ee40-44c5-9195-99d936edacb3","resolution":{"observed_at":"2026-08-02T05:17:24.414031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.01202","last_updated":"2026-05-12T07:58:24Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-11-03T03:56:34Z","title":"Forget BIT, It is All about TOKEN: Towards Semantic Information Theory for LLMs","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.01202","snapshot_observed_at":"2026-08-02T05:17:24.873091Z","title":"Forget bit, it is all about token: Towards semantic information theory for llms.ArXiv preprint, abs/2511.01202,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:24.873091Z"},"links":{"cited_paper":"/paper/2511.01202","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:9f973b97c4c264472556c3aa868697281ca028c9fc1824c9a3066550b5111b63","observation_id":"8eeceaa1-36d7-42df-a73f-5c7ea191d469","resolution":{"observed_at":"2026-08-02T05:17:24.873091Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:25.026617Z","title":"Enabling approximate joint sampling in diffusion lms.ArXiv preprint, abs/2509.22738,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:25.026617Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:77b9878b8a97b0c019d039f38d02b024cb8ea9401a988ee63b97db3c117f6ea0","observation_id":"f613642c-7893-4fe7-8bb2-c20ac51afccb","resolution":{"observed_at":"2026-08-02T05:17:25.026617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:25.156329Z","title":"Learning to parallel: Accelerating diffusion large language models via learnable parallel decoding, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:25.156329Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:cc5442f7e9491e3a01b19a1fc519b805a6259e9e6305f78fa43acfef28cbe547","observation_id":"e9c2f428-83aa-4079-aad2-e54579273865","resolution":{"observed_at":"2026-08-02T05:17:25.156329Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:25.384577Z","title":"Simple and critical iterative denoising: A recasting of discrete diffusion in graph generatio","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:25.384577Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:8cb7f96b4e17bf69405f4a68ed5a422ef1d00c23cf058b408efb3ea1c955efbf","observation_id":"87b8f282-77c9-4994-96e0-125971b78c9e","resolution":{"observed_at":"2026-08-02T05:17:25.384577Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07735","last_updated":"2024-01-30T14:46:57Z","snapshot_observed_at":"2026-08-05T20:13:51.166540Z","submitted_at":"2023-06-13T12:40:39Z","title":"Discrete Graph Auto-Encoder","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07735","snapshot_observed_at":"2026-08-02T05:17:25.538627Z","title":"Discrete graph auto-encoder.ArXiv preprint, abs/2306.07735,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:25.538627Z"},"links":{"cited_paper":"/paper/2306.07735","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:f28967aea8419846932fcc383d8b7d487ceaa7526973f374fcb7e4898818b642","observation_id":"c3158f0f-0c35-4f03-ae9a-2f25705d5fd9","resolution":{"observed_at":"2026-08-02T05:17:25.538627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:25.622775Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:25.622775Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:53b891c3cce7f196147c82ee24c546b3fa71fdd0f5a562b776365af46d1e6674","observation_id":"ccfca371-8fc9-4db1-9f9d-142d93ca243a","resolution":{"observed_at":"2026-08-02T05:17:25.622775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:25.796121Z","title":"ScanDL: A diffusion model for generating synthetic scanpaths on texts","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:25.796121Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:d417219733933284db3d73343c1b993e500b850d4a6ee67b3186fe6521290827","observation_id":"175d1b65-03ed-4463-93d3-7b9e7dbeef98","resolution":{"observed_at":"2026-08-02T05:17:25.796121Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:25.883782Z","title":"Breckon, and Chris G","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:25.883782Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:068a9e9b86b0ccccb0581729da97e5884eea49646d01f4c4e415e5585bce40b8","observation_id":"d6ebe78e-3873-43f5-95be-0f1b5bffcdd1","resolution":{"observed_at":"2026-08-02T05:17:25.883782Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.08295","last_updated":"2025-04-09T14:34:53Z","snapshot_observed_at":"2026-08-06T03:04:09.762985Z","submitted_at":"2025-03-11T11:07:35Z","title":"Preference-Based Alignment of Discrete Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.08295","snapshot_observed_at":"2026-08-02T05:17:26.053113Z","title":"Preference-based alignment of discrete diffusion models.ArXiv preprint, abs/2503.08295,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:26.053113Z"},"links":{"cited_paper":"/paper/2503.08295","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:bfeec9f82c2c22a9702d56155f94222b902999e53ab69ecc304774f7daaf15db","observation_id":"d745f52d-d994-4407-9582-7a90bec8eb76","resolution":{"observed_at":"2026-08-02T05:17:26.053113Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:26.431979Z","title":"Jaakkola","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:26.431979Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:0f9036b839691675d8278c8dfca5bb50b52b7c9b3c18f1dc11e69f44bc20871a","observation_id":"d9dcf831-99c4-4920-98c0-848dcc667a5e","resolution":{"observed_at":"2026-08-02T05:17:26.431979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:26.513470Z","title":"Self-speculative masked diffusions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:26.513470Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:997466e98d4edb91ee4950997848f174c05598fbf198503f47c85a9feb8929a6","observation_id":"36be6434-6669-466b-97d7-5d8e08aff6cc","resolution":{"observed_at":"2026-08-02T05:17:26.513470Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:26.619388Z","title":"Generating directed graphs with dual attention and asymmetric encoding.ArXiv preprint, abs/2506.16404,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:26.619388Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:1b0f750ee30dbb133a57d427e30e95f8d5c4e8ff0642b6b2d20fe250755c63ff","observation_id":"86b3b660-1029-4079-a5d6-6d85579940ec","resolution":{"observed_at":"2026-08-02T05:17:26.619388Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:26.726286Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:26.726286Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:2aa7183b273c09aeb2d6e1ee8ea7c575497f8f4c9896fb46ab2ae2b56f5a8ebd","observation_id":"cb31b453-c571-4beb-9006-d9bb0edaaf14","resolution":{"observed_at":"2026-08-02T05:17:26.726286Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:26.812367Z","title":"Freeman, Michael Rubinstein, Yuanzhen Li, and Dilip Krishnan","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:26.812367Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:4b42d61b273867f2ccefdec3d1dbf59cdea6ea4ac7200cad09b1904c401386ea","observation_id":"b3098fca-ba68-46c6-b122-f19895d22ea0","resolution":{"observed_at":"2026-08-02T05:17:26.812367Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:26.931028Z","title":"Dtom: Decider-guided dynamic token merging for accelerating diffusion mllms.ArXiv preprint, abs/2511.12280,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:26.931028Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:302cf18dc86d9094d88812df315c9adaa1c67dbb2facb80608ffec3feee88165","observation_id":"8b1992ae-e30c-4829-8aea-447823f19226","resolution":{"observed_at":"2026-08-02T05:17:26.931028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:27.065064Z","title":"Krishnan","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:27.065064Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:8f90459ea9baf63f74d83f0769622d894b6d14a0569da296d6479e192aaeba34","observation_id":"4fcb1aad-3ba3-4e1a-b729-ab52ea5257cd","resolution":{"observed_at":"2026-08-02T05:17:27.065064Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:27.205629Z","title":"Aligning visual foundation encoders to tokenizers for diffusion models.ArXiv preprint, abs/2509.25162, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:27.205629Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:795f8fa2369fdc933a776d7751e63e949f449cc7e7aa4b107ed77c068b3fd886","observation_id":"fb38532a-da63-4fc2-ad1b-f42eb85a0cc6","resolution":{"observed_at":"2026-08-02T05:17:27.205629Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:27.483151Z","title":"Controllable conversation generation with conversation structures via diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:27.483151Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:63d62bccea9f7cb8bcffcf747931f08bbdd04684f86a4bcbc551f170ff54c050","observation_id":"3b267c34-a996-4352-9a20-ef6505b2b8bd","resolution":{"observed_at":"2026-08-02T05:17:27.483151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:27.596770Z","title":"A cheaper and better diffusion language model with soft-masked noise","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:27.596770Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:09e3c006608300ebe48bf0e3be3fd9eebb128d387ad7a7823d9c12cc00b47b64","observation_id":"0fbc067a-6486-4465-b68c-cd4fee2c9eef","resolution":{"observed_at":"2026-08-02T05:17:27.596770Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:27.836993Z","title":"Sdar-vl: Stable and efficient block-wise diffusion for vision-language understanding.ArXiv preprint, abs/2512.14068, 2025a","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:27.836993Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:fa5fc5e3869ca748855e12d2e668fdd2f9edf70c5c70a0824b8c980ad4b6be76","observation_id":"9a60d4dd-9534-44c6-88cf-ce74d5914457","resolution":{"observed_at":"2026-08-02T05:17:27.836993Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:27.996242Z","title":"M2d2m: Multi-motion generation from text with discrete diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:27.996242Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:b27bd5980a489cd30219c299f23ef8b204e5f9976ec02a83436b1457c43760fe","observation_id":"93758f68-8410-421b-9f9d-ec87a2962ab7","resolution":{"observed_at":"2026-08-02T05:17:27.996242Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:28.164921Z","title":"Speculative diffusion decoding: Accelerating language generation through diffusion","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:28.164921Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:50a2230640767769cd5f486b707304f4402e178487f8200d3bf0d5f6e047ae75","observation_id":"11be11f9-fe27-4c66-b52b-2c5ef596b46a","resolution":{"observed_at":"2026-08-02T05:17:28.164921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:28.336120Z","title":"Split gibbs discrete diffusion posterior sampling.ArXiv preprint, abs/2503.01161,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:28.336120Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:571155fe0d539cb520dea85a2381c7d46600ac6d293ff64ed0a5743371a86c0f","observation_id":"90c15a08-5bab-4da6-bd31-0cf1811d7d7c","resolution":{"observed_at":"2026-08-02T05:17:28.336120Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:28.483794Z","title":"Gaus, Toby P","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:28.483794Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:56aa850eb4c2c4b57c16033f22e42671533232b920cf73e20b59fea658b5c591","observation_id":"2ac9e466-3242-4d6b-be4d-4012a0de0cc0","resolution":{"observed_at":"2026-08-02T05:17:28.483794Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.12603","last_updated":"2025-08-18T04:01:56Z","snapshot_observed_at":"2026-08-05T19:22:37.512861Z","submitted_at":"2025-08-18T04:01:56Z","title":"ViLaD: A Large Vision Language Diffusion Framework for End-to-End Autonomous Driving","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.12603","snapshot_observed_at":"2026-08-02T05:17:28.595180Z","title":"Vilad: A large vision language diffusion framework for end-to-end autonomous driving.ArXiv preprint, abs/2508.12603,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:28.595180Z"},"links":{"cited_paper":"/paper/2508.12603","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:34fb2a40c58d8e80e3d2e43c4a06568da715a97d635a34425603bb3aaba99ead","observation_id":"c0c61636-e4ab-4a06-808e-921822e59ef5","resolution":{"observed_at":"2026-08-02T05:17:28.595180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.23721","last_updated":"2025-06-03T04:40:52Z","snapshot_observed_at":"2026-08-04T04:34:38.185425Z","submitted_at":"2025-05-29T17:53:37Z","title":"DiffER: Categorical Diffusion for Chemical Retrosynthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.23721","snapshot_observed_at":"2026-08-02T05:17:28.764984Z","title":"Differ: Cate- gorical diffusion for chemical retrosynthesis.ArXiv preprint, abs/2505.23721,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:28.764984Z"},"links":{"cited_paper":"/paper/2505.23721","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:b9a80aad69d2a46ad3a0fd211e8f64f47b44125e25503bf98d4b363ac994cfd1","observation_id":"326619fb-c028-4682-a809-e8ab2bd20bf2","resolution":{"observed_at":"2026-08-02T05:17:28.764984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:28.844913Z","title":"Periodic materials generation using text-guided joint diffusion model","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:28.844913Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:15520fe2d87078f04a4af6376ceba06d8e4f3caafc5c1f84fd6fabb7e2f2cade","observation_id":"b8512c24-68a8-40c5-8839-41cd5e83899e","resolution":{"observed_at":"2026-08-02T05:17:28.844913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:28.986531Z","title":"Discrete diffusion language model for efficient text summarization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:28.986531Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:0e1bdb8358aa8734589fef2160dfa71da2b644ecfffe006ccb433cac22c0ccae","observation_id":"a681e60a-1003-49c1-8bd5-7de7113930c4","resolution":{"observed_at":"2026-08-02T05:17:28.986531Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:29.126175Z","title":"Alexandre Défossez, Jade Copet, Gabriel Synnaeve, and Yossi Adi","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:29.126175Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:42aaa71c2924200331720507d861f12c4d92a0804d90df7edef5d329696cbb7e","observation_id":"eaf47460-f954-494c-aa60-ae0c8f640f3c","resolution":{"observed_at":"2026-08-02T05:17:29.126175Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:29.277422Z","title":"Uniform discrete diffusion with metric path for video generation.ArXiv preprint, abs/2510.24717,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:29.277422Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:3025cc3c52928d9127d4040e1c3386aa48720a70808b2065a81a3b68675d2339","observation_id":"e249cd17-2620-430a-8dd8-bf41af7edce0","resolution":{"observed_at":"2026-08-02T05:17:29.277422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:29.383718Z","title":"Llada-medv: Exploring large language diffusion models for biomedical image understanding.ArXiv preprint, abs/2508.01617, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:29.383718Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:08534a0b41d7e63d5a7de16c83fac3177df81c07f0cbe286bbb12916674d80cb","observation_id":"c6fdf842-01c9-4952-943a-1437bc829bf0","resolution":{"observed_at":"2026-08-02T05:17:29.383718Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:29.558222Z","title":"Planning with diffusion models for target-oriented dialogue systems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:29.558222Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:0ec078ff1f2557cb2f09bebdbf18fc1be242a5dbf91fdd6251a75214e6c065a4","observation_id":"16301bc2-bbac-4515-8b49-9f9b80a6f5c8","resolution":{"observed_at":"2026-08-02T05:17:29.558222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:29.675451Z","title":"Vector quantized diffusion model based speech bandwidth extension","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:29.675451Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:632fb29010c5a65bfb71bf7d958ac7acc20016e5f7afa405e0415592f5839c47","observation_id":"e9a438b3-224e-4dac-965f-31d8fe43669b","resolution":{"observed_at":"2026-08-02T05:17:29.675451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.16959","last_updated":"2025-09-01T20:18:07Z","snapshot_observed_at":"2026-07-06T21:28:43.610849Z","submitted_at":"2025-05-22T17:40:08Z","title":"Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.16959","snapshot_observed_at":"2026-08-02T05:17:29.851866Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:29.851866Z"},"links":{"cited_paper":"/paper/2505.16959","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:64d58e0b1196595ce48d302991e71ed06c7a26c08529ef800fd9af560ad52691","observation_id":"65adc0e2-ffa0-43b1-a350-b52440e666f1","resolution":{"observed_at":"2026-08-02T05:17:29.851866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:29.980665Z","title":"Masked diffusion captioning for visual feature learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:29.980665Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:f4d7d94c4d4008f86c0af7b974986dd043059a0d240e4c8b42a114b616306dfa","observation_id":"275c27ae-7aac-4d04-b39d-b0f93b2c97fd","resolution":{"observed_at":"2026-08-02T05:17:29.980665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:30.119369Z","title":"Learnable sampler distillation for discrete diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:30.119369Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:7f7d0e8b48c74cb44c1fc6d0dc0a143a558bbf0a29336c977ccca9bc9d6734ae","observation_id":"eb3fc785-a25f-4e4a-a91c-83c0cedd376f","resolution":{"observed_at":"2026-08-02T05:17:30.119369Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.09642","last_updated":"2023-01-22T05:07:54Z","snapshot_observed_at":"2026-08-05T18:01:07.942771Z","submitted_at":"2023-01-22T05:07:54Z","title":"DiffSDS: A language diffusion model for protein backbone inpainting under geometric conditions and constraints","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.09642","snapshot_observed_at":"2026-08-02T05:17:30.319128Z","title":"Diffu- COMET: Contextual commonsense knowledge diffusion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:30.319128Z"},"links":{"cited_paper":"/paper/2301.09642","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:c03851d26635fa3ce03ac124b231e71d017010da3cca51ad58ec101806ed4bbe","observation_id":"cdd5ea2c-9233-4ae9-997d-703bb19f12be","resolution":{"observed_at":"2026-08-02T05:17:30.319128Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.09673","last_updated":"2024-03-19T05:29:23Z","snapshot_observed_at":"2026-07-06T17:44:45.924645Z","submitted_at":"2024-02-04T12:18:51Z","title":"FoldToken: Learning Protein Language via Vector Quantization and Beyond","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.09673","snapshot_observed_at":"2026-08-02T05:17:30.392773Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:30.392773Z"},"links":{"cited_paper":"/paper/2403.09673","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:5f86db87b66448afbcc63f8fe9a6ea49aa596d893aedc1ce67aaf5406391eddc","observation_id":"4755cf5a-b8df-48d5-bc3c-1ef78a1ab9b8","resolution":{"observed_at":"2026-08-02T05:17:30.392773Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:30.458809Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:30.458809Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:196c0043d8291655153d8754ce220d4291e6924cf2804833eace464a25d5e2c0","observation_id":"1cd5413d-6d7b-42a5-a741-ba4b75bffc43","resolution":{"observed_at":"2026-08-02T05:17:30.458809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:30.514006Z","title":"Mask-predict: Parallel decoding of conditional masked language models","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:30.514006Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:de3c47b8bb3cd87e498d5ae878e8a33c3067ea89ae3ea941d43c860e2caa1e7e","observation_id":"1edec23e-f446-4d4d-81be-3fae8cc3a777","resolution":{"observed_at":"2026-08-02T05:17:30.514006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:30.572570Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:30.572570Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:6f38db13730f9bd1927d3f5716dbb467f70e0dfc8d1731b14a2da0018137e874","observation_id":"fe508446-3fe9-4735-bfc9-14e1eddad06e","resolution":{"observed_at":"2026-08-02T05:17:30.572570Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:30.645276Z","title":"Text-guidedmoleculegenerationwithdiffusionlanguage model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:30.645276Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:94e7da90ead366c4c77dcbeb43e3ae6ea13b7418d1f612932b3e882366f554f5","observation_id":"c00fa05f-b078-4b39-8d9c-d1f7e0be03be","resolution":{"observed_at":"2026-08-02T05:17:30.645276Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-01T20:24:21.885586Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-02T05:17:30.794886Z","title":"Diffuseq: Sequence to sequence text generation with diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:30.794886Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:3ba2128a9035181eed256c26dbc3b9547f910f27e7bcf1b80e1f59ea85ea9541","observation_id":"adb2c22b-069d-410f-81a3-0e1ded022e21","resolution":{"observed_at":"2026-08-02T05:17:30.794886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:30.955613Z","title":"Frey, Tim G","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:30.955613Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:d91e18406742e7276b4e769cea35ec35b3d74e32ddace927e2638d080152e0cb","observation_id":"51f28e20-606a-4a89-b5eb-07646c20718b","resolution":{"observed_at":"2026-08-02T05:17:30.955613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:30.992600Z","title":"Vector quantized diffusion model for text-to-image synthesis","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:30.992600Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:8ac13fcf104b01a428fe074661eda1b27d65a9f8c52b389541fb26920a1f75f9","observation_id":"61e4ed69-321d-436b-ad36-8d822fd51f8d","resolution":{"observed_at":"2026-08-02T05:17:30.992600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:31.033664Z","title":"Powers, Weili Nie, Tomas Geffner, Karsten Kreis, Jure Leskovec, Arash Vahdat, and Stefano Ermon","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:31.033664Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:b531343c71b4c8a37b27325abf835513ff7013a0ca611736a8aa932e4a4434be","observation_id":"d34ccce4-8127-4066-9df5-f82ff3f0a781","resolution":{"observed_at":"2026-08-02T05:17:31.033664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:31.185077Z","title":"Hashimoto","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:31.185077Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:21b12c1dc5ab8f67205d04428ffa17529c175082be3a0cd0d1dd1d6c4a3da6b4","observation_id":"44e29ee7-e190-4370-b6cf-8d361f0cb055","resolution":{"observed_at":"2026-08-02T05:17:31.185077Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.20456","last_updated":"2025-04-29T06:33:13Z","snapshot_observed_at":"2026-08-04T17:37:28.160944Z","submitted_at":"2025-04-29T06:33:13Z","title":"Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.20456","snapshot_observed_at":"2026-08-02T05:17:31.309322Z","title":"Revivingany-subsetautoregressivemodelswithprincipledparallelsampling and speculative decoding.ArXiv preprint, abs/2504.20456,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:31.309322Z"},"links":{"cited_paper":"/paper/2504.20456","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:56442ac3687d499033aab26a0eebba8e7e0c500aa46a648553f205c48a881f07","observation_id":"dca79464-4a53-482a-92cb-18d9c66dea75","resolution":{"observed_at":"2026-08-02T05:17:31.309322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11420","last_updated":"2025-06-11T01:18:01Z","snapshot_observed_at":"2026-07-06T20:37:33.041473Z","submitted_at":"2025-02-17T04:20:39Z","title":"Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11420","snapshot_observed_at":"2026-08-02T05:17:31.413207Z","title":"Training-free guidance beyond differentiability: Scalable path steering with tree search in diffusion and flow models.ArXiv preprint, abs/2502.11420,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:31.413207Z"},"links":{"cited_paper":"/paper/2502.11420","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:aa32ef94c0d1bc0a612488e49211d6b6b9d78d568e29b7bf3af235cdac4bc771","observation_id":"b0b8b430-6035-40ea-ae03-36d4dafbc1c4","resolution":{"observed_at":"2026-08-02T05:17:31.413207Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:31.476330Z","title":"Reward-weighted sampling: Enhancing non-autoregressive characteristics in masked diffusion llms","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:31.476330Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:eea1a409ad78573043c4bfc7564509e46335b7419c1cf24213e5cc7591f08623","observation_id":"dd12318d-f770-4515-a490-95ecb1ebee97","resolution":{"observed_at":"2026-08-02T05:17:31.476330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.01549","last_updated":"2023-08-15T23:10:57Z","snapshot_observed_at":"2026-07-06T13:59:27.098801Z","submitted_at":"2022-10-04T12:20:21Z","title":"Diffusion Models for Graphs Benefit From Discrete State Spaces","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.01549","snapshot_observed_at":"2026-08-02T05:17:31.527969Z","title":"Wattenhofer","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:31.527969Z"},"links":{"cited_paper":"/paper/2210.01549","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:b7aae5483b487c08092b269fd20592e98c89923e3b8d499d254b7e321cb91793","observation_id":"c4107daf-f858-4406-b072-2b081ff2b3e9","resolution":{"observed_at":"2026-08-02T05:17:31.527969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:31.619395Z","title":"Discrete diffusion trajectory alignment via stepwise decomposition.ArXiv preprint, abs/2507.04832, 2025a","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:31.619395Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:d85247579c6827d57bde30542cb5c2fd13303e66044d2dff9a94c16e091769ea","observation_id":"2f7e9333-41b9-47e7-ac25-46db179b0508","resolution":{"observed_at":"2026-08-02T05:17:31.619395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:31.740525Z","title":"Discovering mathemat- ical equations with diffusion language model.ArXiv preprint, abs/2509.13136, 2025c","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:31.740525Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:9d0ea2e9aa8b8101272105b6f706ae8f2b6b7faf0a4c7c979e8fd40f5fa73c44","observation_id":"dd84ffa1-1739-4a6e-bf15-12b026128db5","resolution":{"observed_at":"2026-08-02T05:17:31.740525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:31.903972Z","title":"Efficient perplexity bound and ratio matching in discrete diffusion language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:31.903972Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:a9daaecf56d225ef634d61b54638b607cf318e5e1f537cb3f08980b3e4f8d8ca","observation_id":"1c0a6f7e-da2e-43e3-a819-d1e469396ae1","resolution":{"observed_at":"2026-08-02T05:17:31.903972Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:31.984545Z","title":"Distillation of discrete diffusion through dimensional correlations","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:31.984545Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:9ba9ccafda6875364112e3d75b485b3185defa3fd2260f8cc5ca229bd21653b8","observation_id":"9791d7d0-0fe2-4cd9-8b74-847560e3546d","resolution":{"observed_at":"2026-08-02T05:17:31.984545Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:32.053256Z","title":"Ultrallada: Scaling the context length to 128k for diffusion large language models.ArXiv preprint, abs/2510.10481, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:32.053256Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:5ee5a2b1b25305052da44a54753d81f6b907ac21b59efad2a09e33c9a9ffb7e2","observation_id":"f032fa3a-b237-41e7-afa4-727a8990fb14","resolution":{"observed_at":"2026-08-02T05:17:32.053256Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10971","last_updated":"2025-06-12T17:59:19Z","snapshot_observed_at":"2026-07-06T21:41:14.693158Z","submitted_at":"2025-06-12T17:59:19Z","title":"What Exactly Does Guidance Do in Masked Discrete Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.10971","snapshot_observed_at":"2026-08-02T05:17:32.147264Z","title":"What exactly does guidance do in masked discrete diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:32.147264Z"},"links":{"cited_paper":"/paper/2506.10971","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:09266f2cd89086beeeaa6cfca157c21eae3391d06c49f9c5c70f8d99595d05ac","observation_id":"1a18c404-a64c-4c47-aefa-deff5ee1ae08","resolution":{"observed_at":"2026-08-02T05:17:32.147264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:32.223467Z","title":"Shao, Chaofan Gan, Shijie Li, Zuxuan Wu, and Weiyao Lin","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:32.223467Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:f98eab32ae1987703ab8a3cd14f987ea350319bafe418bc5fc2f3c439f8844c2","observation_id":"6dee0289-2409-4978-991c-1ebdac0547e2","resolution":{"observed_at":"2026-08-02T05:17:32.223467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:32.335001Z","title":"Unsu- pervised training of diffusion models for feasible solution generation in neural combinatorial optimization, 2024a","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:32.335001Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:3109c215e3d37c21a070c79146de306aba82f2e3f7833f08ff01a5dae97c4d0f","observation_id":"3977ba91-dc7d-4e6c-96f9-703f04d46f9b","resolution":{"observed_at":"2026-08-02T05:17:32.335001Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:32.337517Z","title":"Gritsenko, Jasmijn Bastings, Ben Poole, Rianne van den Berg, and Tim Salimans","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:32.337517Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:667394f0a7c310e8acc40d937999cdbafa45073c3b478b514236e3a940bae0ef","observation_id":"0d6277e3-ec59-4d2c-9e3d-96c8f3832f46","resolution":{"observed_at":"2026-08-02T05:17:32.337517Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:32.417635Z","title":"Bad: Bidirectional auto-regressive diffusion for text-to-motion generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:32.417635Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:387badc68f726b2e2f1aa02c11aff7c90f83a0e62d1964979c39607a18377ccf","observation_id":"54801633-1881-4a7f-9773-b194df6c0d39","resolution":{"observed_at":"2026-08-02T05:17:32.417635Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:32.566758Z","title":"Suganthan","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:32.566758Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:2b155d1fea89b9842137bf967f0061ff727b3ddef8ca66f09139a5a11f9989ff","observation_id":"3d500c39-58b1-462d-b037-0abe148ab9e8","resolution":{"observed_at":"2026-08-02T05:17:32.566758Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:32.703434Z","title":"Suganthan","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:32.703434Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:65f6ea4a37ea206e91fde1f1acaef85d35599ff47064cf4b6518b1f953665c57","observation_id":"58ab6e8a-5c87-4a4a-af61-12325b36ef57","resolution":{"observed_at":"2026-08-02T05:17:32.703434Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.21066","last_updated":"2024-12-09T22:33:30Z","snapshot_observed_at":"2026-08-04T10:47:11.184088Z","submitted_at":"2024-05-31T17:54:52Z","title":"Mixed Diffusion for 3D Indoor Scene Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.21066","snapshot_observed_at":"2026-08-02T05:17:32.790034Z","title":"Mixed diffusion for 3d indoor scene synthesis.ArXiv preprint, abs/2405.21066,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:32.790034Z"},"links":{"cited_paper":"/paper/2405.21066","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:84bcd475955a87aef3aa54e5d76aa750989ce2da0540e159afaf0761dedf64a5","observation_id":"b4080fd9-9a41-4d7a-8518-a083b1514b5d","resolution":{"observed_at":"2026-08-02T05:17:32.790034Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:32.987822Z","title":"Abdelfattah, Jae sun Seo, Zhiru Zhang, and Udit Gupta","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:32.987822Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:8f9035b86edc69b39fa3e64e6a0cb4f84a88bac98084fe957b04642665d9788e","observation_id":"fe4732c1-14e2-49d9-9c74-9c9e3356ee51","resolution":{"observed_at":"2026-08-02T05:17:32.987822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.22450","last_updated":"2026-06-02T21:39:29Z","snapshot_observed_at":"2026-08-03T17:20:53.310227Z","submitted_at":"2026-01-30T01:36:00Z","title":"Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from $k$-Parity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.22450","snapshot_observed_at":"2026-08-02T05:17:33.121605Z","title":"Tuning the implicit regularizer of masked diffusion language models: Enhancing generalization via insights from -parity.ArXiv preprint, abs/2601.22450,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:33.121605Z"},"links":{"cited_paper":"/paper/2601.22450","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:c9eaa19fba188cd4dc5c96ab15e872dfb24b5dcdd1eb1eb4fe45375f7e6897c0","observation_id":"36f7b735-a471-4ebe-bc6b-b120983e1f66","resolution":{"observed_at":"2026-08-02T05:17:33.121605Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:33.291621Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:33.291621Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:0703c9186d637def69bcfddbaf3ec34629025d11c79bdacff881c2f598ea209d","observation_id":"e8b5d56e-5972-413b-a5b5-935dd9522279","resolution":{"observed_at":"2026-08-02T05:17:33.291621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.18245","last_updated":"2025-03-24T00:03:16Z","snapshot_observed_at":"2026-07-06T20:57:30.357469Z","submitted_at":"2025-03-24T00:03:16Z","title":"DiffGED: Computing Graph Edit Distance via Diffusion-based Graph Matching","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.18245","snapshot_observed_at":"2026-08-02T05:17:33.452765Z","title":"Diffged: Computing graph edit distance via diffusion-based graph matching.ArXiv preprint, abs/2503.18245, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:33.452765Z"},"links":{"cited_paper":"/paper/2503.18245","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:400419630c4a6ebc793cf31fdd1cb1c8cf931be5d38c258bdb3fc6ae28e41ab4","observation_id":"7047bd65-9896-4799-93ed-754cd26dbf24","resolution":{"observed_at":"2026-08-02T05:17:33.452765Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:33.603400Z","title":"Reinforcing the diffusion chain of lateral thought with diffusion language models.ArXiv preprint, abs/2505.10446, 2025b","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:33.603400Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:24b7429e9a6b6143c6367e2bd1673f26ef113853478e3a5513e6b4caec813929","observation_id":"3dada1d2-545f-4eaa-8ce5-cdef7e3a6169","resolution":{"observed_at":"2026-08-02T05:17:33.603400Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:33.737724Z","title":"Layoutdm: Discrete diffusion model for controllable layout generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:33.737724Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:ccdc47a1cb68e9fbe1e90a9729f5ff942eda0020e915be60547c0f1f93fdb871","observation_id":"413a5a95-60a1-45ff-b844-989515dcdedf","resolution":{"observed_at":"2026-08-02T05:17:33.737724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:33.899597Z","title":"Cheng, Guy Van den Broeck, Aditya Grover, Suvinay Subramanian, and Michael Carbin","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:33.899597Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:ef1dc204a9e93f52858f1f222e9d007750192a0a972985182f2e00ff5266a126","observation_id":"da49e11a-7c3a-4105-89f9-571a4fcb3665","resolution":{"observed_at":"2026-08-02T05:17:33.899597Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:34.071137Z","title":"Layout-corrector: Alleviating layout sticking phenomenon in discrete diffusion model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:34.071137Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:a0f330103999a07af4a74fcfd862f79d442c035d72242c0c356647bccf882db5","observation_id":"f191be1c-7bfc-44bf-a76a-ea44a8da6451","resolution":{"observed_at":"2026-08-02T05:17:34.071137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.09106","last_updated":"2026-06-01T18:15:10Z","snapshot_observed_at":"2026-08-03T17:33:28.590038Z","submitted_at":"2025-12-09T20:44:33Z","title":"Learning Unmasking Policies for Diffusion Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.09106","snapshot_observed_at":"2026-08-02T05:17:34.231807Z","title":"Olausson, Louis Béthune, Pierre Ablin, Michael Kirchhof, João Monteiro, Victor Turrisi, Jason Ramapuram, and Marco Cuturi","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:34.231807Z"},"links":{"cited_paper":"/paper/2512.09106","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:04a6f7ea116784202ac787bdf64edf63c57524bf073fab23ed55c04f05628061","observation_id":"8f622027-1e51-43c6-90fc-d4f4ba497d6d","resolution":{"observed_at":"2026-08-02T05:17:34.231807Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:34.424703Z","title":"A2d: Any-order, any-step safety alignment for diffusion language models.ArXiv preprint, abs/2509.23286,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:34.424703Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:15a994e987409f2ffed23ad1443c8790ba64ea3d4e2ecbab0582756652bfc601","observation_id":"e9f04c9e-fc28-44e6-ac9d-974b8658c91d","resolution":{"observed_at":"2026-08-02T05:17:34.424703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:34.568617Z","title":"From denoising to refining: A corrective framework for vision-language diffusion model.ArXiv preprint, abs/2510.19871,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:34.568617Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:557cd4762b8299e6bfe4c6892a85e1c57ded970809bbc3a4a4d83732e9fe2915","observation_id":"4ed0f45c-2051-416d-8d38-521fcb97569f","resolution":{"observed_at":"2026-08-02T05:17:34.568617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.18159","last_updated":"2026-05-21T06:06:30Z","snapshot_observed_at":"2026-08-01T12:50:23.977642Z","submitted_at":"2025-11-22T19:04:47Z","title":"Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.18159","snapshot_observed_at":"2026-08-02T05:17:34.633934Z","title":"Bringing stability to diffusion: Decomposing and reducing variance of training masked diffusion models.ArXiv preprint, abs/2511.18159,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:34.633934Z"},"links":{"cited_paper":"/paper/2511.18159","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:ce04a8da743c771108f15334772becddf9a0e7cd1ea31e308f1935dc9de20c89","observation_id":"fefb9a68-4acd-45a4-b24c-9767a6ca6e2f","resolution":{"observed_at":"2026-08-02T05:17:34.633934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:34.696736Z","title":"Diffusion language models are provably optimal parallel samplers.ArXiv preprint, abs/2512.25014, 2025a","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:34.696736Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:ccd7df50df7325297ccbc803aabf6a317c7c77d8a716d43ba5c3d417c31e4607","observation_id":"7faa59ca-2500-4b85-b922-4d7257105a20","resolution":{"observed_at":"2026-08-02T05:17:34.696736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.19304","last_updated":"2026-05-13T06:53:46Z","snapshot_observed_at":"2026-08-02T05:48:44.106137Z","submitted_at":"2025-10-22T07:08:47Z","title":"Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.19304","snapshot_observed_at":"2026-08-02T05:17:34.759121Z","title":"Loopholing discrete diffu- sion: Deterministic bypass of the sampling wall.ArXiv preprint, abs/2510.19304,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:34.759121Z"},"links":{"cited_paper":"/paper/2510.19304","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:c172f891e79af6bc3328abe192c32c1d2ca60efca267e27832f73e0eed6fc372","observation_id":"93123214-8b33-4119-9a52-898107a127ed","resolution":{"observed_at":"2026-08-02T05:17:34.759121Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.04767","last_updated":"2026-06-23T05:37:09Z","snapshot_observed_at":"2026-08-04T11:28:05.944981Z","submitted_at":"2025-10-06T12:41:31Z","title":"ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.04767","snapshot_observed_at":"2026-08-02T05:17:34.851055Z","title":"Parallelbench: Understanding the trade-offs of parallel decoding in diffusion llms.ArXiv preprint, abs/2510.04767,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:34.851055Z"},"links":{"cited_paper":"/paper/2510.04767","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:41a18ed941d11879400703196f213c1ea8d4a8afab3a6e8af6fee206f963d9a9","observation_id":"154ee8ab-a2b8-46c8-898a-c7dfcebf3179","resolution":{"observed_at":"2026-08-02T05:17:34.851055Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:35.060025Z","title":"Discriminator guidance for autoregressive diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:35.060025Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:1e1f12d59492f80d4ea8ee8c73bbe76113fd0a4ed4a6c306d8c2f47e26dcc969","observation_id":"0a0073fb-6228-486e-9331-4da1c3af14d2","resolution":{"observed_at":"2026-08-02T05:17:35.060025Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:35.205271Z","title":"Andersson, Abhijith S","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:35.205271Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:d32b3780246912c830acf77187fd0dbede6a5685795e59a103ece0af55427199","observation_id":"252ee7aa-104a-456c-9149-b02516be042b","resolution":{"observed_at":"2026-08-02T05:17:35.205271Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.07359","last_updated":"2024-09-11T15:43:47Z","snapshot_observed_at":"2026-07-06T19:13:50.684379Z","submitted_at":"2024-09-11T15:43:47Z","title":"Training-Free Guidance for Discrete Diffusion Models for Molecular Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.07359","snapshot_observed_at":"2026-08-02T05:17:35.360077Z","title":"Kerby and Kevin R","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:35.360077Z"},"links":{"cited_paper":"/paper/2409.07359","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:e6e1be9e902cb1387a9ade9c7fc125e2734d3d87aabff30d6f9bb80d2e3cac3f","observation_id":"0215874d-dff8-469a-b948-618b95dbbba3","resolution":{"observed_at":"2026-08-02T05:17:35.360077Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.17298","last_updated":"2025-06-17T17:06:18Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-17T17:06:18Z","title":"Mercury: Ultra-Fast Language Models Based on Diffusion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.17298","snapshot_observed_at":"2026-08-02T05:17:35.518221Z","title":"Mercury: Ultra-fast language models based on diffusion.ArXiv preprint, abs/2506.17298,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:35.518221Z"},"links":{"cited_paper":"/paper/2506.17298","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:160494fe21dea05cf86eadb230ccc5e1fbffd89487cd21f59ace1079533b190b","observation_id":"8a646e21-2273-4970-a29f-13db29b93f22","resolution":{"observed_at":"2026-08-02T05:17:35.518221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:35.670451Z","title":"Fréchet Audio Distance: A Reference-Free Metric for Evaluating Music Enhancement Algorithms","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:35.670451Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:8a1725ecf9cd47ee17ab05ec507e6a7d9f5ba7d32e2f0c2026a95604d0903dcb","observation_id":"25b2acd8-f78c-4f8c-9efb-42b5f4fa7116","resolution":{"observed_at":"2026-08-02T05:17:35.670451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:35.844263Z","title":"Rainbow padding: Mitigating early termination in instruction-tuned diffusion llms.ArXiv preprint, abs/2510.03680, 2025a","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:35.844263Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:7d360e187e31bd2031162066de3e9d1b832b3e6a0c5ccdc6d2049b1bf591b844","observation_id":"407d6d58-a3fc-4888-adaa-2f862b4868e3","resolution":{"observed_at":"2026-08-02T05:17:35.844263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:35.980632Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:35.980632Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:ea9f5f904cbbfcd795715b9a3d930a80e6d8a56e45c82ae938e350fde163c531","observation_id":"9a59f7b7-ffc9-4f3e-a52d-16f0278ffc08","resolution":{"observed_at":"2026-08-02T05:17:35.980632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:36.129090Z","title":"Conditional [mask] discrete diffusionlanguagemodel","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:36.129090Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:65eac8a543ae132a27dc841cdcba79278b167b3a92d8c0ac160f508d7df1cf03","observation_id":"a7942f14-9df7-4ad9-954a-d3e882cc9cea","resolution":{"observed_at":"2026-08-02T05:17:36.129090Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:36.296704Z","title":"Victoria, and Guorui Zhou","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:36.296704Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:3b33acdbf4d67feeba7e562c7bc129e2f79f7fdac67020e4669d4841ba602aa8","observation_id":"58721067-5fd4-42a4-bd3f-34e21cfafc5f","resolution":{"observed_at":"2026-08-02T05:17:36.296704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:36.425541Z","title":"Aditya Prakash, and Chao Zhang","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:36.425541Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:9fa01c0b24f7af5120e8e874a7641789b7ba4ac7badf647e40579aa807ee7a19","observation_id":"cf47a84f-b6d8-43df-87b9-fc2d7b5a459a","resolution":{"observed_at":"2026-08-02T05:17:36.425541Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:36.621406Z","title":"Fairwire: Fair graph generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:36.621406Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:0923e431e1eff374ba238a0b61fa6c3f1244d39bb7d7ab133687b524545e6749","observation_id":"85daa80d-a464-4209-a85e-b68a55331050","resolution":{"observed_at":"2026-08-02T05:17:36.621406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:36.750230Z","title":"Tabddpm: Modelling tabular data with diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:36.750230Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:2fe5ed22cd6418366b9040fbbc843253dec8ee02ec6efe6a6744c888b9e911ef","observation_id":"f56ee9da-5872-4c73-abe4-f1eb068252a5","resolution":{"observed_at":"2026-08-02T05:17:36.750230Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:36.883140Z","title":"Feedback guidance of diffusion models.ArXiv preprint, abs/2506.06085,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":102,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:36.883140Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:9738a0d26643a3120e00cbb388dfa5ea7a4adabb75520df16732b18bf0f9adcb","observation_id":"066f80c3-31c5-405d-882a-6dd010226c33","resolution":{"observed_at":"2026-08-02T05:17:36.883140Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01416","last_updated":"2025-08-16T08:29:31Z","snapshot_observed_at":"2026-08-05T09:31:51.561049Z","submitted_at":"2025-02-03T14:55:28Z","title":"Categorical Schr\\\"odinger Bridge Matching","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01416","snapshot_observed_at":"2026-08-02T05:17:37.019763Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:37.019763Z"},"links":{"cited_paper":"/paper/2502.01416","citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:6bcb4e73059c9c3b7dc9196b85c4e007c20426805c2d0d5f379764bb82a24963","observation_id":"aeee64a9-8342-4fc7-bfca-7bdd77685fa7","resolution":{"observed_at":"2026-08-02T05:17:37.019763Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:37.152519Z","title":"Lad: Lora-adapted diffusion","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":104,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:37.152519Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:77c91523b9a6d5b0c5e1e4f283773afefb787c9ec79118be1fcdf0262063bc60","observation_id":"589c4360-b8ca-4b1a-b40d-0c90ceef907c","resolution":{"observed_at":"2026-08-02T05:17:37.152519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:37.280041Z","title":"EdiText: Controllable coarse-to-fine text editing with diffusion language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":105,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:37.280041Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:04793ee5e5a0d285c8d045dfdb145dce58109d2cc553b7374b8f34dd3e89286b","observation_id":"560d5cee-3394-4688-a127-c3c9311cbbef","resolution":{"observed_at":"2026-08-02T05:17:37.280041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:37.395813Z","title":"Fragfm: Efficient fragment-based molecular generation via discrete flow matching.ArXiv preprint, abs/2502.15805, 2025b","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":106,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:37.395813Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:559dde136fb1162254dc5440c64197e9d4cd3906b886c1f44b27671d0b311aa4","observation_id":"f06f7996-5b9f-4cb8-b0a1-d45285778812","resolution":{"observed_at":"2026-08-02T05:17:37.395813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:37.561961Z","title":"DLT: conditioned layout generation with joint discrete-continuous diffusion layout transformer","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":107,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:37.561961Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:7db85d640e6e1f618ffcbf17bb93b22e82b63016f930be1d079d340a27ac7680","observation_id":"3dfcfebd-b66c-4856-a707-b40c4d3f47c8","resolution":{"observed_at":"2026-08-02T05:17:37.561961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T05:17:37.697168Z","title":"Improved masked image generation with token-critic","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation","version":1},"reference_index":108,"source":"pdf_text","source_observed_at":"2026-08-02T05:17:37.697168Z"},"links":{"citing_paper":"/paper/2607.13431"},"observation_digest":"sha256:0d64aff8bab9286eafd84b4fc49611db6f83c488df4391b7dd62d1394f0df020","observation_id":"6b68693e-3e63-44ec-8795-dc49056e74ab","resolution":{"observed_at":"2026-08-02T05:17:37.697168Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.13431","last_updated":"2026-07-15T04:23:22Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T04:46:55.163964Z","submitted_at":"2026-07-15T04:23:22Z","title":"Discrete Diffusion Models: A Unified Framework from Tokenization to Generation"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":100,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":212},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 100 of 212 outbound references and 0 inbound Pith citation observations for arXiv:2607.13431."}