{"as_of":"2026-08-14T15:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:322ffdf0b429350d3243d51651e3659dab15377b5e625141a2735cce8c379d60","coverage":[{"denominator":84,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":84,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:52:33.541150Z","state":"measured"},{"denominator":154,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":154,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":70,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":70,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:06:07.719627Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","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":"2026-08-06T17:06:07.719627Z","title":"Diffucoder: Understanding and improving masked diffusion models for code generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.11851","last_updated":"2025-07-16T02:31:40Z","snapshot_observed_at":"2026-08-13T01:40:25.997863Z","submitted_at":"2025-07-16T02:31:40Z","title":"Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-06T17:06:07.719627Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2507.11851"},"observation_digest":"sha256:2782f74efc332ebcf245c44065f26cef1044eceb9d3f8f07ca0ec2dfd0c91157","observation_id":"3fc2d063-21c9-4eb7-89b0-9d35c9bc826a","resolution":{"observed_at":"2026-08-06T17:06:07.719627Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-05T20:15:19.968135Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.10875","last_updated":"2026-06-04T15:16:30Z","snapshot_observed_at":"2026-08-05T20:14:58.845639Z","submitted_at":"2025-08-14T17:47:22Z","title":"A Survey on Diffusion Language Models","version":3},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-05T20:15:19.968135Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2508.10875"},"observation_digest":"sha256:64fa8f1985295bad0d9335e0cb70bd83a4a3c5afcf950d7c64f72d3cbfbb2b20","observation_id":"b0bd7c05-de1a-4e61-bbfa-52bd2106b039","resolution":{"observed_at":"2026-08-05T20:15:19.968135Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-05T14:42:22.236761Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.21016","last_updated":"2025-08-28T17:18:31Z","snapshot_observed_at":"2026-08-06T03:08:28.577840Z","submitted_at":"2025-08-28T17:18:31Z","title":"Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-05T14:42:22.236761Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2508.21016"},"observation_digest":"sha256:31e1b1d21be7dca04a0cbe094b545a13c1f64890e40c5f510bb4e993434d2b75","observation_id":"221f89fb-3a73-4331-9671-19a81ecf03de","resolution":{"observed_at":"2026-08-05T14:42:22.236761Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-05T13:20:05.358512Z","title":"Diffucoder: Understanding and improving masked diffusion models for code generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.01025","last_updated":"2025-09-07T22:48:13Z","snapshot_observed_at":"2026-08-06T04:06:34.224683Z","submitted_at":"2025-08-31T23:34:53Z","title":"Any-Order Flexible Length Masked Diffusion","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-05T13:20:05.358512Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2509.01025"},"observation_digest":"sha256:309c341bf2b9d45663359d12d31bf97dabf9aadd0729bb49506baa9f9265ad01","observation_id":"514da1a9-d2c9-43f6-b49f-a2d77aa6dce7","resolution":{"observed_at":"2026-08-05T13:20:05.358512Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-05T12:56:35.061994Z","title":"Diffucoder: Understanding and improving masked diffusion models for code generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.01142","last_updated":"2025-09-01T05:30:56Z","snapshot_observed_at":"2026-08-14T02:47:52.528567Z","submitted_at":"2025-09-01T05:30:56Z","title":"Dream-Coder 7B: An Open Diffusion Language Model for Code","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-05T12:56:35.061994Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2509.01142"},"observation_digest":"sha256:d3d95e5f857d808adfa7d1d2acff49d1a355c5e86d49578ff74b8a0255ff1f14","observation_id":"e4990451-0ad1-4c34-9ff2-737558872ee0","resolution":{"observed_at":"2026-08-05T12:56:35.061994Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-05T10:24:24.035220Z","title":"Diffucoder: Understanding and improving masked diffusion models for code generation, 2025.https://arxiv.org/ abs/2506.20639","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.04185","last_updated":"2025-09-04T13:02:39Z","snapshot_observed_at":"2026-08-08T01:49:11.121908Z","submitted_at":"2025-09-04T13:02:39Z","title":"Set Block Decoding is a Language Model Inference Accelerator","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T10:24:24.035220Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2509.04185"},"observation_digest":"sha256:5f4f31c547dbe4ca20ae92ae08f19f3a8e7863a094d062e56a94440d573205fd","observation_id":"2b0407d5-340d-4d8e-9261-46b063a6af7b","resolution":{"observed_at":"2026-08-05T10:24:24.035220Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-04T22:56:05.150719Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.06949","last_updated":"2025-09-08T17:58:06Z","snapshot_observed_at":"2026-08-13T09:48:36.853401Z","submitted_at":"2025-09-08T17:58:06Z","title":"Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-04T22:56:05.150719Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2509.06949"},"observation_digest":"sha256:def118d46a19906aee9cf0ac74fcbcadf4235ebdc41545eedc42abfa360f4894","observation_id":"c30401bf-c138-45b5-9c2b-ee98055d6589","resolution":{"observed_at":"2026-08-04T22:56:05.150719Z","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":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2509.08827","last_updated":"2025-10-09T17:08:52Z","snapshot_observed_at":"2026-08-06T15:38:05.011922Z","submitted_at":"2025-09-10T17:59:43Z","title":"A Survey of Reinforcement Learning for Large Reasoning Models","version":3},"reference_index":164,"source":"arxiv_source","source_observed_at":"2026-05-18T00:02:24.352947Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2509.08827"},"observation_digest":"sha256:aa25e7597fa7d0f399c10f7029026532e0ae9313fd56a25a5ce06d75c82f66e7","observation_id":"5a4f0adf-1bda-4917-b276-6b600e13663f","resolution":{"observed_at":"2026-05-18T00:02:25.467341Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","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":"2026-08-04T17:57:46.961329Z","title":"Diffucoder: Understanding and improving masked diffusion models for code generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10396","last_updated":"2025-09-12T16:44:31Z","snapshot_observed_at":"2026-08-12T01:25:18.465764Z","submitted_at":"2025-09-12T16:44:31Z","title":"Inpainting-Guided Policy Optimization for Diffusion Large Language Models","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T17:57:46.961329Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2509.10396"},"observation_digest":"sha256:cb0cc9b5023b5d3a82b2c8b97022b62b56d8a023884763e98e5ef012e1a3ad35","observation_id":"0162aa2f-a1d6-4908-9afa-cd944c5e0b61","resolution":{"observed_at":"2026-08-04T17:57:46.961329Z","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":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2509.20624","last_updated":"2026-04-11T00:36:13Z","snapshot_observed_at":"2026-07-06T22:30:41.141182Z","submitted_at":"2025-09-24T23:59:05Z","title":"FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models","version":5},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-18T13:35:43.365164Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2509.20624"},"observation_digest":"sha256:16fe72918ba45715d473033cf8843b4f4083bca134f4e57b11f9b3307454066a","observation_id":"beffa496-133e-4054-8e73-820fa20aec50","resolution":{"observed_at":"2026-05-18T13:36:24.909123Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","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":"2026-08-04T13:15:31.707050Z","title":"Diffucoder: Understanding and improving masked diffusion models for code gen- eration.arXiv preprint arXiv:2506.20639,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.01384","last_updated":"2026-05-22T19:48:31Z","snapshot_observed_at":"2026-08-09T16:34:10.718069Z","submitted_at":"2025-10-01T19:15:25Z","title":"Fine-Tuning Masked Diffusion for Provable Self-Correction","version":4},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-04T13:15:31.707050Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2510.01384"},"observation_digest":"sha256:d6e4942cfddfbb659a3388a103750478eba58a457988ab7323f891f3cdb866e0","observation_id":"017ff2ae-bc7b-43e6-9d51-2f6cfa799953","resolution":{"observed_at":"2026-08-04T13:15:31.707050Z","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":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2510.03206","last_updated":"2026-05-12T17:53:41Z","snapshot_observed_at":"2026-08-12T12:26:44.786730Z","submitted_at":"2025-10-03T17:44:41Z","title":"Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-18T10:15:10.746336Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2510.03206"},"observation_digest":"sha256:9f6db91ed443749e3239d20b23c77a5166f7eb7d435173ab064da1d31c077903","observation_id":"9e49b96e-8959-4739-99cb-49ff062aafe7","resolution":{"observed_at":"2026-05-18T10:16:14.114595Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","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":"2026-08-04T11:28:09.593678Z","title":"Diffucoder: Understanding and improving masked diffusion models for code gen- eration.arXiv preprint arXiv:2506.20639,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.04767","last_updated":"2026-06-23T05:37:09Z","snapshot_observed_at":"2026-08-14T05:07:06.472323Z","submitted_at":"2025-10-06T12:41:31Z","title":"ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-04T11:28:09.593678Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2510.04767"},"observation_digest":"sha256:29d401f0807ed565d1a5b843be99582204cb478653bd79e4a4f8b09e86731332","observation_id":"e03e251a-12ef-4eae-b18b-6a2c41a8a34b","resolution":{"observed_at":"2026-08-04T11:28:09.593678Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-04T10:56:36.658022Z","title":"Carles Domingo-Enrich, Michal Drozdzal, Brian Karrer, and Ricky T","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.08233","last_updated":"2026-07-12T05:47:08Z","snapshot_observed_at":"2026-08-09T09:48:38.822024Z","submitted_at":"2025-10-09T13:59:50Z","title":"Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization","version":3},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:36.658022Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2510.08233"},"observation_digest":"sha256:1c3a3a644e35aa4594bf28c5c4c6724e7d57deed4c4a1262784aa172b7e1ac1d","observation_id":"7b1cadbe-872b-4225-999f-b31939406525","resolution":{"observed_at":"2026-08-04T10:56:36.658022Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-04T10:10:07.008967Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.11683","last_updated":"2026-05-29T17:51:48Z","snapshot_observed_at":"2026-08-14T01:51:20.020970Z","submitted_at":"2025-10-13T17:47:50Z","title":"Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T10:10:07.008967Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2510.11683"},"observation_digest":"sha256:1f299f6c72c1435c5b24758301011beeb5773aa8d866f55d7fb33f9fc102ab20","observation_id":"219c33d0-6259-495e-a86f-3250938fab81","resolution":{"observed_at":"2026-08-04T10:10:07.008967Z","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":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2510.18165","last_updated":"2026-04-29T02:39:52Z","snapshot_observed_at":"2026-08-03T23:37:43.649187Z","submitted_at":"2025-10-20T23:38:12Z","title":"Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-18T05:32:13.409022Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2510.18165"},"observation_digest":"sha256:732efc55cd71722bbef29b12bf85cbfba6a0dbb7ad56ba673eda6655bc57bf05","observation_id":"1692b1fb-c5e3-417c-b459-488f0dbbe7a7","resolution":{"observed_at":"2026-05-18T05:32:25.277283Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2511.18801","last_updated":"2026-07-30T14:58:39Z","snapshot_observed_at":"2026-08-03T20:41:14.428059Z","submitted_at":"2025-11-24T06:11:21Z","title":"PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-21T18:37:14.113436Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2511.18801"},"observation_digest":"sha256:e7c08738eaf7016b62b5fe151a4c8bbb31a44c0879ccfa0b39e9f9124702d9c3","observation_id":"f7ec7ae9-497b-4031-990b-e58be4e42996","resolution":{"observed_at":"2026-05-21T18:40:29.075008Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","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":"2026-08-03T20:41:15.928161Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.18801","last_updated":"2026-07-30T14:58:39Z","snapshot_observed_at":"2026-08-03T20:41:14.428059Z","submitted_at":"2025-11-24T06:11:21Z","title":"PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T20:41:15.928161Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2511.18801"},"observation_digest":"sha256:c1cf547b5d3a998f7a947fa6c10f3a683edb20b66c1273a7a4ddf45a9159d725","observation_id":"3be0d842-2301-4d18-8b46-e060c2fc3730","resolution":{"observed_at":"2026-08-03T20:41:15.928161Z","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":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2512.14067","last_updated":"2026-04-29T20:52:08Z","snapshot_observed_at":"2026-08-13T02:27:38.752907Z","submitted_at":"2025-12-16T04:12:17Z","title":"Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-16T22:29:08.669964Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2512.14067"},"observation_digest":"sha256:d98fed441c3c01a345671d82ab844bcf2c0eef69821b9bb5a1e392b27d3e8168","observation_id":"617adb40-3f13-4ff0-98f5-2d6e369c3193","resolution":{"observed_at":"2026-05-16T22:31:19.362914Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","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":"2026-08-03T10:09:22.801810Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.11214","last_updated":"2026-06-03T10:02:48Z","snapshot_observed_at":"2026-08-13T10:28:09.308949Z","submitted_at":"2026-01-16T11:44:12Z","title":"T$^\\star$: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning","version":5},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-03T10:09:22.801810Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2601.11214"},"observation_digest":"sha256:332dd19bd3b0dd6c98fe4f32ee20e4d8961464e109fa71d7437e78ef09f9b22d","observation_id":"d7e21525-dc05-407e-a031-dcb667a7f54b","resolution":{"observed_at":"2026-08-03T10:09:22.801810Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-03T09:03:17.926031Z","title":"Diffucoder: Understanding and improving masked diffusion models for code generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.15165","last_updated":"2026-06-08T15:43:52Z","snapshot_observed_at":"2026-08-08T11:50:23.271252Z","submitted_at":"2026-01-21T16:41:58Z","title":"The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models","version":4},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-03T09:03:17.926031Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2601.15165"},"observation_digest":"sha256:fdb9521a1b7be378c898ffff4e51b81216cc0a0b606e3c24dba2d6cea13b3393","observation_id":"e3f2b1e0-da3d-4df8-807a-16cb98d815c0","resolution":{"observed_at":"2026-08-03T09:03:17.926031Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-03T04:44:07.514075Z","title":"Diffucoder: Understanding and improving masked diffusion models for code generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.04344","last_updated":"2026-07-20T14:58:37Z","snapshot_observed_at":"2026-08-09T23:56:27.703002Z","submitted_at":"2026-02-04T09:13:08Z","title":"UnMaskFork: Test-Time Scaling for Masked Diffusion via Deterministic Action Branching","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-03T04:44:07.514075Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2602.04344"},"observation_digest":"sha256:339398db2fa505850ce41563794db6120312cd9acc597b0b0eceb21c51f003a9","observation_id":"0881c3cf-7621-424b-8d2b-895dc7cfeeb6","resolution":{"observed_at":"2026-08-03T04:44:07.514075Z","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":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2602.06462","last_updated":"2026-05-19T02:44:29Z","snapshot_observed_at":"2026-08-13T16:20:38.237823Z","submitted_at":"2026-02-06T07:47:22Z","title":"Diffusion-State Policy Optimization for Masked Diffusion Language Models","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-16T07:17:56.797506Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2602.06462"},"observation_digest":"sha256:02f1ae63ba4bace50a7957f7a7acb0d897f00da3212d3498289c2687037cf75e","observation_id":"e19f6644-342f-42a9-bdb8-c009f0d7ea48","resolution":{"observed_at":"2026-05-16T07:20:43.904797Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2602.06462","last_updated":"2026-05-19T02:44:29Z","snapshot_observed_at":"2026-08-13T16:20:38.237823Z","submitted_at":"2026-02-06T07:47:22Z","title":"Diffusion-State Policy Optimization for Masked Diffusion Language Models","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-21T14:39:44.391920Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2602.06462"},"observation_digest":"sha256:07f1d264f4d993566520c77e973745b8e80e94a498198b3845642ff19681a43e","observation_id":"075c6df8-e80c-4935-ba58-53e14dcc2620","resolution":{"observed_at":"2026-05-21T14:40:14.344829Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","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":"2026-08-03T00:05:25.346266Z","title":"Gong, S., Zhang, R., Zheng, H., Gu, J., Jaitly, N., Kong, L., and Zhang, Y","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.11715","last_updated":"2026-06-16T06:09:33Z","snapshot_observed_at":"2026-08-06T17:55:54.375326Z","submitted_at":"2026-02-12T08:45:13Z","title":"DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T00:05:25.346266Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2602.11715"},"observation_digest":"sha256:05bc4ece9c34fdda287ad06712306c85b68a220eaa43fd74e7648ec373bc06c4","observation_id":"7645492c-b747-4fc7-a406-05a27be87c8a","resolution":{"observed_at":"2026-08-03T00:05:25.346266Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-02T23:50:33.939670Z","title":"Diffucoder: Understanding and improving masked diffusion models for code generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.12586","last_updated":"2026-05-27T16:01:59Z","snapshot_observed_at":"2026-08-08T22:46:16.097170Z","submitted_at":"2026-02-13T03:56:22Z","title":"Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-02T23:50:33.939670Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2602.12586"},"observation_digest":"sha256:c295f4e88905f9037f99f0bd1e5dad51df5d1951de7bd2d80f26f2c11e56c178","observation_id":"25bab7dd-04e8-481d-810f-ac3cc2f2310d","resolution":{"observed_at":"2026-08-02T23:50:33.939670Z","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":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2603.07475","last_updated":"2026-08-02T20:40:52Z","snapshot_observed_at":"2026-08-06T23:24:21.844380Z","submitted_at":"2026-03-08T05:31:52Z","title":"A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-15T15:03:23.792608Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2603.07475"},"observation_digest":"sha256:33e50c3306fbf5673c2bc98ad206c15a60c9cc1f454b0704306f7568e5b1862b","observation_id":"9f938b7c-3a01-4a52-9f10-eeef2a24379d","resolution":{"observed_at":"2026-05-15T15:06:10.094918Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","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":"2026-08-04T05:57:07.958994Z","title":"Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.07475","last_updated":"2026-08-02T20:40:52Z","snapshot_observed_at":"2026-08-06T23:24:21.844380Z","submitted_at":"2026-03-08T05:31:52Z","title":"A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs","version":4},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-04T05:57:07.958994Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2603.07475"},"observation_digest":"sha256:dd75841621ef57b4b1d0c859075df37fa32be94ce33c83d5b61c3ee13d4c2b4b","observation_id":"0160b08a-2cd8-42e5-a2bf-0128f7487d66","resolution":{"observed_at":"2026-08-04T05:57:07.958994Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-03T02:38:06.994951Z","title":"Gulrajani, I","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-10T17:58:56.026827Z","submitted_at":"2026-03-04T11:43:19Z","title":"LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:06.994951Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:c708118b7335979d1eb2c239bc973212bbe6fe4d3861210187401c6071d33841","observation_id":"63497513-2a0f-4229-b29f-efd07cf2549e","resolution":{"observed_at":"2026-08-03T02:38:06.994951Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-07-13T18:04:43.103159Z","title":"Diffucoder: Understanding and improving masked diffusion models for code generation.arXiv preprint arXiv:2506.20639,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.25702","last_updated":"2026-06-17T19:47:34Z","snapshot_observed_at":"2026-08-14T02:45:10.761706Z","submitted_at":"2026-03-26T17:48:50Z","title":"S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-13T18:04:43.103159Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2603.25702"},"observation_digest":"sha256:a9bd88b59f0f38a4f4c41829a623119b29fc971eef4c85dc80b9c410752d795c","observation_id":"d51c7a66-1170-4051-a65d-19dcee1f0a86","resolution":{"observed_at":"2026-07-13T18:04:43.103159Z","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":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2604.02340","last_updated":"2026-04-11T10:21:32Z","snapshot_observed_at":"2026-08-11T13:36:37.294844Z","submitted_at":"2026-02-04T13:04:58Z","title":"Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-16T07:43:45.415485Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2604.02340"},"observation_digest":"sha256:416056903c27ccd125adea29818b72a621dfdeb87fb3dacc9287f49b3c23109c","observation_id":"f7618b32-54b3-462c-94d3-eb7feaaec0d7","resolution":{"observed_at":"2026-05-16T07:47:33.037258Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2604.08302","last_updated":"2026-05-15T04:19:14Z","snapshot_observed_at":"2026-08-12T18:40:27.785502Z","submitted_at":"2026-04-09T14:35:42Z","title":"DMax: Aggressive Parallel Decoding for dLLMs","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-10T17:58:17.880199Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2604.08302"},"observation_digest":"sha256:3a279308398b47d38a5c86ef5814b25141512a04b00896d6a8ea6e7f5cb12de8","observation_id":"38c8914c-a52f-440e-8a59-ec4e9ec19a88","resolution":{"observed_at":"2026-05-11T05:45:55.980021Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2604.08302","last_updated":"2026-05-15T04:19:14Z","snapshot_observed_at":"2026-08-12T18:40:27.785502Z","submitted_at":"2026-04-09T14:35:42Z","title":"DMax: Aggressive Parallel Decoding for dLLMs","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-19T16:46:56.743268Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2604.08302"},"observation_digest":"sha256:99c09dbc877fc77ee712d85d3d268523700940e4b3d124c7b5eed42042a56ea2","observation_id":"6c45b0c2-2c19-41da-b8fc-74005817c17d","resolution":{"observed_at":"2026-05-19T16:47:40.189153Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2604.13413","last_updated":"2026-04-15T02:31:31Z","snapshot_observed_at":"2026-08-11T13:26:01.255993Z","submitted_at":"2026-04-15T02:31:31Z","title":"Dataset-Level Metrics Attenuate Non-Determinism: A Fine-Grained Non-Determinism Evaluation in Diffusion Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T13:31:46.940449Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2604.13413"},"observation_digest":"sha256:cba0f6ffa004c430681a0a60613b95c5d58377c60831e30e8ddf66c682c92287","observation_id":"c7aa6ed4-c02b-46eb-b4de-21f9d937c096","resolution":{"observed_at":"2026-05-10T13:35:26.423954Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","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":"2026-07-12T20:50:53.567415Z","title":"Diffucoder: Understanding and improving masked diffusion models for code generation.arXiv preprint arXiv:2506.20639,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2604.13416","last_updated":"2026-07-06T05:33:02Z","snapshot_observed_at":"2026-08-02T11:35:00.658422Z","submitted_at":"2026-04-15T02:33:44Z","title":"DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-12T20:50:53.567415Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2604.13416"},"observation_digest":"sha256:6a1d2a19e5a88b70759731313dcc6254b761ae82f4400201aee4e3af29b388ae","observation_id":"24dff20c-7ca7-48b3-9a0a-0d14f782033e","resolution":{"observed_at":"2026-07-12T20:50:53.567415Z","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":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2604.17068","last_updated":"2026-04-18T17:04:10Z","snapshot_observed_at":"2026-08-13T07:57:55.536750Z","submitted_at":"2026-04-18T17:04:10Z","title":"Stability-Weighted Decoding for Diffusion Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T06:12:37.804816Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2604.17068"},"observation_digest":"sha256:3adf58affec66289222beea2f7f1db18bd46c77b964b3d7f060fdd26d9e652b8","observation_id":"58ea2630-a7b9-40af-83c6-9ae380efb600","resolution":{"observed_at":"2026-05-10T06:31:31.355025Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2604.18739","last_updated":"2026-05-19T01:39:31Z","snapshot_observed_at":"2026-08-13T01:33:42.615166Z","submitted_at":"2026-04-20T18:43:37Z","title":"Discrete Tilt Matching","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-05-10T04:31:08.195730Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2604.18739"},"observation_digest":"sha256:e181723fdbad48ae3439abbb695d0eaf247da89dbb2f610bffb68776b90ad638","observation_id":"d7764524-7db5-4011-a839-bea9ebc5f276","resolution":{"observed_at":"2026-05-11T11:51:04.127694Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2604.26985","last_updated":"2026-06-06T20:43:37Z","snapshot_observed_at":"2026-08-11T01:32:38.249839Z","submitted_at":"2026-04-28T19:34:04Z","title":"Simple Self-Conditioning Adaptation for Masked Diffusion Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-07T16:38:22.306140Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2604.26985"},"observation_digest":"sha256:70e9f4faff2215824cf20ded3797ebc39510188473a9ff81ee023459e38fdf30","observation_id":"90ae4c27-6b08-4d5b-9ce9-8cdfe7e97bef","resolution":{"observed_at":"2026-05-11T23:36:34.126996Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.08659","last_updated":"2026-05-19T08:15:11Z","snapshot_observed_at":"2026-08-11T13:28:34.514657Z","submitted_at":"2026-05-09T03:55:15Z","title":"Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-12T01:11:15.866440Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.08659"},"observation_digest":"sha256:6a49e3d96953dcc90e1b0de2eda9f7ae964381b0b8414c26863cc022f3c8195b","observation_id":"2529f573-1aad-4724-a874-574a704f4b48","resolution":{"observed_at":"2026-05-12T08:26:23.586659Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.08659","last_updated":"2026-05-19T08:15:11Z","snapshot_observed_at":"2026-08-11T13:28:34.514657Z","submitted_at":"2026-05-09T03:55:15Z","title":"Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-20T23:30:36.222968Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.08659"},"observation_digest":"sha256:577756ac63739d0c16ae79a1eac9c5d8588f8bb192092668c6e5ddbec1b54503","observation_id":"238f76db-ce4e-4e37-9156-a108055f4f2a","resolution":{"observed_at":"2026-05-20T23:33:50.998290Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.10518","last_updated":"2026-05-11T13:07:03Z","snapshot_observed_at":"2026-08-11T17:05:06.074087Z","submitted_at":"2026-05-11T13:07:03Z","title":"Infinite Mask Diffusion for Few-Step Distillation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-12T04:05:57.880725Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.10518"},"observation_digest":"sha256:b4be6f9a6e8c3baf7988cdda519022519b9a7815159c6d79784307a43449620d","observation_id":"ddc5fe59-19a2-4f1e-a479-4fdb3aa21c93","resolution":{"observed_at":"2026-05-12T06:36:28.236032Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.16342","last_updated":"2026-05-08T01:02:31Z","snapshot_observed_at":"2026-08-12T12:24:15.770320Z","submitted_at":"2026-05-08T01:02:31Z","title":"DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-05-20T22:53:48.008589Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.16342"},"observation_digest":"sha256:2d1edf5426c1db5c9dc879210c5346676dcbb5e6b5d800f50238368350f76a3a","observation_id":"cec11caf-92a9-43a9-9e0c-90c3161df71c","resolution":{"observed_at":"2026-05-20T22:54:09.817515Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.16829","last_updated":"2026-05-16T06:15:47Z","snapshot_observed_at":"2026-08-13T05:35:52.398905Z","submitted_at":"2026-05-16T06:15:47Z","title":"Constrained Code Generation with Discrete Diffusion","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-19T21:24:10.211816Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.16829"},"observation_digest":"sha256:e50b0b97de8c6e218211cbd0781c677ef34778f0d1ea200e980bd1390eb7ca65","observation_id":"939c2c32-ac32-4b56-9e4a-d3818825b68a","resolution":{"observed_at":"2026-05-19T21:27:47.889187Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.17174","last_updated":"2026-05-16T22:18:04Z","snapshot_observed_at":"2026-08-14T07:54:10.015225Z","submitted_at":"2026-05-16T22:18:04Z","title":"Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-20T14:03:45.869373Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.17174"},"observation_digest":"sha256:735bcf2ad3416b49334ab1fa524e24bdb60b8b2e4d91a0e4fb1005b63813f098","observation_id":"5e26651e-60f9-49bf-984c-2f0ea7e635c2","resolution":{"observed_at":"2026-05-20T14:08:21.285223Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.17842","last_updated":"2026-07-08T06:32:43Z","snapshot_observed_at":"2026-07-12T16:36:39.172164Z","submitted_at":"2026-05-18T04:28:16Z","title":"SNLP: Layer-Parallel Inference via Structured Newton Corrections","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-20T12:36:41.055552Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.17842"},"observation_digest":"sha256:0130cd7372ff34a1c14195c2a2e1acd856f881d7875217a25bf1025949687577","observation_id":"0b740989-a82e-4ef3-b76a-282c7c41de34","resolution":{"observed_at":"2026-05-20T12:38:16.795278Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.17842","last_updated":"2026-07-08T06:32:43Z","snapshot_observed_at":"2026-07-12T16:36:39.172164Z","submitted_at":"2026-05-18T04:28:16Z","title":"SNLP: Layer-Parallel Inference via Structured Newton Corrections","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-30T18:53:40.889001Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.17842"},"observation_digest":"sha256:6162aa4ec05f2f68b5dcc306e975623c83278b67e28b0e6d021b292a56449ace","observation_id":"ce483b1d-6593-41e1-81b1-6966073a435c","resolution":{"observed_at":"2026-06-30T18:55:00.157099Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.25638","last_updated":"2026-06-05T03:07:08Z","snapshot_observed_at":"2026-07-06T23:35:36.158984Z","submitted_at":"2026-05-25T09:39:13Z","title":"Reinforcement Learning from Denoising Feedback","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T21:20:32.039699Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.25638"},"observation_digest":"sha256:5e277ac7470cb8fd03764ac70909b490cff46f4e1cd2b6f8bd4b6d846aeb663d","observation_id":"d7db372a-2ab4-44fa-8a20-7d10cf9089fd","resolution":{"observed_at":"2026-06-29T21:23:58.920191Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.29123","last_updated":"2026-05-27T21:33:37Z","snapshot_observed_at":"2026-08-13T01:15:23.981477Z","submitted_at":"2026-05-27T21:33:37Z","title":"The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T11:43:27.577980Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.29123"},"observation_digest":"sha256:6450d3f3092f3580e5c61a6376d19f59d38f27b4194cac3002f97d1dd7d1be32","observation_id":"11c48055-25b6-4d3f-945b-faac05859e13","resolution":{"observed_at":"2026-06-29T12:13:27.370526Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.29398","last_updated":"2026-05-28T05:47:40Z","snapshot_observed_at":"2026-07-06T23:38:51.349968Z","submitted_at":"2026-05-28T05:47:40Z","title":"GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-29T08:44:53.969301Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.29398"},"observation_digest":"sha256:ca71ffee1cd0210cb7cac1e2fe33da6a68d4a9a2b79559c33b5634c2e3fca8f2","observation_id":"c3004e32-4a08-4461-99f2-30a01c9966ca","resolution":{"observed_at":"2026-06-29T08:53:16.296177Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.30553","last_updated":"2026-05-28T20:35:16Z","snapshot_observed_at":"2026-08-06T17:29:17.741581Z","submitted_at":"2026-05-28T20:35:16Z","title":"Destruction is a General Strategy to Learn Generation; Diffusion's Strength is to Take it Seriously; Exploration is the Future","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-29T08:48:10.444113Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.30553"},"observation_digest":"sha256:12052840f0f6421becdd2d64e7e4845245101ccfabb4e7d448ca460374bb4915","observation_id":"7bb60e64-6ab6-49a8-bfb0-ab18c450b356","resolution":{"observed_at":"2026-06-29T08:53:16.012929Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2605.30876","last_updated":"2026-06-20T08:46:49Z","snapshot_observed_at":"2026-08-03T23:34:59.657375Z","submitted_at":"2026-05-29T06:03:50Z","title":"dMoE: dLLMs with Learnable Block Experts","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-06-28T22:50:51.900169Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2605.30876"},"observation_digest":"sha256:e410e27a4476e97d7b6d9da053d3dbf953026488356f103b1a747e77c339c0e8","observation_id":"8f1b375b-00ca-4521-9b9a-889899d0de85","resolution":{"observed_at":"2026-06-28T22:52:45.144554Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2606.00724","last_updated":"2026-05-30T13:32:26Z","snapshot_observed_at":"2026-08-13T12:51:37.389110Z","submitted_at":"2026-05-30T13:32:26Z","title":"WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filtering","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-06-28T18:57:54.491506Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2606.00724"},"observation_digest":"sha256:6d3cb72a31b4cecfd53e75281058cd9b5a0206957d7bcc71a0f7f4d8ed71120d","observation_id":"a8d63bc0-4713-4e57-ad6e-ee66eba88d3f","resolution":{"observed_at":"2026-06-28T19:02:33.530600Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2606.04027","last_updated":"2026-06-01T18:10:21Z","snapshot_observed_at":"2026-08-14T02:58:22.489089Z","submitted_at":"2026-06-01T18:10:21Z","title":"MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-28T13:43:51.171443Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2606.04027"},"observation_digest":"sha256:e2229a6001289e5771509fe0d52c16e435fac9765e65050a4d7ae9d8c3a904ac","observation_id":"f8fa62d9-6698-4114-998b-c16b5ee64a76","resolution":{"observed_at":"2026-07-01T23:56:24.411128Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2606.04535","last_updated":"2026-06-03T07:18:23Z","snapshot_observed_at":"2026-07-06T23:44:37.797802Z","submitted_at":"2026-06-03T07:18:23Z","title":"Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-06-28T06:20:27.041099Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2606.04535"},"observation_digest":"sha256:ca28a70efdb2cf8c17c9af956684e7ca4dbbe5f113202701b2be0b5aab5ad355","observation_id":"72a33a4b-f832-4c15-b5d6-f2c903efd0fa","resolution":{"observed_at":"2026-07-02T08:06:48.400710Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2606.06031","last_updated":"2026-06-04T11:24:47Z","snapshot_observed_at":"2026-07-06T23:45:56.266116Z","submitted_at":"2026-06-04T11:24:47Z","title":"NAVIRA: Decoupled Stochastic Remasking for Masked Diffusion Language Models","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-06-28T01:43:38.252406Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2606.06031"},"observation_digest":"sha256:69fdffb8f04f0757e8b37307b42a4d1ac99ba2e45b5e56f03365d52b7f7a723a","observation_id":"8ecc9a3a-8629-4cb3-ac93-ecfa3dd15024","resolution":{"observed_at":"2026-06-28T01:51:29.207203Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2606.08501","last_updated":"2026-06-07T07:59:55Z","snapshot_observed_at":"2026-07-06T23:47:57.376596Z","submitted_at":"2026-06-07T07:59:55Z","title":"Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-06-27T18:31:21.493677Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2606.08501"},"observation_digest":"sha256:8e1da972980dc90a8f8b8f4f2b5d2b712cfc18a2201a4967d9f74c4a786bc60a","observation_id":"9f10043a-2bb9-4931-9a40-e85ef29c0f0a","resolution":{"observed_at":"2026-07-02T22:57:26.560262Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2606.12273","last_updated":"2026-06-10T16:14:23Z","snapshot_observed_at":"2026-08-12T12:25:57.043879Z","submitted_at":"2026-06-10T16:14:23Z","title":"Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-06-27T09:34:02.484344Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2606.12273"},"observation_digest":"sha256:a9d0c768ac1ba125415d36de7d24c8ff7b4431f0720addcbcf998cb23e3fb1be","observation_id":"a1fff427-e6cf-491a-b9ec-2fa8115ca9d5","resolution":{"observed_at":"2026-07-03T11:28:04.437246Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2606.18195","last_updated":"2026-06-25T16:08:43Z","snapshot_observed_at":"2026-07-06T23:53:40.698123Z","submitted_at":"2026-06-16T17:24:57Z","title":"Learning from the Self-future: On-policy Self-distillation for dLLMs","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-27T01:20:14.919054Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2606.18195"},"observation_digest":"sha256:52055987f2da14e7e9659f4b490f165762462a055af28113018469b4ea9af840","observation_id":"fb4f6fe9-af7b-4840-8670-39f8a12ba079","resolution":{"observed_at":"2026-07-03T20:28:55.619794Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2607.00208","last_updated":"2026-06-30T21:38:46Z","snapshot_observed_at":"2026-07-07T00:05:54.401681Z","submitted_at":"2026-06-30T21:38:46Z","title":"SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-02T19:05:59.651008Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2607.00208"},"observation_digest":"sha256:34d7323a5c8db814bfe44473a83c043ab37307cbced45e02979f36530187be92","observation_id":"95bcc3e0-7698-491d-bc9e-6b36e4e1361b","resolution":{"observed_at":"2026-07-02T19:07:17.223330Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","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":"2026-07-12T03:56:26.770729Z","title":"Diffucoder: Understanding and improving masked diffusion models for code generation, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03236","last_updated":"2026-07-03T11:45:21Z","snapshot_observed_at":"2026-08-13T00:18:22.569383Z","submitted_at":"2026-07-03T11:45:21Z","title":"TACG: Trajectory-Aware Commit Gating for Diffusion Language Model Decoding","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-12T03:56:26.770729Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2607.03236"},"observation_digest":"sha256:7c46712c168278f4b4a64be5e0d2c3f721e17552f112da0860b1f6f3373236b7","observation_id":"d2e5b1b3-0be4-4705-a441-4728d71b3c7d","resolution":{"observed_at":"2026-07-12T03:56:26.770729Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-07-11T13:03:39.236118Z","title":"arXiv preprint arXiv:2506.20639 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04819","last_updated":"2026-07-13T09:12:14Z","snapshot_observed_at":"2026-08-13T16:53:06.345450Z","submitted_at":"2026-07-06T08:51:22Z","title":"Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-07-11T13:03:39.236118Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2607.04819"},"observation_digest":"sha256:652e2ebdf33f6c0098ea5e62be9f7d975652ab9fbbe582f7adeb98d25cfb6925","observation_id":"e83a8e57-60fd-4b7b-86eb-64fa80541bc3","resolution":{"observed_at":"2026-07-11T13:03:39.236118Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-07-14T16:21:05.570023Z","title":"arXiv preprint arXiv:2506.20639 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04819","last_updated":"2026-07-13T09:12:14Z","snapshot_observed_at":"2026-08-13T16:53:06.345450Z","submitted_at":"2026-07-06T08:51:22Z","title":"Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers","version":2},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-07-14T16:21:05.570023Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2607.04819"},"observation_digest":"sha256:7daf07e18a4db463542180d3301d84f1a87bd9920fcfe03b9f4884172c1eb4b0","observation_id":"03c7ef51-da16-42ce-89cb-f26fa37712c6","resolution":{"observed_at":"2026-07-14T16:21:05.570023Z","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":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"cited_work":{"arxiv_id":"2506.20639","doi":"10.48550/arxiv.2506.20639","metadata_source":"pith","pith_arxiv_id":"2506.20639","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffu- coder: Understanding and improving masked diffusion mod- els for code generation.arXiv preprint arXiv:2506.20639","venue":"cs.CL","work_id":"174cb4e5-25ae-4cca-b4e2-405cbd5774ba","year":2025},"citing_paper":{"arxiv_id":"2607.05722","last_updated":"2026-07-07T01:09:54Z","snapshot_observed_at":"2026-08-06T13:45:31.949136Z","submitted_at":"2026-07-07T01:09:54Z","title":"Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-11T03:04:12.500342Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2607.05722"},"observation_digest":"sha256:7dd60f3135e3185b9e7af84f53f40ba34a0d29b60ec4932b70bae78a6af14607","observation_id":"6ce9c2c3-aacd-485d-acd7-144acb5d389d","resolution":{"observed_at":"2026-07-11T03:07:51.370846Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","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":"2026-08-07T01:50:04.940823Z","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:d0d56cf482ac53211e6e5ffdfd3ea0a02b94759cd7ec526848246a5dbeb173f6","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":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","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":"2026-08-02T14:50:11.366692Z","title":"Diffucoder: Understanding and improving masked diffusion models for code generation.arXiv preprint arXiv:2506.20639, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16204","last_updated":"2026-05-07T00:40:32Z","snapshot_observed_at":"2026-08-06T07:49:27.049032Z","submitted_at":"2026-05-07T00:40:32Z","title":"Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T14:50:11.366692Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2607.16204"},"observation_digest":"sha256:5fb783f4c3179f8cd4eb5bd3bdd3ed77dd335ec81e0b5528dc38161de3480b6c","observation_id":"e02d4c03-53ea-46d9-9c5f-124315a3a594","resolution":{"observed_at":"2026-08-02T14:50:11.366692Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-01T20:54:17.464045Z","title":"arXiv preprint arXiv:2506.20639 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.16528","last_updated":"2026-07-17T22:09:01Z","snapshot_observed_at":"2026-08-07T07:19:10.753414Z","submitted_at":"2026-07-17T22:09:01Z","title":"Hierarchical Domain Generalization","version":1},"reference_index":163,"source":"arxiv_source","source_observed_at":"2026-08-01T20:54:17.464045Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2607.16528"},"observation_digest":"sha256:22f807d37ce6f179a7a8ac5e00a50f89bcfc284fca8a7afcc31b374bdcc02665","observation_id":"4a7ff4ee-9cc4-49c0-8bdd-9b199bdd6f54","resolution":{"observed_at":"2026-08-01T20:54:17.464045Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-07-31T18:41:13.757351Z","title":"arXiv preprint arXiv:2506.20639 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24306","last_updated":"2026-07-27T11:49:50Z","snapshot_observed_at":"2026-08-01T20:26:52.504076Z","submitted_at":"2026-07-27T11:49:50Z","title":"Rethinking the Generation Order of Block Diffusion Language Models","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-07-31T18:41:13.757351Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2607.24306"},"observation_digest":"sha256:87e674ed07c2e2345f15860cfcb16d3b84d804e5952d737f7493954bdd04ba23","observation_id":"01931d61-0985-4037-acdd-543c2aa4af8a","resolution":{"observed_at":"2026-07-31T18:41:13.757351Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-01T14:25:34.991006Z","title":"arXiv preprint arXiv:2506.20639 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.26504","last_updated":"2026-08-09T19:34:25Z","snapshot_observed_at":"2026-08-14T06:58:43.954033Z","submitted_at":"2026-07-29T06:09:12Z","title":"From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-01T14:25:34.991006Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2607.26504"},"observation_digest":"sha256:d28a07c4016d00534bb72c22bc99578c396f46c8bed0c1a60b32d0d633ab55ae","observation_id":"33c79516-26e1-4ed0-94e9-6a4f8b6d6b5b","resolution":{"observed_at":"2026-08-01T14:25:34.991006Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-07-31T04:32:30.217492Z","title":"arXiv preprint arXiv:2506.20639 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28529","last_updated":"2026-07-30T17:02:12Z","snapshot_observed_at":"2026-08-11T04:50:37.368635Z","submitted_at":"2026-07-30T17:02:12Z","title":"CoGate: Confidence-Gated Co-Decoding for Secure Code Generation","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-07-31T04:32:30.217492Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2607.28529"},"observation_digest":"sha256:46291098904234a4eb7bf754dcd9c37fc6ad22660b33f2eccc466323475eecc6","observation_id":"cbfbfa29-65ab-4a66-978b-fe882089a4f9","resolution":{"observed_at":"2026-07-31T04:32:30.217492Z","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":"2026-08-14T01:37:07.461149Z","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":"2026-08-04T22:20:08.768240Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.01717","last_updated":"2026-08-03T05:28:37Z","snapshot_observed_at":"2026-08-13T18:43:27.150082Z","submitted_at":"2026-08-03T05:28:37Z","title":"Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T22:20:08.768240Z"},"links":{"cited_paper":"/paper/2506.20639","citing_paper":"/paper/2608.01717"},"observation_digest":"sha256:9e3e9784cf64f21496c42d5be8bc27a7d520269de57c9e4ef9014eaa10c502e2","observation_id":"4ad35dd3-0b95-467f-9b14-95345db8f117","resolution":{"observed_at":"2026-08-04T22:20:08.768240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.20639/citation-record","integrity":"/paper/2506.20639/integrity","json":"/paper/2506.20639/citation-record.json","paper":"/paper/2506.20639"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.15134","last_updated":"2025-05-21T05:39:11Z","snapshot_observed_at":"2026-08-13T03:09:24.809367Z","submitted_at":"2025-05-21T05:39:11Z","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.15134","snapshot_observed_at":"2026-08-06T22:52:33.288724Z","title":"The unreasonable effectiveness of entropy minimization in llm reasoning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.288724Z"},"links":{"cited_paper":"/paper/2505.15134","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:a1f4c717cf73fced6007109bd6c2351f03ba59797e55e0dbb25344ed9001e42d","observation_id":"35b4920e-d56c-441c-81db-4ba07203416a","resolution":{"observed_at":"2026-08-06T22:52:33.288724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14740","last_updated":"2024-02-26T18:26:25Z","snapshot_observed_at":"2026-08-09T14:30:33.899591Z","submitted_at":"2024-02-22T17:52:34Z","title":"Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.14740","snapshot_observed_at":"2026-08-06T22:52:33.293218Z","title":"Back to basics: Revisiting reinforce style optimization for learning from human feedback in llms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.293218Z"},"links":{"cited_paper":"/paper/2402.14740","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:7f683f7f852aa5ce7b0e801eaefe4ee2b7a676d06f0de7780e5e1a4b5301f4db","observation_id":"1a7c8bc8-64f7-43b7-8049-887ba289edd3","resolution":{"observed_at":"2026-08-06T22:52:33.293218Z","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":"2026-08-06T22:52:33.297086Z","title":"Polaris: A post-training recipe for scaling reinforcement learning on advanced reasoning models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.297086Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:52134c46444e0087229264a924659d94441cbaa7720997d1319bd84d8abff9e9","observation_id":"aecdd066-c2de-480c-8521-39710ecfa293","resolution":{"observed_at":"2026-08-06T22:52:33.297086Z","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":"2026-08-06T22:52:33.300613Z","title":"Block diffusion: Interpolating between autoregressive and diffusion language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.300613Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:f08f3fde06259387eb93ded6b7bd90aa6b6c8ea7e934b88e0e62db8e0aec9174","observation_id":"db42ccc0-7a3e-45d2-a676-876405df1bb0","resolution":{"observed_at":"2026-08-06T22:52:33.300613Z","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":"2026-08-06T22:52:33.304166Z","title":"Johnson, Jonathan Ho, Daniel Tarlow, and Rianne van den Berg","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.304166Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:c32c93b6bda76e3beee550294ccb00a747014ce2291870f5b3f3066d6c56aa94","observation_id":"bc8505a4-762c-4656-a3d0-7578fa208f87","resolution":{"observed_at":"2026-08-06T22:52:33.304166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.07732","last_updated":"2021-08-16T03:57:30Z","snapshot_observed_at":"2026-08-02T19:23:53.535075Z","submitted_at":"2021-08-16T03:57:30Z","title":"Program Synthesis with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07732","snapshot_observed_at":"2026-08-06T22:52:33.307636Z","title":"Program synthesis with large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.307636Z"},"links":{"cited_paper":"/paper/2108.07732","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:00e87a75eb8ae359def40f0ea97bb734502e3fe814236768225e5942dd0cfd27","observation_id":"95d22bea-d38d-49d6-91e4-f163730094c4","resolution":{"observed_at":"2026-08-06T22:52:33.307636Z","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":"2026-08-06T22:52:33.311386Z","title":"Llama-nemotron: Efficient reasoning models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.311386Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:8f11e5e274ac97eebbe50192511bdfb47115ad9750d52cba5842f576a0f08aee","observation_id":"e43b4bae-1179-43e7-b106-eafa3daed8b8","resolution":{"observed_at":"2026-08-06T22:52:33.311386Z","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":"2026-08-06T22:52:33.314147Z","title":"Training diffusion models with reinforcement learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.314147Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:b2550dc0cc3d2eb05e3a2644278800721d6d28e0395f0532cc12531229922dd2","observation_id":"c368e680-46ab-4aac-88c0-91e137cfbded","resolution":{"observed_at":"2026-08-06T22:52:33.314147Z","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":"2026-08-06T22:52:33.317241Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.317241Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:9cc7923c0022aafc3c328b9c8fda0918f7fbab04f99a51acae69c31678dc2f7c","observation_id":"943b9cfb-15b4-4cf3-952c-c4a21ecb73af","resolution":{"observed_at":"2026-08-06T22:52:33.317241Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-08-08T11:58:24.516369Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-06T22:52:33.320370Z","title":"Evaluating large language models trained on code","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.320370Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:6b51f57fa324e3db9a15c0dbb4d03722bbb599df188a7be32384bce519a22adc","observation_id":"22993bdf-2d4b-4974-9151-774c00f752e4","resolution":{"observed_at":"2026-08-06T22:52:33.320370Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.794958Z","title":null,"venue":null,"work_id":"a282b11e-3c4c-4aa2-ba99-6f3494843aac","year":2023},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.323542Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:44ecd5ebb72c60f972629d45ec008881e8ef95232a16bd279b7c1d110a01f982","observation_id":"342f4fc3-af26-4517-bd75-cb3d47f0ba3e","resolution":{"observed_at":"2026-08-06T22:52:34.797793Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-14T02:43:01.480086Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-06T22:52:33.326508Z","title":"Training verifiers to solve math word problems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.326508Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:4bcf5901cedccf1ec1ad1b6b4ad3d85b884ae81fa78810e6d8adb84bc9ed9b1c","observation_id":"90b71b4e-1f47-4617-a2d8-91aff242c4b8","resolution":{"observed_at":"2026-08-06T22:52:33.326508Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22617","last_updated":"2025-05-28T17:38:45Z","snapshot_observed_at":"2026-08-12T12:02:17.912725Z","submitted_at":"2025-05-28T17:38:45Z","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.22617","snapshot_observed_at":"2026-08-06T22:52:33.329691Z","title":"The entropy mechanism of reinforcement learning for reasoning language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.329691Z"},"links":{"cited_paper":"/paper/2505.22617","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:618a7783519795de49fe8d633158c20b99c449f7faa45b14e9a7b86b71059eb9","observation_id":"a82f1126-2343-42f4-9861-ee0dd95ad312","resolution":{"observed_at":"2026-08-06T22:52:33.329691Z","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":"2026-08-06T22:52:33.332868Z","title":"Gemini diffusion","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.332868Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:553601434d0af51ca447b4c9892eeb5343f8ee98116b1a0c245a7384937e10f9","observation_id":"65d7eb15-acb3-4dc9-9ab2-76968a7f49e8","resolution":{"observed_at":"2026-08-06T22:52:33.332868Z","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":"2026-08-06T22:52:33.335623Z","title":"D iffu S eq-v2: Bridging discrete and continuous text spaces for accelerated S eq2 S eq diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.335623Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:8d5907fe7dbe129cee42a66b2e68f4bafe2daa124e13374a5c52f8f370647c2f","observation_id":"d180f60a-efde-4ac2-a192-54c4c558b518","resolution":{"observed_at":"2026-08-06T22:52:33.335623Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.779461Z","title":"Diffuseq: Sequence to sequence text generation with diffusion models","venue":null,"work_id":"bd56b31e-1c5e-4786-8cc3-d4627539f1a3","year":2023},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.338577Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:ddf44f5deb6aa0b2c9ddd735a9fa7e20679c10fb249daf1ce61e9e26abfa6939","observation_id":"4953ae13-3f41-4590-9e9a-56df3d28527d","resolution":{"observed_at":"2026-08-06T22:52:34.782583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.770389Z","title":"Scaling diffusion language models via adaptation from autoregressive models","venue":null,"work_id":"82332612-989f-4dfb-b1c8-36d03a29b3a4","year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.341429Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:486b91d8a5a31e8e7de89454360287e0bff13b9a3c032ef06ebe34c189801ed4","observation_id":"f4c91171-2ca6-4a4d-bb9d-7d08a93b87ff","resolution":{"observed_at":"2026-08-06T22:52:34.773226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10781","last_updated":"2025-03-02T14:37:53Z","snapshot_observed_at":"2026-08-02T20:46:05.666977Z","submitted_at":"2024-10-14T17:50:28Z","title":"When Attention Sink Emerges in Language Models: An Empirical View","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10781","snapshot_observed_at":"2026-08-06T22:52:33.344510Z","title":"When attention sink emerges in language models: An empirical view","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.344510Z"},"links":{"cited_paper":"/paper/2410.10781","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:f8c65f30ab0a5db9f0273891b411f08059c51d7ad9ead744e955d810e05de262","observation_id":"349c6bd8-6914-43ae-8f08-df82f8e15abd","resolution":{"observed_at":"2026-08-06T22:52:33.344510Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-08-13T15:58:13.809876Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-06T22:52:33.347685Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.347685Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:00e364de437b8aa3d6c7e1c57062f77f021f9e2b5a66973d10af1528910a83e2","observation_id":"2c1fff0f-d1a1-47dd-bab4-7c82de6815f0","resolution":{"observed_at":"2026-08-06T22:52:33.347685Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.760950Z","title":"General principles of antithetic variates","venue":null,"work_id":"9cdf1514-df82-4189-909d-00eb0acba4c8","year":1956},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.350467Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:40b7ba75cd0c4579aa5c3b36758a7c5319a1f7df5b36f7512bb894411acb563d","observation_id":"83ecd04e-edea-41be-8424-c85991e71397","resolution":{"observed_at":"2026-08-06T22:52:34.764052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.751942Z","title":"A new monte carlo technique: antithetic variates","venue":null,"work_id":"454a0f3f-5908-4f22-b265-bd586207e0a3","year":1956},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.353338Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:cf56bd0768fa08c83260c8870e0297a957b9c9185e47619237366eafb6bb09f4","observation_id":"46984c64-d22f-475e-98b5-00f3ceb6a2aa","resolution":{"observed_at":"2026-08-06T22:52:34.754974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:33.356226Z","title":"SSD - LM : Semi-autoregressive simplex-based diffusion language model for text generation and modular control","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.356226Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:b0b57e1105bc8b05a15f68cf16c4a11095b4a5650401cf69dc8fcc034bfa1312","observation_id":"f37fd0fd-7dec-4715-a760-1ac361c8c057","resolution":{"observed_at":"2026-08-06T22:52:33.356226Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.742789Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":"1cd35326-77a5-4795-b0fa-661ae6b070d8","year":2020},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.358910Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:a006e882c76b0c68dba81a76dca06f205b5ea2cb2693117ec240941a72e1eb63","observation_id":"77b63564-c539-494c-958a-4e15c048b751","resolution":{"observed_at":"2026-08-06T22:52:34.745796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.733422Z","title":"Argmax flows and multinomial diffusion: Learning categorical distributions","venue":null,"work_id":"172be6b7-404c-48ee-9b2e-0af0385a2987","year":2021},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.361521Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:03519bdde2d655704a5489326f550342b36a4c2872fd4c30a010b510e6453a4b","observation_id":"8e7730d0-1cf3-4842-99fc-86300987cd1f","resolution":{"observed_at":"2026-08-06T22:52:34.736633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:33.364823Z","title":"Abdelfattah, Jae-sun Seo, Zhiru Zhang, and Udit Gupta","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.364823Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:c16b94ebcfd40d7b1056e3508640df815057b6ca7148538a98edae05d6e8d333","observation_id":"01f4f8b2-ac0b-41fb-8bb1-20ea026bc99a","resolution":{"observed_at":"2026-08-06T22:52:33.364823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.04905","last_updated":"2025-03-20T03:28:56Z","snapshot_observed_at":"2026-08-12T22:05:29.529733Z","submitted_at":"2024-11-07T17:47:25Z","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.04905","snapshot_observed_at":"2026-08-06T22:52:33.367701Z","title":"Opencoder: The open cookbook for top-tier code large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.367701Z"},"links":{"cited_paper":"/paper/2411.04905","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:5f4680b472d973e5890bee852ec71573bcfbcf76ddea9e3d9c81b785c3b625ea","observation_id":"dfd7f65e-d5ef-44aa-81d4-d2841c7e5952","resolution":{"observed_at":"2026-08-06T22:52:33.367701Z","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":"2026-08-06T22:52:33.370496Z","title":"Reinforcing the diffusion chain of lateral thought with diffusion language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.370496Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:3d2a3fea35b7a28e0ac8e7c3c1b52bbf29c120b30c2b119e0d82664ff79502ca","observation_id":"e9c52383-826d-42e8-836c-14c0c978da78","resolution":{"observed_at":"2026-08-06T22:52:33.370496Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12186","last_updated":"2024-11-12T13:24:25Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-09-18T17:57:57Z","title":"Qwen2.5-Coder Technical Report","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.12186","snapshot_observed_at":"2026-08-06T22:52:33.373077Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.373077Z"},"links":{"cited_paper":"/paper/2409.12186","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:c3d95c5b991e9f1f3daae73612bfe865f38bc992e9775094bb7d0e27459baaac","observation_id":"aa61b1f1-b68c-4c8c-8308-fe3e1e61e0ed","resolution":{"observed_at":"2026-08-06T22:52:33.373077Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.723865Z","title":"Mercury: Ultra-fast language models based on diffusion","venue":null,"work_id":"36302e32-40fb-4428-8040-8ec92a9befee","year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.375914Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:329bed21a294af31b9ece09de98e322b02ba76d71ec60a52ebebcf9578e96514","observation_id":"b87197d5-73d9-4246-89e8-b0125b67f252","resolution":{"observed_at":"2026-08-06T22:52:34.726726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.714159Z","title":"Buy 4 reinforce samples, get a baseline for free! DeepRLStructPred Workshop ICLR, 2019","venue":null,"work_id":"6e272c4b-6de4-485c-91e6-1b751853f035","year":2019},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.378943Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:6e1fa0f5577467f410733500f39600fb69ac12cb821c7ef29679a2b6bd732584","observation_id":"d984a48f-fe14-4d49-a2c2-c1caad56a6a8","resolution":{"observed_at":"2026-08-06T22:52:34.717742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.16839","last_updated":"2026-07-15T22:41:27Z","snapshot_observed_at":"2026-08-14T13:42:27.582012Z","submitted_at":"2025-05-22T16:07:12Z","title":"LaViDa: A Large Diffusion Language Model for Multimodal Understanding","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.16839","snapshot_observed_at":"2026-08-06T22:52:33.381401Z","title":"Lavida: A large diffusion language model for multimodal understanding","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.381401Z"},"links":{"cited_paper":"/paper/2505.16839","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:2ad37582b8c3bac452cc843880229f9b8c3f1dc2938810d9f634d1b6beaa854e","observation_id":"f2285d3e-0bc7-49d8-b305-5e4eb7a8fec6","resolution":{"observed_at":"2026-08-06T22:52:33.381401Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.705228Z","title":"Hashimoto","venue":null,"work_id":"c31bb692-1e59-4dde-9cd7-1699633998c7","year":2022},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.384328Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:29aa40d59aaa7df0e8bdede7a642b0562b57768cb652db32c74f2109082e5e28","observation_id":"ae8fc883-1c2e-4312-8073-448980397a3e","resolution":{"observed_at":"2026-08-06T22:52:34.708448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.695887Z","title":"Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation","venue":null,"work_id":"6a2a4926-cff9-4a1d-934a-29afa0094caa","year":2023},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.387043Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:b9f9a91f65f19612dcf0fcc8007214f3766e188b02a12ba4da686b12c1a5c8cc","observation_id":"41d95bfc-7167-4e85-9681-9cb8f0143687","resolution":{"observed_at":"2026-08-06T22:52:34.699134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.24864","last_updated":"2025-05-30T17:59:01Z","snapshot_observed_at":"2026-08-07T07:17:16.299213Z","submitted_at":"2025-05-30T17:59:01Z","title":"ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.24864","snapshot_observed_at":"2026-08-06T22:52:33.390202Z","title":"Prorl: Prolonged reinforcement learning expands reasoning boundaries in large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.390202Z"},"links":{"cited_paper":"/paper/2505.24864","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:b1aa9f22a7ba27352dc98ba7f8dc656ad010a30b5c3b74925a1a3b20c58a7900","observation_id":"f20fba18-42b1-4061-b4f8-a82e513065ec","resolution":{"observed_at":"2026-08-06T22:52:33.390202Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.686620Z","title":"dllm-cache: Accelerating diffusion large language models with adaptive caching, 2025 b","venue":null,"work_id":"d262e5ad-caf0-4f57-a9ff-7da2d46943c8","year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.393079Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:f61dea54e17f3e5b54f77a077595d8059a290e2cb1c3a6be7bd4c7bbdf7d7699","observation_id":"91969777-dccf-47b9-aeeb-a05632efa01e","resolution":{"observed_at":"2026-08-06T22:52:34.689796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.13284","last_updated":"2025-06-16T09:27:48Z","snapshot_observed_at":"2026-08-13T16:04:27.350434Z","submitted_at":"2025-06-16T09:27:48Z","title":"AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.13284","snapshot_observed_at":"2026-08-06T22:52:33.396332Z","title":"Acereason-nemotron 1.1: Advancing math and code reasoning through sft and rl synergy","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.396332Z"},"links":{"cited_paper":"/paper/2506.13284","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:3979add6708b42baa42c134455527a3caea383b0530a07509257408ddbe396df","observation_id":"e7e64ebd-a01c-41a6-b536-78b606eefee0","resolution":{"observed_at":"2026-08-06T22:52:33.396332Z","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":"2026-08-06T22:52:33.399507Z","title":"Discrete diffusion language modeling by estimating the ratios of the data distribution","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.399507Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:3ea2200bf2846460d3084ce83e734e8cfc4de2f7078e172ec88298b7bb2fafdd","observation_id":"061c17ac-9c16-4e18-8ddd-e19a38bdf87e","resolution":{"observed_at":"2026-08-06T22:52:33.399507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.19173","last_updated":"2024-02-29T13:53:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-02-29T13:53:35Z","title":"StarCoder 2 and The Stack v2: The Next Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.19173","snapshot_observed_at":"2026-08-06T22:52:33.402266Z","title":"Starcoder 2 and the stack v2: The next generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.402266Z"},"links":{"cited_paper":"/paper/2402.19173","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:971187d8f51838f848dedff8087e190d3d5089022befedcdc5632b77d00c8e77","observation_id":"788070b1-0934-4fbf-9194-823c3dadc4b9","resolution":{"observed_at":"2026-08-06T22:52:33.402266Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.15781","last_updated":"2025-05-21T17:32:10Z","snapshot_observed_at":"2026-08-11T13:17:41.186341Z","submitted_at":"2025-05-21T17:32:10Z","title":"dKV-Cache: The Cache for Diffusion Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.15781","snapshot_observed_at":"2026-08-06T22:52:33.405224Z","title":"dkv-cache: The cache for diffusion language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.405224Z"},"links":{"cited_paper":"/paper/2505.15781","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:4fc06e3567841ec12f8cbf637b07586b9c3c9d74e6a1b003c4d5adaba1466186","observation_id":"6941bb93-5eb0-4e45-b145-5b5565d57b65","resolution":{"observed_at":"2026-08-06T22:52:33.405224Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.18514","last_updated":"2025-02-28T07:02:59Z","snapshot_observed_at":"2026-08-12T22:16:08.064745Z","submitted_at":"2024-10-24T08:01:22Z","title":"Scaling up Masked Diffusion Models on Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.18514","snapshot_observed_at":"2026-08-06T22:52:33.408341Z","title":"Scaling up masked diffusion models on text","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.408341Z"},"links":{"cited_paper":"/paper/2410.18514","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:19ad3244e084276d1fe0b80f53a04f67b1f48e0df1887f66bb5f93f9d81368db","observation_id":"7507ae08-6a85-4625-9cbb-2caa81350b89","resolution":{"observed_at":"2026-08-06T22:52:33.408341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-06T22:52:33.411088Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.411088Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:bef44a84b6fd04fe6b9ce21ba7fcf7a4dc2ec6f5ee56a84899a640871e6c6234","observation_id":"70f894c6-17aa-4f27-9c13-1fa862c4299d","resolution":{"observed_at":"2026-08-06T22:52:33.411088Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.672273Z","title":"Open r1: A fully open reproduction of deepseek-r1, 2025","venue":null,"work_id":"0c2dd075-acb6-4303-bd29-13ff63f2f4bc","year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.414039Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:1fca77982abcc7e1b22040327f8377930cbacd6998f4fdc9ce0b2d924d9f34fb","observation_id":"4ccddc52-46cb-40e2-8e6a-794d7be09165","resolution":{"observed_at":"2026-08-06T22:52:34.675218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.03736","last_updated":"2026-03-23T09:46:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-06-06T04:22:11Z","title":"Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.03736","snapshot_observed_at":"2026-08-06T22:52:33.416659Z","title":"Your absorbing discrete diffusion secretly models the conditional distributions of clean data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.416659Z"},"links":{"cited_paper":"/paper/2406.03736","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:e0d2c993a2b7e0e47cbfb4a3a282566ddc7b9a0120c568750e00bdb5018ac1c2","observation_id":"6232dcd8-0ed2-49aa-afce-09de34d8c120","resolution":{"observed_at":"2026-08-06T22:52:33.416659Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.662755Z","title":"Raffel, Leandro von Werra, and Thomas Wolf","venue":null,"work_id":"8e60246f-cca5-4d26-9220-59ce75e58ef3","year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.419537Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:4d47132194f9e9fcdcd5f4ffbc5657e8c466d95cea50203fc4003ab433c36c7a","observation_id":"fd76d239-ee1b-44c1-85ca-ee20311c3249","resolution":{"observed_at":"2026-08-06T22:52:34.666248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:33.422222Z","title":"Direct preference optimization: Your language model is secretly a reward model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.422222Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:82fe8c43b099a512e6d03e24fccf549c261d54187a0d34af0d0f5de8bfe9ec23","observation_id":"8045cb99-b3bd-4d31-bb6f-8d2e0c32d7b8","resolution":{"observed_at":"2026-08-06T22:52:33.422222Z","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":"2026-08-06T22:52:33.425023Z","title":"Zero: Memory optimizations toward training trillion parameter models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.425023Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:1d06d82b6ae2fa70d854d6b64971d74a3fd42839d0e69ad5e20bd24f626780dd","observation_id":"45330013-a74c-41f7-bb9b-0051433960db","resolution":{"observed_at":"2026-08-06T22:52:33.425023Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.641695Z","title":"Diffusion policy policy optimization","venue":null,"work_id":"833df3bb-ece4-4ea7-9695-001949b5d794","year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.428240Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:1d76296a4773363b37f4403f8ea425819b175f0e52a82815d9259413a5224f31","observation_id":"851afa51-1f60-4846-bd8b-b7d5bba9eac2","resolution":{"observed_at":"2026-08-06T22:52:34.645262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12950","last_updated":"2024-01-31T19:47:26Z","snapshot_observed_at":"2026-08-13T04:25:38.282910Z","submitted_at":"2023-08-24T17:39:13Z","title":"Code Llama: Open Foundation Models for Code","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12950","snapshot_observed_at":"2026-08-06T22:52:33.431182Z","title":"Code llama: Open foundation models for code","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.431182Z"},"links":{"cited_paper":"/paper/2308.12950","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:f3e01ceb73e713f283125b557290ebbd962b5bd6c0631aa9fda3e4c319f4d416","observation_id":"a02d735f-44c0-4c12-a623-78d6fd137dab","resolution":{"observed_at":"2026-08-06T22:52:33.431182Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.631884Z","title":"Sahoo, Marianne Arriola, Yair Schiff, Aaron Gokaslan, Edgar Marroquin, Justin T","venue":null,"work_id":"f691e15f-a410-4487-a317-ebf740c31909","year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.434345Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:1e9f8cbd8c7f09498867c1dbdee7dfed8b705455db4e53cebe6fb410833cec22","observation_id":"9aa62572-298d-49bf-b666-580796476c39","resolution":{"observed_at":"2026-08-06T22:52:34.635051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:33.437414Z","title":"Esoteric language models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.437414Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:6de02c22aa2a47680e3235be2282cad2686f2e4512c313b14410b763403abdce","observation_id":"67b6bcae-788c-41ba-9957-5cc863fe57f9","resolution":{"observed_at":"2026-08-06T22:52:33.437414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-06T22:52:33.440349Z","title":"Proximal policy optimization algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.440349Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:40caaf64d6a23425332b818cbe2391b7b35be3cb04ce0429f88bde498be3e267","observation_id":"b9023cc1-16ed-4922-84df-bb550e38d40d","resolution":{"observed_at":"2026-08-06T22:52:33.440349Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.616836Z","title":"Spurious rewards: Rethinking training signals in rlvr","venue":null,"work_id":"b558efc4-2a15-40b9-8db6-1c065198e1a5","year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.443649Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:8639ef2bd64f1ee4344b2872efa0f620dc39e9479e8d29e7b8a0468750911f73","observation_id":"7a082c10-aec9-484f-aefe-8f3beaaa7539","resolution":{"observed_at":"2026-08-06T22:52:34.619743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-06T22:52:33.446883Z","title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.446883Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:97b8686af52d4147dcc406ff5a76ed43c59d04adabf7c4ed5a13fbacc314470d","observation_id":"1e4dbcd1-e02a-43d4-a9ef-0e8ddb12c4d3","resolution":{"observed_at":"2026-08-06T22:52:33.446883Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.607553Z","title":null,"venue":null,"work_id":"75132e49-fae5-4380-a4f9-42ec9f179ced","year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.449722Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:f4c630d41dc546c84305ae4ff4c630eb6c3b5df7ef894e18247d68c6942ecc8c","observation_id":"4b26a2bf-f06c-4f68-a834-d75c1a9fc81b","resolution":{"observed_at":"2026-08-06T22:52:34.610715Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2023.emnlp-main.716","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":"C ode F usion: A pre-trained diffusion model for code generation","venue":null,"work_id":"04981d3b-49f9-467e-9760-1d12dce1a2c0","year":2023},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.452552Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:beb5a4a719f58b3bdd1cc546b520e59a6513c45772e8d700b3f565d928c02520","observation_id":"74772195-4f5c-419e-880b-682a60dc6c42","resolution":{"observed_at":"2026-08-06T22:52:33.575776Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.597483Z","title":"Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole","venue":null,"work_id":"85eabe81-c6e7-4b19-b230-46749a3f5f0a","year":2021},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.455516Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:2e0c77e0dc7b99e520867d89d421d602065e8a244903c17087fc2952335cb53f","observation_id":"14c19048-b284-44f8-9271-ce8e3172e947","resolution":{"observed_at":"2026-08-06T22:52:34.600557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14734","last_updated":"2025-01-26T10:48:44Z","snapshot_observed_at":"2026-08-13T00:48:51.622964Z","submitted_at":"2024-03-21T08:54:56Z","title":"A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14734","snapshot_observed_at":"2026-08-06T22:52:33.458261Z","title":"A survey of neural code intelligence: Paradigms, advances and beyond","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.458261Z"},"links":{"cited_paper":"/paper/2403.14734","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:1ad70fd5f3c08c6e6f9d7c0831eee5e9b33b6f75511b7b680c243c43649cf193","observation_id":"30e2108d-cc45-4412-a2bd-010d01a5cba2","resolution":{"observed_at":"2026-08-06T22:52:33.458261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-06T22:52:33.461637Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.461637Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:3d472141d54e9db72a26763aa589047eb6bf2642b80782355242ebc6a62f4980","observation_id":"a7e7eea0-899b-4fe1-86bd-c33acbbeb3c0","resolution":{"observed_at":"2026-08-06T22:52:33.461637Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.588407Z","title":"Octothinker: Revisiting mid-training in the era of rl scaling","venue":null,"work_id":"e5fff324-60d8-43c1-97cc-1ee6dfe6b5da","year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.465166Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:57ea942a1ebb22d3d989428930cca431ddf7d069ccaceb4c173efc0e84239933","observation_id":"2023d32f-cf75-4183-ad3e-1c782f27e7b3","resolution":{"observed_at":"2026-08-06T22:52:34.591508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:33.467869Z","title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.467869Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:8e0d26c5dc1f94a734e3ce6f77a6e2a46dd19e751c6101172e8187e6f495bee8","observation_id":"8199fe4f-c1b7-4ab6-bc1a-fd3c4878da75","resolution":{"observed_at":"2026-08-06T22:52:33.467869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22618","last_updated":"2025-07-03T04:51:05Z","snapshot_observed_at":"2026-07-06T21:32:23.537939Z","submitted_at":"2025-05-28T17:39:15Z","title":"Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.22618","snapshot_observed_at":"2026-08-06T22:52:33.470475Z","title":"Fast dllm: Training-free acceleration of diffusion llm by enabling kv cache and parallel decoding","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.470475Z"},"links":{"cited_paper":"/paper/2505.22618","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:f2958b663f5a15dca878a2c6c107cda49fb3e7daef678c946a787a6697b498c8","observation_id":"b7da2604-7f64-4ea0-a450-7e26d3078921","resolution":{"observed_at":"2026-08-06T22:52:33.470475Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.573301Z","title":"Efficient streaming language models with attention sinks","venue":null,"work_id":"21168db3-6402-4b61-8822-229ec1293f5b","year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.473188Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:b3e61c1cd0e0e711da32ed34c11524370000f3e3fdc79a91de2bd5d39a7e5e82","observation_id":"dd18ec1e-341f-43a2-bd23-64a1891860e3","resolution":{"observed_at":"2026-08-06T22:52:34.576384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:33.476233Z","title":"Teaching language models to critique via reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.476233Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:94dd5715fdc92b10cbd35d2373c1feba249edaa76203b6abbe7460c764500e87","observation_id":"4e418eaa-cf53-4bef-ac2e-75f065cc471e","resolution":{"observed_at":"2026-08-06T22:52:33.476233Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.564171Z","title":"Lemur: Harmonizing natural language and code for language agents","venue":null,"work_id":"7d3e07d0-3a3c-4922-abd0-a2f70b1cb2cf","year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.479282Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:44123cb893e02a6dca6a43af698c62c8b9a93f4cc95095103472bdd32ab64ad6","observation_id":"2916f53f-436c-4614-b8c7-6634093e594d","resolution":{"observed_at":"2026-08-06T22:52:34.567361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.15809","last_updated":"2025-09-25T02:40:45Z","snapshot_observed_at":"2026-08-05T05:27:10.277230Z","submitted_at":"2025-05-21T17:59:05Z","title":"MMaDA: Multimodal Large Diffusion Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.15809","snapshot_observed_at":"2026-08-06T22:52:33.482004Z","title":"Mmada: Multimodal large diffusion language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.482004Z"},"links":{"cited_paper":"/paper/2505.15809","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:09bedd14fb3fe9b1ef3810e73a03bafdc010196e044d91887f3c3af56d548d8a","observation_id":"9a2ecb17-bfb0-451d-95f2-81a6ddaf1b09","resolution":{"observed_at":"2026-08-06T22:52:33.482004Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.14157","last_updated":"2025-02-18T03:52:31Z","snapshot_observed_at":"2026-08-12T22:20:24.169202Z","submitted_at":"2024-10-18T03:48:53Z","title":"Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.14157","snapshot_observed_at":"2026-08-06T22:52:33.485058Z","title":"Beyond autoregression: Discrete diffusion for complex reasoning and planning, 2024 a","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.485058Z"},"links":{"cited_paper":"/paper/2410.14157","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:5c2d7f11df0a16d3360c38ff22ac88794e9f54ce551be84aaeb19d62c39eaed5","observation_id":"ddd3084f-690f-4856-8a3f-6efcf9aa4416","resolution":{"observed_at":"2026-08-06T22:52:33.485058Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07754","last_updated":"2024-12-05T06:49:06Z","snapshot_observed_at":"2026-08-14T09:18:58.443946Z","submitted_at":"2024-02-12T16:23:28Z","title":"Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07754","snapshot_observed_at":"2026-08-06T22:52:33.488204Z","title":"Diffusion of thoughts: Chain-of-thought reasoning in diffusion language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.488204Z"},"links":{"cited_paper":"/paper/2402.07754","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:ffe0cf81378244dfd3f73dfcf45e61d148c0c4cc376d366547296013ba7077e2","observation_id":"b86167c5-cfb7-4d65-b829-19c4d5611590","resolution":{"observed_at":"2026-08-06T22:52:33.488204Z","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":"2026-08-06T22:52:33.491011Z","title":"Dream 7b, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.491011Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:9e6dd3bcc8793a07b9eba5113043f448f1e1d7e9f154fbfe00d06dbdf0785d35","observation_id":"2090e4a7-10da-4a62-bcf5-af66247ba34f","resolution":{"observed_at":"2026-08-06T22:52:33.491011Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.16990","last_updated":"2025-05-26T02:04:39Z","snapshot_observed_at":"2026-08-07T14:49:45.584405Z","submitted_at":"2025-05-22T17:55:04Z","title":"Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.16990","snapshot_observed_at":"2026-08-06T22:52:33.493730Z","title":"Dimple: Discrete diffusion multimodal large language model with parallel decoding","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.493730Z"},"links":{"cited_paper":"/paper/2505.16990","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:b1b263326367fc97b3b3cb5e46ad91b3414df5d3f79c4b99293040f7b2c34fbb","observation_id":"f0fa195d-da71-42d5-8edb-47a305183176","resolution":{"observed_at":"2026-08-06T22:52:33.493730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.13837","last_updated":"2025-11-24T06:11:04Z","snapshot_observed_at":"2026-08-14T14:03:15.178702Z","submitted_at":"2025-04-18T17:59:56Z","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.13837","snapshot_observed_at":"2026-08-06T22:52:33.496674Z","title":"Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model? ArXiv preprint, abs/2504.13837, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.496674Z"},"links":{"cited_paper":"/paper/2504.13837","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:463920d042045e173e8712b725d47727e1186ea1251a97ce1e04f5faf26ba317","observation_id":"185e9cb2-38c3-4ea7-ac56-f082bac3e8b7","resolution":{"observed_at":"2026-08-06T22:52:33.496674Z","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":"2026-08-06T22:52:33.499481Z","title":"Fine-tuning discrete diffusion models with policy gradient methods","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.499481Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:bcb2d06b3fdc7f1449cafc661560fff2836f3db997dd9b5665ea77eb6c1e65b2","observation_id":"99725b8d-bb82-47e3-b1f2-21ec8ecd8be8","resolution":{"observed_at":"2026-08-06T22:52:33.499481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01718","last_updated":"2025-05-24T04:36:48Z","snapshot_observed_at":"2026-08-14T06:10:00.978457Z","submitted_at":"2025-02-03T18:46:04Z","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01718","snapshot_observed_at":"2026-08-06T22:52:33.502352Z","title":"Acecoder: Acing coder rl via automated test-case synthesis","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.502352Z"},"links":{"cited_paper":"/paper/2502.01718","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:782b2fc9e3e6b37c12f0096fa68b9d88285e7050d4f9811b6e9cc04f9afcf4eb","observation_id":"6f6953f7-05e4-4410-bbaa-3b8830999e0e","resolution":{"observed_at":"2026-08-06T22:52:33.502352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.16431","last_updated":"2025-04-23T05:32:58Z","snapshot_observed_at":"2026-08-13T20:53:07.894199Z","submitted_at":"2025-04-23T05:32:58Z","title":"Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.16431","snapshot_observed_at":"2026-08-06T22:52:33.505638Z","title":"Target concrete score matching: A holistic framework for discrete diffusion","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.505638Z"},"links":{"cited_paper":"/paper/2504.16431","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:087479297ecf65b1fe49c90dd83600cb3e46982da1d3ce6501401599013e7002","observation_id":"c88d42fa-4be3-49af-8e7b-fff0583869e9","resolution":{"observed_at":"2026-08-06T22:52:33.505638Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.548329Z","title":"Susskind, and Navdeep Jaitly","venue":null,"work_id":"c023d386-0ea8-4f0c-9b3c-fb5c1033bfa3","year":2023},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.509061Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:0ac2b74501eec34a0abed1935e7d4bedb46df55d63ea7533afd3a571b3e5bfdb","observation_id":"e6ab4d78-1c0c-40cd-a22c-10cd1d1b4742","resolution":{"observed_at":"2026-08-06T22:52:34.551775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.12216","last_updated":"2025-06-03T17:02:25Z","snapshot_observed_at":"2026-08-07T16:01:44.170215Z","submitted_at":"2025-04-16T16:08:45Z","title":"d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.12216","snapshot_observed_at":"2026-08-06T22:52:33.512057Z","title":"d1: Scaling reasoning in diffusion large language models via reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.512057Z"},"links":{"cited_paper":"/paper/2504.12216","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:b500f80f209bc05a22b2f121431aa4d081c52c78c03613ff4c82d9b43ef5b17d","observation_id":"3edbd26d-a14d-4fcf-a186-7929a40f4206","resolution":{"observed_at":"2026-08-06T22:52:33.512057Z","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":"2026-08-06T22:52:33.515073Z","title":"Pytorch fsdp: Experiences on scaling fully sharded data parallel","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.515073Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:8316493c14af3ea2e2e2774d463c2fb717f30c6d66ccaa704386ba1aaf3c84d2","observation_id":"e010413f-a123-437d-ac21-4a8dc4953a60","resolution":{"observed_at":"2026-08-06T22:52:33.515073Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:52:34.539073Z","title":"A reparameterized discrete diffusion model for text generation","venue":null,"work_id":"85b74ff8-7b83-4101-9779-6778c7c1edfd","year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.517946Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:3b6a92813b38c7ccaa5ea72d5283a40024be2943d479f522b381bc1ee3fb6f3e","observation_id":"ddad496a-8d58-4194-b483-71899c74492d","resolution":{"observed_at":"2026-08-06T22:52:34.542267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.17115","last_updated":"2025-02-14T16:44:08Z","snapshot_observed_at":"2026-08-13T01:51:23.532121Z","submitted_at":"2024-09-25T17:28:13Z","title":"Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.17115","snapshot_observed_at":"2026-08-06T22:52:33.521093Z","title":"Programming every example: Lifting pre-training data quality like experts at scale","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.521093Z"},"links":{"cited_paper":"/paper/2409.17115","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:e691d892604a04705dd462cfe148ac0b20095414f72bd02995e4083fc76d2449","observation_id":"ca73abac-acf3-492a-bf6b-0a3c7bce0c6f","resolution":{"observed_at":"2026-08-06T22:52:33.521093Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.19223","last_updated":"2025-10-12T15:42:47Z","snapshot_observed_at":"2026-08-09T15:57:47.133628Z","submitted_at":"2025-05-25T16:36:20Z","title":"LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.19223","snapshot_observed_at":"2026-08-06T22:52:33.524300Z","title":"Llada 1.5: Variance-reduced preference optimization for large language diffusion models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.524300Z"},"links":{"cited_paper":"/paper/2505.19223","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:189be774bc6b4598497287d5d822772fa4a0fbfdb9125d759b7f2e6fb2fe96e0","observation_id":"cd8fd60d-0714-442b-b3b7-7e9f45828514","resolution":{"observed_at":"2026-08-06T22:52:33.524300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15877","last_updated":"2025-04-01T08:36:44Z","snapshot_observed_at":"2026-08-14T15:45:30.011625Z","submitted_at":"2024-06-22T15:52:04Z","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.15877","snapshot_observed_at":"2026-08-06T22:52:33.527500Z","title":"Bigcodebench: Benchmarking code generation with diverse function calls and complex instructions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.527500Z"},"links":{"cited_paper":"/paper/2406.15877","citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:d85dc8424263ea2b0c9b9a63e4da5d4aa9dedecdb60ce56046c9aaf454df79be","observation_id":"abfacc94-7386-4372-836a-b8e5a97d6fc0","resolution":{"observed_at":"2026-08-06T22:52:33.527500Z","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":"2026-08-06T22:52:33.530719Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.530719Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:3db731dbdfea935173369e93ed09892efd4e255e4549c0f81431eb22eced9ab3","observation_id":"1e15c7ca-f0ae-4844-ac14-4d0c4f3ee90b","resolution":{"observed_at":"2026-08-06T22:52:33.530719Z","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":"2026-08-06T22:52:33.534500Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.534500Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:3c4c10861819aa3cd611b222e7cb2812a5abb899b734f094ae76ea2c72e367f5","observation_id":"fa4e605e-4c3a-4cb4-b117-553c5a8f7bb7","resolution":{"observed_at":"2026-08-06T22:52:33.534500Z","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":"2026-08-06T22:52:33.538070Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.538070Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:75037f7ce7ffcf6d6660bb6e6fbaa21eef2a7452750955e5fec9c9168f2a19c2","observation_id":"b77f981d-fd08-4a15-86df-a70a2a31c8f5","resolution":{"observed_at":"2026-08-06T22:52:33.538070Z","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":"2026-08-06T22:52:33.541150Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","version":2},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-06T22:52:33.541150Z"},"links":{"citing_paper":"/paper/2506.20639"},"observation_digest":"sha256:10fc4cb19a410884d1a5cf60529381690fa070c6ca1f76acb4822f61823bdbb2","observation_id":"39935ecf-11fb-49a0-9066-fe22cffe3bc1","resolution":{"observed_at":"2026-08-06T22:52:33.541150Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.20639","last_updated":"2025-06-26T15:46:40Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-14T01:37:07.461149Z","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation"},"reference_resolution":{"displayed":84,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":60,"verified_exact":1,"verified_fuzzy":22},"total_outbound_references":84},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 84 of 84 outbound references and 70 inbound Pith citation observations for arXiv:2506.20639."}