{"as_of":"2026-08-21T21:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7646a10046e7e643a4861fd13e54d33654450b2d3a456931c8c76557a9ed7652","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T02:38:07.792710Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-02T19:05:59.651008Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T19:07:17.248530Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","submitted_at":"2026-03-04T11:43:19Z","title":"LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2603.13319","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2603.13319","snapshot_observed_at":"2026-08-03T02:15:22.563508Z","title":"Lightningrl: Breaking the accuracy- parallelism trade-off of block-wise dllms via reinforcement learning","venue":null,"work_id":"31f5a8f4-86dc-42cd-8713-e1ab10e11898","year":2026},"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":33,"source":"pdf_text","source_observed_at":"2026-05-10T17:58:17.880199Z"},"links":{"cited_paper":"/paper/2603.13319","citing_paper":"/paper/2604.08302"},"observation_digest":"sha256:13230d28a1da989339bdb2883299d79d03cceb4893ea13fca7574732db35e6c8","observation_id":"b27d0e8e-9d66-4651-b8a6-a507b627b1c6","resolution":{"observed_at":"2026-08-03T02:15:22.563508Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","submitted_at":"2026-03-04T11:43:19Z","title":"LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2603.13319","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2603.13319","snapshot_observed_at":"2026-08-03T02:15:22.563508Z","title":"Lightningrl: Breaking the accuracy- parallelism trade-off of block-wise dllms via reinforcement learning","venue":null,"work_id":"31f5a8f4-86dc-42cd-8713-e1ab10e11898","year":2026},"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":33,"source":"pdf_text","source_observed_at":"2026-05-19T16:46:56.743268Z"},"links":{"cited_paper":"/paper/2603.13319","citing_paper":"/paper/2604.08302"},"observation_digest":"sha256:c97f2b94a01551f49357e182e1d05abb14300d3667c823a6a2187e9e5aeca6f3","observation_id":"54612009-22a3-4466-b8e2-a04bc12cfa8a","resolution":{"observed_at":"2026-08-03T02:15:22.563508Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","submitted_at":"2026-03-04T11:43:19Z","title":"LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2603.13319","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2603.13319","snapshot_observed_at":"2026-08-03T02:15:22.563508Z","title":"Lightningrl: Breaking the accuracy- parallelism trade-off of block-wise dllms via reinforcement learning","venue":null,"work_id":"31f5a8f4-86dc-42cd-8713-e1ab10e11898","year":2026},"citing_paper":{"arxiv_id":"2605.09536","last_updated":"2026-05-10T13:38:53Z","snapshot_observed_at":"2026-07-06T23:21:35.327066Z","submitted_at":"2026-05-10T13:38:53Z","title":"TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-12T05:01:03.570848Z"},"links":{"cited_paper":"/paper/2603.13319","citing_paper":"/paper/2605.09536"},"observation_digest":"sha256:a742ba3f3611dc215695a89581a3b029a92f8378730d87c7103b0e31cdd9b33f","observation_id":"18c0fe33-981c-4c7b-92fb-15d85d583c93","resolution":{"observed_at":"2026-08-03T02:15:22.563508Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","submitted_at":"2026-03-04T11:43:19Z","title":"LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2603.13319","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2603.13319","snapshot_observed_at":"2026-08-03T02:15:22.563508Z","title":"Lightningrl: Breaking the accuracy- parallelism trade-off of block-wise dllms via reinforcement learning","venue":null,"work_id":"31f5a8f4-86dc-42cd-8713-e1ab10e11898","year":2026},"citing_paper":{"arxiv_id":"2606.29215","last_updated":"2026-06-30T11:21:37Z","snapshot_observed_at":"2026-08-05T15:07:19.155221Z","submitted_at":"2026-06-28T05:53:45Z","title":"Multi-Block Diffusion Language Models","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-06-30T08:53:31.494892Z"},"links":{"cited_paper":"/paper/2603.13319","citing_paper":"/paper/2606.29215"},"observation_digest":"sha256:6a8f9939cb7dae5c3b8f88790990ad37a310200feca9a154ae444904d6a49f78","observation_id":"4e5c39db-ecb3-4f93-95a0-fd972894b91a","resolution":{"observed_at":"2026-08-03T02:15:22.563508Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","submitted_at":"2026-03-04T11:43:19Z","title":"LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2603.13319","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2603.13319","snapshot_observed_at":"2026-08-03T02:15:22.563508Z","title":"Lightningrl: Breaking the accuracy- parallelism trade-off of block-wise dllms via reinforcement learning","venue":null,"work_id":"31f5a8f4-86dc-42cd-8713-e1ab10e11898","year":2026},"citing_paper":{"arxiv_id":"2606.29215","last_updated":"2026-06-30T11:21:37Z","snapshot_observed_at":"2026-08-05T15:07:19.155221Z","submitted_at":"2026-06-28T05:53:45Z","title":"Multi-Block Diffusion Language Models","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-07-01T07:04:06.161855Z"},"links":{"cited_paper":"/paper/2603.13319","citing_paper":"/paper/2606.29215"},"observation_digest":"sha256:0a7c94acf9a124331b1a9918fa69b0eea9fc13174b061bdea238c92fda115fd0","observation_id":"7397b7b8-4bff-4691-b33f-164251f386e2","resolution":{"observed_at":"2026-08-03T02:15:22.563508Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","submitted_at":"2026-03-04T11:43:19Z","title":"LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2603.13319","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2603.13319","snapshot_observed_at":"2026-08-03T02:15:22.563508Z","title":"Lightningrl: Breaking the accuracy- parallelism trade-off of block-wise dllms via reinforcement learning","venue":null,"work_id":"31f5a8f4-86dc-42cd-8713-e1ab10e11898","year":2026},"citing_paper":{"arxiv_id":"2607.00208","last_updated":"2026-06-30T21:38:46Z","snapshot_observed_at":"2026-08-21T13:13:18.801806Z","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":11,"source":"pdf_text","source_observed_at":"2026-07-02T19:05:59.651008Z"},"links":{"cited_paper":"/paper/2603.13319","citing_paper":"/paper/2607.00208"},"observation_digest":"sha256:3e4c115235fc68812dc7c05f44be00657a75005191728d1c4d1c068c50ad6134","observation_id":"b6828c79-8b48-4cd2-b437-515298ed7d5a","resolution":{"observed_at":"2026-08-03T02:15:22.563508Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2603.13319/citation-record","integrity":"/paper/2603.13319/integrity","json":"/paper/2603.13319/citation-record.json","paper":"/paper/2603.13319"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:38:06.677290Z","title":"Chen, M., Tworek, J., Jun, H., Yuan, Q., de Oliveira Pinto, H","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":2,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:06.677290Z"},"links":{"citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:f10d3d56cc48020912161b9d5d6ef54bb5c693f1f5b82e2286c81571e1c81efa","observation_id":"5c47cb0a-1340-4f7d-82ac-388e4fa4af60","resolution":{"observed_at":"2026-08-03T02:38:06.677290Z","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":"2026-08-03T02:38:06.860909Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":4,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:06.860909Z"},"links":{"citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:dde123718b6a649cc11bf15cfd83b3a53beca6196beb155be46e1ae951499ae5","observation_id":"3941abfc-c6e8-4f92-9a74-a512fc5d6fc2","resolution":{"observed_at":"2026-08-03T02:38:06.860909Z","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":"2026-08-19T21:26:16.218628Z","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":"2026-08-19T13:30:53.693078Z","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":"sha256:0a5838ec1305b8273658736b0815a7e1c030f0391d281eca5c3347f75b0c4391","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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T02:38:07.141752Z","title":"Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., and Steinhardt, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":7,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.141752Z"},"links":{"citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:90981757282fbb79e516dc3cb100769712faccb503cf6c3ad10e6dd8f62aa8d8","observation_id":"4b9709a4-caf6-41ee-92c6-b18fdc339f1d","resolution":{"observed_at":"2026-08-03T02:38:07.141752Z","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":"2026-08-03T02:38:07.171455Z","title":"Kou, S., Hu, L., He, Z., Deng, Z., and Zhang, H","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":8,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.171455Z"},"links":{"citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:8a607ebddb8fd4293ccff11b4ac741868e59a2c1001dd21fbba3bdc0dc99d0c0","observation_id":"0fffe2e3-612c-49df-ba4c-d8e2ca2a7132","resolution":{"observed_at":"2026-08-03T02:38:07.171455Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.01840","last_updated":"2025-04-23T07:08:17Z","snapshot_observed_at":"2026-08-13T11:30:48.832931Z","submitted_at":"2025-03-03T18:59:04Z","title":"EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.01840","snapshot_observed_at":"2026-08-03T02:38:07.303471Z","title":"Ma, Y ., Melnychuk, V ., Schweisthal, J., and Feuerriegel, S","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":10,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.303471Z"},"links":{"cited_paper":"/paper/2503.01840","citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:bc29adb243b87c70f0a3d2d93640588016efb5d28d5c64599a83e1f71e025929","observation_id":"665a3857-097b-4d99-a28c-60edd1d6e172","resolution":{"observed_at":"2026-08-03T02:38:07.303471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09992","last_updated":"2025-10-18T15:35:05Z","snapshot_observed_at":"2026-08-04T04:34:22.998376Z","submitted_at":"2025-02-14T08:23:51Z","title":"Large Language Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.09992","snapshot_observed_at":"2026-08-03T02:38:07.376925Z","title":"Ou, J., Han, J., Xu, M., Xu, S., Xie, J., Ermon, S., Wu, Y ., and Li, C","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":12,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.376925Z"},"links":{"cited_paper":"/paper/2502.09992","citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:e1747eda821b97db60be579d0bf1d6add5d4dfde92c952e0a150377dffb82ed7","observation_id":"642cb122-0f95-4d18-bfd3-1eed2d9d1f47","resolution":{"observed_at":"2026-08-03T02:38:07.376925Z","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":"2026-08-03T02:38:07.404372Z","title":"Qian, Y .-Y ., Su, J., Hu, L., Zhang, P., Deng, Z., Zhao, P., and Zhang, H","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":13,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.404372Z"},"links":{"citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:64e8e57662d8d8dd8f94df9f9e9ce9f6981f0527a0c0c62d3c983526a90c8273","observation_id":"30ed7448-ff04-4149-a2ae-a03ceff90ced","resolution":{"observed_at":"2026-08-03T02:38:07.404372Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-08-17T18:50:07.059564Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-03T02:38:07.456254Z","title":"Sahoo, S","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":15,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.456254Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:155c9c7210992b41f84ee9f95239ffb00e3fd194e88605340f9d9c737e7f0740","observation_id":"08312bbe-f7f8-4812-b3fc-6b4b35b2a898","resolution":{"observed_at":"2026-08-03T02:38:07.456254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-03T02:38:07.490906Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":16,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.490906Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:85b1fd1b90daf0023ccbf6fab104750fca2f3f78f604ccc86da5e6500bd6b935","observation_id":"24ca1cbf-1358-462b-8703-20735188147a","resolution":{"observed_at":"2026-08-03T02:38:07.490906Z","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":"2026-08-03T02:38:07.545572Z","title":"Wang, X., Xu, C., Jin, Y ., Jin, J., Zhang, H., and Deng, Z","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":17,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.545572Z"},"links":{"citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:8cabb2b6d97d90b07c2cd2e3e6c5026c71ecdbd77b602863078b8d53da56f04d","observation_id":"8c9038e8-082d-4646-a1e2-b759ed86e4af","resolution":{"observed_at":"2026-08-03T02:38:07.545572Z","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":"2026-08-03T02:38:07.603621Z","title":"Ye, J., Xie, Z., Zheng, L., Gao, J., Wu, Z., Jiang, X., Li, Z., and Kong, L","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":18,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.603621Z"},"links":{"citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:7dc8db29f222e74bd099a358db49fe76521212b100d127d4fee3d318f3c9cd75","observation_id":"6c6f10af-c110-41dc-97f7-198d53a0046a","resolution":{"observed_at":"2026-08-03T02:38:07.603621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.12216","last_updated":"2025-06-03T17:02:25Z","snapshot_observed_at":"2026-08-19T23:20:06.183863Z","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":"2026-08-03T02:38:07.646818Z","title":"org/abs/2504.12216","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":19,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.646818Z"},"links":{"cited_paper":"/paper/2504.12216","citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:0b832deb65e773a8e52ee5a3f38c99a1adf5b84ebf8b76f39baeb977bc2f1752","observation_id":"6cbe0675-721d-4b0f-9d84-b9fc1fab8da3","resolution":{"observed_at":"2026-08-03T02:38:07.646818Z","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":"2026-08-03T02:38:07.710297Z","title":"Zhu, Y ., Wan, J., Liu, X., He, S., Wang, Q., Guo, X., Liang, T., Huang, Z., He, Z., and Qiu, X","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":20,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.710297Z"},"links":{"citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:057173e7084df9f0ee273eeeaf38f07592ceda69add565bccd651ef3bccc1b07","observation_id":"3c07cb2b-3121-4236-a156-102f8ee78344","resolution":{"observed_at":"2026-08-03T02:38:07.710297Z","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":"2026-08-03T02:38:07.753774Z","title":"11 LightningRL: Breaking the Accuracy–Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":21,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.753774Z"},"links":{"citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:aa9c5f44769d6e849acb0c15891a6ecb215a04969e0f1d804a5326bafc73d0ff","observation_id":"52184a1d-bc60-4a33-92f9-152df3cb409e","resolution":{"observed_at":"2026-08-03T02:38:07.753774Z","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":"2026-08-03T02:38:07.792710Z","title":"Notably, LightningRL achieves exceptional inference speed, significantly outperforming the baselines","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":22,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.792710Z"},"links":{"citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:9a9a1abec5c2d25788c0d88f761da840ff81820781dc2d70983ffb39705c407a","observation_id":"c0f34ff7-4f5f-4bb9-9951-755ad1f7b349","resolution":{"observed_at":"2026-08-03T02:38:07.792710Z","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":"2026-08-03T02:38:06.784739Z","title":"dparallel: Learnable parallel decoding for dllms.arXiv preprint arXiv:2509.26488,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":2021,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:06.784739Z"},"links":{"citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:d04c8964d3295361938e3a0b8957acaea08590302cfd21e4338cb432f0530ba1","observation_id":"2ad29a45-8315-4a6d-a37a-bd2cbb45667d","resolution":{"observed_at":"2026-08-03T02:38:06.784739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.14217","last_updated":"2022-05-27T20:12:09Z","snapshot_observed_at":"2026-08-20T09:35:53.430024Z","submitted_at":"2022-05-27T20:12:09Z","title":"Diffusion-LM Improves Controllable Text Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.14217","snapshot_observed_at":"2026-08-03T02:38:07.250100Z","title":"Li, Y ., Wei, F., Zhang, C., and Zhang, H","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":2022,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.250100Z"},"links":{"cited_paper":"/paper/2205.14217","citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:39fd7fdc9f220865438a1c0ab9549f5617a2f7e573d89b59a87bf2ec5b186fbe","observation_id":"e50a3b0c-40b5-4d15-affa-ed18d5e79363","resolution":{"observed_at":"2026-08-03T02:38:07.250100Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18619","last_updated":"2023-05-30T16:43:31Z","snapshot_observed_at":"2026-08-21T20:25:16.819714Z","submitted_at":"2023-05-30T16:43:31Z","title":"Likelihood-Based Diffusion Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18619","snapshot_observed_at":"2026-08-03T02:38:07.094506Z","title":"org/abs/2305.18619","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":2023,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.094506Z"},"links":{"cited_paper":"/paper/2305.18619","citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:d070404a20365e0cb678422761af51aa6fc41595c41802f1ae20ceb8ad0418fe","observation_id":"9f17ac21-ece7-456e-97e1-c746dce835db","resolution":{"observed_at":"2026-08-03T02:38:07.094506Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08924","last_updated":"2024-10-11T15:50:17Z","snapshot_observed_at":"2026-08-19T12:28:46.875521Z","submitted_at":"2024-10-11T15:50:17Z","title":"DiffPO: A causal diffusion model for learning distributions of potential outcomes","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.08924","snapshot_observed_at":"2026-08-03T02:38:07.338027Z","title":"Nie, S., Zhu, F., You, Z., Zhang, X., Ou, J., Hu, J., Zhou, J., Lin, Y ., Wen, J.-R., and Li, C","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":2024,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.338027Z"},"links":{"cited_paper":"/paper/2410.08924","citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:8e6c5460d93f344e7ce930c584e3b4c5d68072c644b0d3268fd7e723ccbeed10","observation_id":"a91a15a5-c597-4a4f-b983-e534698bd366","resolution":{"observed_at":"2026-08-03T02:38:07.338027Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.09573","last_updated":"2025-05-17T21:15:02Z","snapshot_observed_at":"2026-08-14T13:55:40.999046Z","submitted_at":"2025-03-12T17:43:40Z","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.09573","snapshot_observed_at":"2026-08-03T02:38:06.591593Z","title":"Austin, J., Odena, A., Nye, M., Bosma, M., Michalewski, H., Dohan, D., Jiang, E., Cai, C., Terry, M., Le, Q., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":2025,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:06.591593Z"},"links":{"cited_paper":"/paper/2503.09573","citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:4596ca674fbe7ce573a149133c8d0058f69eb8bd8201e3c247f1683eb35bec86","observation_id":"b8f02295-77d3-4147-9ac6-0c5cb5d0258f","resolution":{"observed_at":"2026-08-03T02:38:06.591593Z","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":"2026-08-03T02:38:07.430036Z","title":"org/abs/2601.07568","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","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":2026,"source":"pdf_text","source_observed_at":"2026-08-03T02:38:07.430036Z"},"links":{"citing_paper":"/paper/2603.13319"},"observation_digest":"sha256:429f9ceeaf890d32d5a6a8fa56fd05c19e12751cc4284aed8744a8316ffb1570","observation_id":"52f0c2b9-843d-43b9-ab85-7cd6d9d53ed4","resolution":{"observed_at":"2026-08-03T02:38:07.430036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.13319","last_updated":"2026-07-31T03:04:43Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T13:30:53.693078Z","submitted_at":"2026-03-04T11:43:19Z","title":"LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":22},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 6 inbound Pith citation observations for arXiv:2603.13319."}