{"as_of":"2026-08-12T20:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fed3624c683afdb5a4b3a7983960ce1b07db646298d6f50c42af2d4e830171dd","coverage":[{"denominator":78,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":78,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:46:50.422272Z","state":"measured"},{"denominator":81,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":81,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T07:30:52.012479Z","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":"2026-05-11T15:46:47.760343Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.23660","snapshot_observed_at":"2026-07-14T22:25:04.080629Z","title":"D-ar: Diffusion via autoregressive models.arXiv preprint arXiv:2505.23660, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.12252","last_updated":"2026-06-18T07:56:55Z","snapshot_observed_at":"2026-07-14T22:25:02.474086Z","submitted_at":"2026-03-12T17:58:48Z","title":"EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-14T22:25:04.080629Z"},"links":{"cited_paper":"/paper/2505.23660","citing_paper":"/paper/2603.12252"},"observation_digest":"sha256:6d9650c502d9b91ef04592eca919faeb54cc0b10cc14873dcce75c7e3b065977","observation_id":"961b28fe-e711-4f17-aec5-53c66f4178aa","resolution":{"observed_at":"2026-07-14T22:25:04.080629Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"cited_work":{"arxiv_id":"2505.23660","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.23660","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Shou, M","venue":null,"work_id":"da4ea99f-1792-4399-b770-340b2e3fdb08","year":null},"citing_paper":{"arxiv_id":"2605.00329","last_updated":"2026-05-01T01:13:50Z","snapshot_observed_at":"2026-08-11T06:31:47.003544Z","submitted_at":"2026-05-01T01:13:50Z","title":"Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-09T19:17:09.247932Z"},"links":{"cited_paper":"/paper/2505.23660","citing_paper":"/paper/2605.00329"},"observation_digest":"sha256:5f7101c9484d6ab272d5f3d97b2ea6c0eccc7c4b811f28c3a0415a411fe5f7dd","observation_id":"e2cea1fd-b2c2-48a6-beb6-07a389a3d921","resolution":{"observed_at":"2026-05-11T15:46:47.878360Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.23660","snapshot_observed_at":"2026-08-04T07:30:52.012479Z","title":"arXiv preprint arXiv:2505.23660 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02432","last_updated":"2026-08-03T16:11:43Z","snapshot_observed_at":"2026-08-10T06:05:37.883917Z","submitted_at":"2026-08-03T16:11:43Z","title":"Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T07:30:52.012479Z"},"links":{"cited_paper":"/paper/2505.23660","citing_paper":"/paper/2608.02432"},"observation_digest":"sha256:b63d880b2aaa6f5eeb9f261c494a2cc4edaea1c9f45a65ce487dd9f3097540f1","observation_id":"01cdc37b-c3df-44f3-bade-2ce3d50209b4","resolution":{"observed_at":"2026-08-04T07:30:52.012479Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.23660/citation-record","integrity":"/paper/2505.23660/integrity","json":"/paper/2505.23660/citation-record.json","paper":"/paper/2505.23660"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:46:58.291976Z","title":"Gpt-4 technical report, 2024","venue":null,"work_id":"c3942bbc-4c87-4449-9c1e-d192e79986e9","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:44.824748Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:ab228b9fde793ede56bbf1edd6307e4a6b7e1f8c2671bd04363bf57aa452d671","observation_id":"cc2fd7a5-6935-4cb7-ae16-d3a166b29127","resolution":{"observed_at":"2026-08-07T12:46:58.368235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:58.088460Z","title":"Llama: Open and efficient foundation language models, 2023","venue":null,"work_id":"a09cbb34-6e88-47af-9487-bf524c588d05","year":2023},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:44.889537Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:a680fd81c7b007389d01b3849e25050d93281963863b9c3fd95aaa3541f7bb63","observation_id":"0bdd1f13-bcc9-484c-b31d-0b763ef99acc","resolution":{"observed_at":"2026-08-07T12:46:58.156310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:57.928860Z","title":"The llama 3 herd of models, 2024","venue":null,"work_id":"856a096f-3f94-42ed-9940-afc504814a18","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:44.970154Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:1dd1285765f635f1187ed554e3e716a049ba13f3da0b9c6148b1f5c71c28c3a3","observation_id":"c1eabaff-639f-404c-bdda-3a8602ee82a0","resolution":{"observed_at":"2026-08-07T12:46:57.993686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:57.748437Z","title":"Megatron-lm: Training multi-billion parameter language models using model parallelism, 2020","venue":null,"work_id":"a9239047-1f16-4e51-b570-2fd8ebab5676","year":2020},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:45.047252Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:be9a708a813dd5989aa8c6b25354e3cabce19979ead105693e0f3347f19c8093","observation_id":"6ae694eb-0ca2-4ed6-8bef-2736a02a5103","resolution":{"observed_at":"2026-08-07T12:46:57.837872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:57.539140Z","title":"Efficient memory management for large language model serving with pagedattention","venue":null,"work_id":"f95a5918-9178-410d-842c-30ef9de65f47","year":2023},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:45.117742Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:128eace327a889eae422dd541f26e6bcebfd0d8fb76669d9eba95b4f03a4e080","observation_id":"1851360f-64dd-42bf-8ead-7a247658c9a8","resolution":{"observed_at":"2026-08-07T12:46:57.635380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:57.373053Z","title":"Gonzalez, Clark W","venue":null,"work_id":"559d7807-0ed6-4245-b3b6-9cef77d87ed7","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:45.192604Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:04ceb79f420fead3aed89866560d94ca8d1848886d624b81d49ee8de157bb7ed","observation_id":"7b29db58-6dc8-4b5a-8b6b-6078c5f33cf3","resolution":{"observed_at":"2026-08-07T12:46:57.456362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:57.140600Z","title":"Taming transformers for high-resolution image synthesis","venue":null,"work_id":"ef199535-957a-4874-bcf6-473473a8ad0c","year":2021},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:45.267918Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:13ed497eb7cf2314972d09c8c867717a93e612d85afab67d27c1027ad5753948","observation_id":"f8e34a4b-1b1a-4a1f-8344-2307473f8521","resolution":{"observed_at":"2026-08-07T12:46:57.257148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06525","last_updated":"2024-06-10T17:59:52Z","snapshot_observed_at":"2026-08-12T17:57:54.262483Z","submitted_at":"2024-06-10T17:59:52Z","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06525","snapshot_observed_at":"2026-08-07T12:46:45.345854Z","title":"Autore- gressive model beats diffusion: Llama for scalable image generation.arXiv, abs/2406.06525, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:45.345854Z"},"links":{"cited_paper":"/paper/2406.06525","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:dd0a158d7a8f820d3d00bd08cfd827b9cbf40169742e061caafe2dc8d7f102c5","observation_id":"5f85896c-36cc-4baa-8d2d-c2ca345acda2","resolution":{"observed_at":"2026-08-07T12:46:45.345854Z","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":"2026-08-07T12:46:56.973251Z","title":"Autoregressive image generation using residual quantization","venue":null,"work_id":"de5cafde-74fd-42a7-9989-5dcf227fda12","year":2022},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:45.408223Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:c0391c6d786cb74886494281c2e9f078b4a65e55a152243e1b0f0fc331c09ee8","observation_id":"6fce79b7-7d9e-47f4-af21-3f66d28121c0","resolution":{"observed_at":"2026-08-07T12:46:57.053333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.09818","last_updated":"2025-03-21T05:54:00Z","snapshot_observed_at":"2026-08-12T11:54:14.007649Z","submitted_at":"2024-05-16T05:23:41Z","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.09818","snapshot_observed_at":"2026-08-07T12:46:45.483428Z","title":"Chameleon: Mixed-modal early-fusion foundation models.arXiv, abs/2405.09818,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:45.483428Z"},"links":{"cited_paper":"/paper/2405.09818","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:291913fd6322b5c835331ebbbbb6075ec2941ade3cf8de1288acb54aa713592e","observation_id":"5fc46b2b-5b37-4b57-9137-6ccfabae1046","resolution":{"observed_at":"2026-08-07T12:46:45.483428Z","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":"2026-08-07T12:46:56.799576Z","title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","venue":null,"work_id":"33807651-0419-49a6-bd05-fa68d0739515","year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:45.522286Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:6e78bbb1447edd9b484b6e1b6efbcbb7100f73e7bef4fd67c6fdee6df21bdb03","observation_id":"c64c6b9a-fb7b-41f6-8bb8-325a8e08c04c","resolution":{"observed_at":"2026-08-07T12:46:56.866677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:56.694382Z","title":"Show-o: One single transformer to unify multimodal understanding and generation","venue":null,"work_id":"4dd047e6-12fc-47ef-af9d-8b059751e4b1","year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:45.607014Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:91e59c0d241508b62b4f5019fa7d912f9560521c8bfeb0b9e14f7957aa40f5ae","observation_id":"ab56922a-5a01-478a-b2d4-753dda0fe3fd","resolution":{"observed_at":"2026-08-07T12:46:56.740306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.07975","last_updated":"2025-03-24T08:33:32Z","snapshot_observed_at":"2026-08-10T17:11:09.825158Z","submitted_at":"2024-11-12T17:55:10Z","title":"JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.07975","snapshot_observed_at":"2026-08-07T12:46:45.711461Z","title":"Janusflow: Harmonizing autoregression and rectified flow for unified multimodal understanding and generation.arXiv, abs/2411.07975, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:45.711461Z"},"links":{"cited_paper":"/paper/2411.07975","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:46248c34f7ac14ae8c286faea39fdb5b732c22a74ed431ed6c4928c37d7b44a7","observation_id":"a3b50abb-d00b-48a1-ac98-81a0c90cbfbf","resolution":{"observed_at":"2026-08-07T12:46:45.711461Z","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":"2026-08-07T12:46:56.592375Z","title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","venue":null,"work_id":"489b9712-ed1e-4f4e-8360-d0bd0737c6d7","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:45.815246Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:c89f185f2217e1eaacf9da829f37eac6ed7e41d2e410c6ad148f60e2fa50d92e","observation_id":"d868a86c-bb90-42a5-b59e-7ee78d579020","resolution":{"observed_at":"2026-08-07T12:46:56.641401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.01827","last_updated":"2025-07-08T00:51:16Z","snapshot_observed_at":"2026-08-12T16:02:34.405350Z","submitted_at":"2024-12-02T18:59:53Z","title":"RandAR: Decoder-only Autoregressive Visual Generation in Random Orders","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.01827","snapshot_observed_at":"2026-08-07T12:46:45.910750Z","title":"Freeman, and Yu-Xiong Wang","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:45.910750Z"},"links":{"cited_paper":"/paper/2412.01827","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:7a90e77b9a7b1a0b021ab4e6624d9d94e12f07592e19788c6b62f81cdbbda541","observation_id":"b6155b4e-48df-4057-89c7-4ea9aa01895b","resolution":{"observed_at":"2026-08-07T12:46:45.910750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.00776","last_updated":"2024-11-01T17:59:58Z","snapshot_observed_at":"2026-07-06T19:43:42.287026Z","submitted_at":"2024-11-01T17:59:58Z","title":"Randomized Autoregressive Visual Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.00776","snapshot_observed_at":"2026-08-07T12:46:46.010289Z","title":"Randomized autoregressive visual generation.arXiv, abs/2411.00776, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.010289Z"},"links":{"cited_paper":"/paper/2411.00776","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:cfc1acba751e18a254d4ccedb6f82ff5febbe9a84579c1b5440b76036c642a88","observation_id":"4321cb41-7cef-4d38-a914-da9370c6a937","resolution":{"observed_at":"2026-08-07T12:46:46.010289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.20388","last_updated":"2025-03-20T18:15:30Z","snapshot_observed_at":"2026-08-09T06:15:55.650722Z","submitted_at":"2025-02-27T18:59:08Z","title":"Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.20388","snapshot_observed_at":"2026-08-07T12:46:46.106673Z","title":"Yuille, and Liang-Chieh Chen","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.106673Z"},"links":{"cited_paper":"/paper/2502.20388","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:ccc304621516a32c462acec02afaa9c10111ee51a07180fcd1a218d55cf2ae63","observation_id":"a78fdd55-6a02-458b-82e4-efb16a63fd60","resolution":{"observed_at":"2026-08-07T12:46:46.106673Z","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":"2026-08-07T12:46:56.471224Z","title":"Imagefolder: Autoregressive image generation with folded tokens","venue":null,"work_id":"125f7b47-eef7-40e5-b14d-4d3ac923e45c","year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.203180Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:962fa238cde023f95b93bbe4274e22d20b3c7579671f0253731ec0bb528fdb91","observation_id":"9f6f1c90-20f1-4684-8e28-cb9b1dacdf79","resolution":{"observed_at":"2026-08-07T12:46:56.544284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:56.381172Z","title":"Denoising diffusion implicit models","venue":null,"work_id":"bacd239e-90ff-41bb-bf7d-223aca5bcd77","year":2021},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.277161Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:0ca60901a5dba6124ff4c37a56687565b03b4ff57512309c5b339fde027ef226","observation_id":"aa9c98c5-9106-4784-8def-9ecd3d449541","resolution":{"observed_at":"2026-08-07T12:46:56.422149Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:56.325292Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":"31ae1a27-ea88-4529-922f-05fcedc8f477","year":2020},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.329003Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:7442518dbe16573582ce7ea3492ea6a82151c385cb131be856c12910114b0e46","observation_id":"e298f9e4-ab65-4006-9974-04b068b9c159","resolution":{"observed_at":"2026-08-07T12:46:56.346787Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:56.287111Z","title":null,"venue":null,"work_id":"1d6591eb-3be1-46de-8328-6643f772d1cd","year":2023},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.395827Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:41f8d374c51837ba3b5d8c18ba54a6e3e7067a7a02f36a37d245351c8dc61a40","observation_id":"3c83ddb2-574b-486c-a879-fed7cba23100","resolution":{"observed_at":"2026-08-07T12:46:56.297325Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:56.160766Z","title":"Zero-shot text-to-image generation","venue":null,"work_id":"07ec1e48-8ecb-444a-9d39-2fbcbbac6d57","year":2021},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.429911Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:6eae1abced93f95a0cb6dc5ef13a52beb72bc9b68f59db19538eb2428bcf1c6a","observation_id":"a7da4bdc-df6e-49b0-a523-14ec3485ec94","resolution":{"observed_at":"2026-08-07T12:46:56.201529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:56.032010Z","title":"Flux.https://github.com/black-forest-labs/flux, 2023","venue":null,"work_id":"05774ad9-e92a-4773-a9d1-71d285f0b4c4","year":2023},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.472756Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:cbfb8663219b6accac110ece2c4ff12a5de18de237fe03af4cf175aea63001df","observation_id":"65f17faa-0034-4b6c-9cf7-56f00d57190c","resolution":{"observed_at":"2026-08-07T12:46:56.075666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:55.939747Z","title":"SDXL: improving latent diffusion models for high-resolution image synthesis","venue":null,"work_id":"eaa24520-41e4-4e16-9162-430e7634a7d8","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.542489Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:8d32184345d76d98b0bbc93cb6cb51c014400c4182b5d2d82582f6cb7a3fc215","observation_id":"c80a2824-d562-4bda-950d-724c1e187904","resolution":{"observed_at":"2026-08-07T12:46:55.977354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:55.837303Z","title":"Generative modelling with inverse heat dissipation","venue":null,"work_id":"a1d26e1f-4cb3-4a0f-9f21-d66b5bf2286e","year":2023},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.612055Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:d1fb3408ea4dc3b97a3422216fd5bf89c3540ae05b06649382676510842f6b34","observation_id":"607903b1-6490-4556-988d-7e022317ba86","resolution":{"observed_at":"2026-08-07T12:46:55.888345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:55.716472Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":"cead3b95-3ccb-40b2-8b28-3e8046ad4f84","year":2009},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.678990Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:267902da6bb915463effd5f330c6cfb241690a0251b6bd6d3ec888c190161505","observation_id":"08767e9d-b55e-424a-9f43-b28360cb607f","resolution":{"observed_at":"2026-08-07T12:46:55.776731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:55.574250Z","title":"Autoregressive image generation without vector quantization","venue":null,"work_id":"3828adfd-aee0-4904-9827-2e7344ebe464","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.740591Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:496529e1b5f4ab1917dff763d0dcd3b298e4fb9c0181ea895522729983a2a9a7","observation_id":"e8d0f683-9a73-4bbd-ae5d-a6bb4c2e194b","resolution":{"observed_at":"2026-08-07T12:46:55.651099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.12095","last_updated":"2024-12-17T18:45:55Z","snapshot_observed_at":"2026-08-11T19:47:52.307932Z","submitted_at":"2024-12-16T18:59:29Z","title":"Causal Diffusion Transformers for Generative Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.12095","snapshot_observed_at":"2026-08-07T12:46:46.812359Z","title":"Causal diffusion transformers for generative modeling.arXiv, abs/2412.12095, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.812359Z"},"links":{"cited_paper":"/paper/2412.12095","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:bdc94481907bcad7547c3979ffe59b06a68cc71b22d0960180a93d16acf0d777","observation_id":"81bce52c-9c4b-4281-bafd-ab8233fa9ba7","resolution":{"observed_at":"2026-08-07T12:46:46.812359Z","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":"2026-08-07T12:46:55.454511Z","title":"Diffusion forcing: Next-token prediction meets full-sequence diffusion","venue":null,"work_id":"b2c7b3fe-8751-4e28-9af5-79b28c4baebc","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.877496Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:7ef1cf01d2c76d7393f771e69943e6b3e32d8cb908584a10b018a153f5743c08","observation_id":"a8055208-63d7-4ffc-aaa9-a1946fc63dcf","resolution":{"observed_at":"2026-08-07T12:46:55.506216Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:55.344488Z","title":"Denoising autoregressive transformers for scalable text-to-image generation","venue":null,"work_id":"36542977-7f14-474c-9fbf-a836f4dac577","year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:46.937239Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:7a1424ae08b355e9781fe6e5f6c66b5ec4088204f4718de6bda0c4a1e93d5b0e","observation_id":"e0c9581b-8d86-4941-a926-74bf4f2de18a","resolution":{"observed_at":"2026-08-07T12:46:55.409488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:55.233799Z","title":"Dreamllm: Synergistic multimodal comprehension and creation","venue":null,"work_id":"0dfe2742-3c32-46fe-9eac-bf6dc0f9cf2e","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.003626Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:71834557904093dee3d162a48c937a89db461cdd35f799a4a868e794fad7ad91","observation_id":"5de7d2cc-1766-4fac-945b-7dc315b83c1d","resolution":{"observed_at":"2026-08-07T12:46:55.274802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.14396","last_updated":"2025-03-02T07:53:44Z","snapshot_observed_at":"2026-08-12T19:12:43.246639Z","submitted_at":"2024-04-22T17:56:09Z","title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.14396","snapshot_observed_at":"2026-08-07T12:46:47.076151Z","title":"SEED-X: multimodal models with unified multi-granularity comprehension and generation.arXiv, abs/2404.14396, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.076151Z"},"links":{"cited_paper":"/paper/2404.14396","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:328bc1f3861d2d35cd22adc186c9c40b52169c667b8a7d69669d2b485c48e254","observation_id":"29768e1e-5749-4550-b08f-3e954b42c2b7","resolution":{"observed_at":"2026-08-07T12:46:47.076151Z","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":"2026-08-07T12:46:55.109803Z","title":"Next-gpt: Any-to-any multimodal llm","venue":null,"work_id":"0e848086-1ea0-4dbd-bca1-697aabc180ca","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.144507Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:c30f2ddfdd5a45b5e7a340ec113a09a7ecda7014e655b325014776923ec8429c","observation_id":"5627c6fb-d2e4-4660-a92d-6c1a2abf21d8","resolution":{"observed_at":"2026-08-07T12:46:55.161398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.06256","last_updated":"2025-04-08T17:58:47Z","snapshot_observed_at":"2026-08-03T00:43:33.310493Z","submitted_at":"2025-04-08T17:58:47Z","title":"Transfer between Modalities with MetaQueries","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.06256","snapshot_observed_at":"2026-08-07T12:46:47.202196Z","title":"Transfer between modalities with metaqueries.arXiv, abs/2504.06256, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.202196Z"},"links":{"cited_paper":"/paper/2504.06256","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:6068cf413fccec88537d3fe4278ff7a412de4f851c32c15c73ad0b51a48f3f67","observation_id":"7eced1e8-7ed3-40a7-834e-8242f4958736","resolution":{"observed_at":"2026-08-07T12:46:47.202196Z","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":"2026-08-07T12:46:54.970369Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","venue":null,"work_id":"9b84fb0a-0736-4ada-8e34-f260e762198c","year":2023},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.282491Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:9b57ed2a3bca96139c10010ad664d556f92bcb7b074a8745c4a1058fe6d68e67","observation_id":"d72283e4-28ef-4e34-a3d0-feddf376213a","resolution":{"observed_at":"2026-08-07T12:46:55.044999Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:54.841957Z","title":"Gemini: A family of highly capable multimodal models, 2025","venue":null,"work_id":"eafa700c-c1b5-4f7a-8a74-51a566c036b4","year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.356553Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:2724810cbd4bb92f6cff510fbe1764e770609026d93ecee9172970ed0b96d29e","observation_id":"95342513-c714-4ea1-8426-46851d6dfad0","resolution":{"observed_at":"2026-08-07T12:46:54.891325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:54.711038Z","title":"Qwen technical report, 2023","venue":null,"work_id":"ff2523d6-0ebc-4bd2-b112-c3f3ea368dc5","year":2023},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.425911Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:b398635a2602b9cf3a31e6382fe2115aa6a7f57e32a54ed31374c0834850f5e1","observation_id":"c867aadb-5927-4c46-9dc8-d14acb312c8c","resolution":{"observed_at":"2026-08-07T12:46:54.771591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:54.543508Z","title":"Neural discrete representation learning","venue":null,"work_id":"39d5a10f-15e4-4b13-91b0-f2e07cbfecf0","year":2017},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.477712Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:57872c327a2e8ea23ce3f611d1dc018ba9bc634a61c6031832c8c885c06be816","observation_id":"9ecfaeb2-d0e0-4cd1-81e5-b186005608ca","resolution":{"observed_at":"2026-08-07T12:46:54.606369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.19325","last_updated":"2025-05-18T02:27:31Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-25T03:38:06Z","title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.19325","snapshot_observed_at":"2026-08-07T12:46:47.553558Z","title":"Long-context autoregressive video modeling with next-frame prediction.CoRR, abs/2503.19325, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.553558Z"},"links":{"cited_paper":"/paper/2503.19325","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:d43e09447c4a7b9aee049e6e32dee91c4f5ef31fb1e6248f779b7ed586748422","observation_id":"fed357c7-d03f-43b7-b084-9698b3cea670","resolution":{"observed_at":"2026-08-07T12:46:47.553558Z","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":"2026-08-07T12:46:54.399621Z","title":"Vector-quantized image modeling with improved VQGAN","venue":null,"work_id":"82d04dc8-3896-47e5-adc9-554a34e60ad0","year":2022},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.605998Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:723851a6f679a0d167a10550af195a53f08a8b4e8967c84fc00bf20aacd77c1c","observation_id":"316ea204-d21e-4210-8d45-57ef8ba94ff0","resolution":{"observed_at":"2026-08-07T12:46:54.455120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:54.245487Z","title":"consistencydecoder.https://github.com/openai/consistencydecoder, 2023","venue":null,"work_id":"a4dcead6-73e3-4a26-a606-9f3ecd5eb2d8","year":2023},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.667123Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:d2057e2f3dc7c45259f5fd81dc405e3324eeab8570219ca755daed245cbc967b","observation_id":"3e8f5478-5fd2-46c8-ae86-02e172096ec6","resolution":{"observed_at":"2026-08-07T12:46:54.308521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04081","last_updated":"2025-05-28T19:15:39Z","snapshot_observed_at":"2026-07-06T19:28:18.775189Z","submitted_at":"2024-10-05T08:27:53Z","title":"Epsilon-VAE: Denoising as Visual Decoding","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04081","snapshot_observed_at":"2026-08-07T12:46:47.729995Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.729995Z"},"links":{"cited_paper":"/paper/2410.04081","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:ac7f7a48e781d0a90be757da2a8aead88638f6f288f144c2f3ff801594253c93","observation_id":"29b6e9f4-6ec3-4d52-8b38-a40df98700e2","resolution":{"observed_at":"2026-08-07T12:46:47.729995Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10812","last_updated":"2024-10-14T17:59:42Z","snapshot_observed_at":"2026-08-09T17:44:55.180658Z","submitted_at":"2024-10-14T17:59:42Z","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10812","snapshot_observed_at":"2026-08-07T12:46:47.784895Z","title":"HART: efficient visual generation with hybrid autoregressive transformer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.784895Z"},"links":{"cited_paper":"/paper/2410.10812","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:fb85b98fd7517008e7ec2db6c3ca787299b61d82bc94544ebdfeefbf50cfa336","observation_id":"6b6c5137-aafc-4905-9915-c36de8743a07","resolution":{"observed_at":"2026-08-07T12:46:47.784895Z","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":"2026-08-07T12:46:47.839343Z","title":"Flow to the mode: Mode-seeking diffusion autoencoders for state-of-the-art image tokenization.arXiv, abs/2503.11056, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.839343Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:52dadda0cf798183e5b120d2d4c109ec1ed63967b61376b4b2f59e0d1fc510ca","observation_id":"cca8bd1c-7bc7-40ba-8abd-4317c47d6275","resolution":{"observed_at":"2026-08-07T12:46:47.839343Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.18593","last_updated":"2025-01-30T18:59:37Z","snapshot_observed_at":"2026-08-10T02:35:35.003821Z","submitted_at":"2025-01-30T18:59:37Z","title":"Diffusion Autoencoders are Scalable Image Tokenizers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.18593","snapshot_observed_at":"2026-08-07T12:46:47.896319Z","title":"Diffusion autoen- coders are scalable image tokenizers.arXiv, abs/2501.18593, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.896319Z"},"links":{"cited_paper":"/paper/2501.18593","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:a2a9dff2443397fbe3a2871a4a1d1795ee03ceed274e62b6781a19377c6b2a6e","observation_id":"f9f6a167-692f-43c5-9e9b-258d056fdc24","resolution":{"observed_at":"2026-08-07T12:46:47.896319Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.08685","last_updated":"2025-07-28T09:59:52Z","snapshot_observed_at":"2026-08-07T17:12:09.965154Z","submitted_at":"2025-03-11T17:59:41Z","title":"\"Principal Components\" Enable A New Language of Images","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.08685","snapshot_observed_at":"2026-08-07T12:46:47.951311Z","title":"principal components","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.951311Z"},"links":{"cited_paper":"/paper/2503.08685","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:d4ebb44d4333cca93f28fc6d1447461b034ecfec380f1b26d530353970884049","observation_id":"28319137-1daa-4ce8-ad0f-920983ee29a3","resolution":{"observed_at":"2026-08-07T12:46:47.951311Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13967","last_updated":"2025-06-04T12:56:23Z","snapshot_observed_at":"2026-08-07T18:04:12.028140Z","submitted_at":"2025-02-19T18:59:44Z","title":"FlexTok: Resampling Images into 1D Token Sequences of Flexible Length","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13967","snapshot_observed_at":"2026-08-07T12:46:47.998604Z","title":"Flextok: Resampling images into 1d token sequences of flexible length.arXiv, abs/2502.13967, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.998604Z"},"links":{"cited_paper":"/paper/2502.13967","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:5b15e12aaab04b415bdc07de6c0fe0f1f5bc242dd255fd8f9777220d188d8a49","observation_id":"325af286-6860-4494-83b2-e583c74728b9","resolution":{"observed_at":"2026-08-07T12:46:47.998604Z","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":"2026-08-07T12:46:54.077777Z","title":"Kingma and Max Welling","venue":null,"work_id":"0e42fd9d-38c6-46c9-9b05-3ec83f669887","year":2014},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.065178Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:682c66f2163487c9ea4f9693727a1266520c214631c4ed59a7e519e9b357b148","observation_id":"9934654c-9867-45f0-bfde-f83ad63e7a00","resolution":{"observed_at":"2026-08-07T12:46:54.161492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:53.931474Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":"11ed1e87-50a7-439a-be00-5c2bedc078f6","year":2022},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.126391Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:fda7872413ccd582b4ad0fd05f438c02ffe5eeef0b38deac14ebbeca574b7fd3","observation_id":"6966e6d1-650c-4e97-aecc-be070dd3e8dc","resolution":{"observed_at":"2026-08-07T12:46:53.985745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.14666","last_updated":"2025-04-20T16:14:28Z","snapshot_observed_at":"2026-08-07T16:00:45.229157Z","submitted_at":"2025-04-20T16:14:28Z","title":"Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.14666","snapshot_observed_at":"2026-08-07T12:46:48.181078Z","title":"Generative multimodal pretraining with discrete diffusion timestep tokens.arXiv, abs/2504.14666, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.181078Z"},"links":{"cited_paper":"/paper/2504.14666","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:2f88b47a8780722fca28015d61082422e5eefe54cc18c60e4f1ceb6bea475f28","observation_id":"855a524b-5a6f-4049-9406-2c283f74792c","resolution":{"observed_at":"2026-08-07T12:46:48.181078Z","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":"2026-08-07T12:46:53.810531Z","title":"An image is worth 32 tokens for reconstruction and generation.Advances in Neural Information Processing Systems, 37:128940–128966, 2024","venue":null,"work_id":"61035911-d1ad-42f9-9fea-cf3c8668e6d3","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.241560Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:f74aba5f05b41f51fdafe827bd9eed48676de3f00eb1fd61cc730c4d94001411","observation_id":"8879aa26-61a5-4ec0-9da7-ca1d08784bcc","resolution":{"observed_at":"2026-08-07T12:46:53.864890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:53.671154Z","title":"Gomez, Lukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":"ded2a6b7-a054-4473-a550-79f456bda268","year":2017},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.297165Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:8301edf9dd6851049c0d5318a2ae90d46a73a431f43934c08f489c35d5caa2a3","observation_id":"bba06e3a-0d78-4188-8753-832dc7b13fab","resolution":{"observed_at":"2026-08-07T12:46:53.744013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:53.529347Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":"261568e4-8121-469d-a0b0-54775bc51750","year":2023},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.362277Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:4ba26f7a332a57237faab4e0d382e7fe33de2983f3b88330d45a8714900d7bf5","observation_id":"5385c25c-defb-4cd7-89d3-ed105ffad586","resolution":{"observed_at":"2026-08-07T12:46:53.583535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:53.370812Z","title":"Albergo, Nicholas M","venue":null,"work_id":"0fb11c65-bffb-4747-bb1a-e0b439d891bf","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.438333Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:790087acc8557465f257addf3d90e8ec7668a0029cc93f7ea92ccfb22317dea1","observation_id":"7d3a0bb2-49ad-405f-87f2-092907dfaa40","resolution":{"observed_at":"2026-08-07T12:46:53.440867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:53.249953Z","title":"Soda: Bottleneck diffusion models for representation learning","venue":null,"work_id":"a810901a-2e68-47fd-b255-ed0365e75750","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.493970Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:7174f3666c28cb112bd922dcc1e1eca7302ceff1f5b90865a8ca1eea17cd4e81","observation_id":"ae76940d-f15a-4eb2-a203-64cb01d7d059","resolution":{"observed_at":"2026-08-07T12:46:53.302150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15505","last_updated":"2023-10-12T07:55:05Z","snapshot_observed_at":"2026-07-06T16:24:17.829828Z","submitted_at":"2023-09-27T09:13:40Z","title":"Finite Scalar Quantization: VQ-VAE Made Simple","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15505","snapshot_observed_at":"2026-08-07T12:46:48.586612Z","title":"Finite scalar quantization: Vq-vae made simple.arXiv preprint arXiv:2309.15505, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.586612Z"},"links":{"cited_paper":"/paper/2309.15505","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:ce442c2544cd31f360e02011be0b533119df42a8d5506091e297e9c943ff289a","observation_id":"76b2d064-cefe-479f-9802-f4884573b7dd","resolution":{"observed_at":"2026-08-07T12:46:48.586612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05737","last_updated":"2024-03-29T17:44:41Z","snapshot_observed_at":"2026-08-02T18:23:02.746177Z","submitted_at":"2023-10-09T14:10:29Z","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05737","snapshot_observed_at":"2026-08-07T12:46:48.646407Z","title":"Language model beats diffusion–tokenizer is key to visual generation.arXiv preprint arXiv:2310.05737, 2023","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.646407Z"},"links":{"cited_paper":"/paper/2310.05737","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:8daa2e9bcbf0afacdf64c7606f0bb654d8e27056c835392fb119f51535a98d0b","observation_id":"9bf76024-39b9-4abb-9a0d-a710eca451f5","resolution":{"observed_at":"2026-08-07T12:46:48.646407Z","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":"2026-08-07T12:46:53.114899Z","title":"Courville","venue":null,"work_id":"a164cbc8-830f-4fd3-91e0-b04bea060928","year":2018},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.718076Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:510c6d81cd29f2fa6c134710d7237b2d29da8287fc9d66f9bb8e9755f4f27e38","observation_id":"ff439393-75df-4481-ad94-fbde8cbe8c92","resolution":{"observed_at":"2026-08-07T12:46:53.177354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:52.948380Z","title":"simple diffusion: End-to-end diffusion for high resolution images","venue":null,"work_id":"1ebe0c88-325d-4ef8-9829-a12ca6264841","year":2023},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.808089Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:9301c0fce5a58d8bc570236a0c1dd275379b67c3a5f95b2aa161a994f11983ce","observation_id":"fd52ed4f-e766-4136-b248-9e4b077a9001","resolution":{"observed_at":"2026-08-07T12:46:53.024188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19324","last_updated":"2025-03-22T19:42:20Z","snapshot_observed_at":"2026-07-06T19:39:33.077694Z","submitted_at":"2024-10-25T06:20:06Z","title":"Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.19324","snapshot_observed_at":"2026-08-07T12:46:48.877251Z","title":"Simpler diffusion (sid2): 1.5 FID on imagenet512 with pixel-space diffusion.arXiv, abs/2410.19324, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.877251Z"},"links":{"cited_paper":"/paper/2410.19324","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:535a08c8073d2a2245753c8327e3ab25e6d03f0bef8746dc2320b329f0d7989b","observation_id":"5372283d-689e-4f8b-bc24-59a8a11c1638","resolution":{"observed_at":"2026-08-07T12:46:48.877251Z","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":"2026-08-07T12:46:52.778417Z","title":"Efros, Eli Shechtman, and Oliver Wang","venue":null,"work_id":"2a571467-d264-4f04-b6dc-e6eace0aa409","year":2018},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:48.977094Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:2d532571db30db801d0bf71adb3413caa218a45c2c832cfa030d1203cf8170a0","observation_id":"97779e07-a3b2-4fd9-8923-cc6859c5518d","resolution":{"observed_at":"2026-08-07T12:46:52.864653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.06940","last_updated":"2025-06-18T04:35:42Z","snapshot_observed_at":"2026-07-06T19:30:26.233621Z","submitted_at":"2024-10-09T14:34:53Z","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.06940","snapshot_observed_at":"2026-08-07T12:46:49.073670Z","title":"Representation alignment for generation: Training diffusion transformers is easier than you think","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:49.073670Z"},"links":{"cited_paper":"/paper/2410.06940","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:5672a11e2da7910d1546d95aa74b929e8dd25d1998db94a678aad071e2cae524","observation_id":"80d725be-ea0b-4133-a641-eae7ac0b35e8","resolution":{"observed_at":"2026-08-07T12:46:49.073670Z","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":"2026-08-07T12:46:52.614014Z","title":"Scaling rectified flow transformers for high-resolution image synthesis","venue":null,"work_id":"93b08f83-fbd2-4906-a5af-ad2fc30df8e7","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:49.162173Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:381cd992a415ed4335a83700f9cc1977ebdc79de46d83e97a2ee667e792ef458","observation_id":"46b4bd64-a50c-4d01-9915-319b3508432c","resolution":{"observed_at":"2026-08-07T12:46:52.695190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-08-12T19:28:23.372660Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-07T12:46:49.234889Z","title":"Classifier-free diffusion guidance.arXiv, abs/2207.12598, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:49.234889Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:1a9acd8e18be4ee0b902de0bb3464c67994df248c48c9cf4d76de37417dd5f02","observation_id":"687b383d-1854-4407-9eed-2dd2db344223","resolution":{"observed_at":"2026-08-07T12:46:49.234889Z","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":"2026-08-07T12:46:52.437170Z","title":"Root mean square layer normalization","venue":null,"work_id":"fcbe9fba-d4d4-4975-8940-14290f62d147","year":null},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:49.328346Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:b870fa43fa3d78a83295d07a8f5d1ef9d0f5029a4d0f13daf2fdfbc3d3093d70","observation_id":"d863ca36-185a-41c7-a4eb-eae09dca3f1b","resolution":{"observed_at":"2026-08-07T12:46:52.519790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05202","last_updated":"2020-02-12T19:57:13Z","snapshot_observed_at":"2026-08-11T06:21:56.129166Z","submitted_at":"2020-02-12T19:57:13Z","title":"GLU Variants Improve Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05202","snapshot_observed_at":"2026-08-07T12:46:49.393422Z","title":"GLU variants improve transformer.arXiv, abs/2002.05202, 2020","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:49.393422Z"},"links":{"cited_paper":"/paper/2002.05202","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:a05afb58c9a11cddbf94d75362596b9a6dba6d32388829de5f653701635f186b","observation_id":"3305620b-3e66-49d0-b7d0-cf7a90c8bd08","resolution":{"observed_at":"2026-08-07T12:46:49.393422Z","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":"2026-08-07T12:46:52.280147Z","title":null,"venue":null,"work_id":"17e7b49d-1739-4bb2-9ce1-c1a08e7cfc98","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:49.496155Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:1cee90d1ea1924a76d907f61a433229f3c4b27feb5d6b117c4043ef6690a4add","observation_id":"bc4ebb81-7754-4ea1-8188-7201e12cb79c","resolution":{"observed_at":"2026-08-07T12:46:52.351782Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:52.117396Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":"eff412c8-61c2-431f-9021-90ff8250cfef","year":2015},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:49.589964Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:409cf6f783c9c90efbe2991d160886423d80c2a7be5fe0a09e3e3a6b5cb54806","observation_id":"6368fa96-e6dc-4ac5-b6fe-cfa727010e68","resolution":{"observed_at":"2026-08-07T12:46:52.204911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-07T12:46:49.660399Z","title":"Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:49.660399Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:b3a1f5c39b556442a7ef5d21a10dce7265f3781e4338ec135a4639db387f4086","observation_id":"0f1ac33e-816f-4432-a5b5-b9c28b561e86","resolution":{"observed_at":"2026-08-07T12:46:49.660399Z","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":"2026-08-07T12:46:51.961181Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","venue":null,"work_id":"c9c67006-4de5-4997-9b86-d5105287eab8","year":null},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:49.766127Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:4e43f34c4dcc707eaed5f44a186de426ef60d4d3983b5521bce654fd5b56fd74","observation_id":"cff7d735-a358-4a25-9363-bd122bb32b7a","resolution":{"observed_at":"2026-08-07T12:46:52.046547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:49.846399Z","title":"Improved techniques for training gans.Advances in neural information processing systems, 29, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:49.846399Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:93630aaba66eaeb028d21173c869ef268de8b28970865d41a715dde6ae26f874","observation_id":"7288a251-59ad-46cc-a52b-2766905c1ca9","resolution":{"observed_at":"2026-08-07T12:46:49.846399Z","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":"2026-08-07T12:46:51.809855Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":"35551c4b-91f9-4e33-999c-74292cacc13c","year":2021},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:49.923905Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:f9106e893b760077234e08655ebf05b003689a06f1f4a6c3d94c11edf22e9eed","observation_id":"43d01ad3-7397-4900-9ab6-b8e9019691a2","resolution":{"observed_at":"2026-08-07T12:46:51.877309Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:51.690993Z","title":"With an Explanation of the Method of Integration Employed in Constructing the Tables Which Give the Theoretical Forms of Such Drops","venue":null,"work_id":"e2b78ca8-d282-4c67-b207-ae672b31bbb7","year":null},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:50.002950Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:523cb8b61a9c08f7a8ccd670a64b98a9130cd87353a8864c9107f3a1ec29c685","observation_id":"a8af3289-c862-4f5b-9275-f24204b80e62","resolution":{"observed_at":"2026-08-07T12:46:51.734187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:51.525918Z","title":null,"venue":null,"work_id":"51492b3f-b289-4790-ae05-a1dd21ef866f","year":2022},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:50.077736Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:8d0c631c4f7ebce484f4e089077f42af38ee73ac4dfd0c3301f8ef6ff0a1792d","observation_id":"1bc34565-56ec-4936-929c-50fdf2b5c808","resolution":{"observed_at":"2026-08-07T12:46:51.581439Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:51.357519Z","title":"Scalable image tokenization with index backpropagation quantization.arXiv, 2024","venue":null,"work_id":"2e997b0d-d12c-4a43-b2b4-d95f8398c441","year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:50.178482Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:aa411c300b8a4f6b76650dfe18f31061665bdb4943a2ed42871b64ab7073193b","observation_id":"1ca93848-08df-464a-a1ef-b0d7cee22c3b","resolution":{"observed_at":"2026-08-07T12:46:51.432509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-08-12T08:59:05.030983Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-08-07T12:46:50.265973Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:50.265973Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:3a7a398046137527237d9f989ede6df6581833f9793663105d8b5362620840e3","observation_id":"c8d65a22-8cc1-4505-953d-979ad1703584","resolution":{"observed_at":"2026-08-07T12:46:50.265973Z","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":"2026-08-07T12:46:51.172421Z","title":"Sigmoid-weighted linear units for neural network function approximation in reinforcement learning.Neural Networks, 107:3–11, 2018","venue":null,"work_id":"ff5f9b2e-3a9b-4cf9-9b1b-de0e6c1fea46","year":2018},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:50.334376Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:e03bf5232ead7e19963e8dfc5dec8174b598156f1737d34ae7d9d08a5b9f51a9","observation_id":"d5bca98a-29ab-4de7-9040-623c354f0860","resolution":{"observed_at":"2026-08-07T12:46:51.285726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T12:46:51.047937Z","title":"Query-key normaliza- tion for transformers","venue":null,"work_id":"dff792b0-a860-44de-aa12-f2a063588454","year":2020},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:50.422272Z"},"links":{"citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:992ad4f7fd0c01205bcc28d8f7cdbdfe66d0c53cd25c02aa01a20ff7b9d77c24","observation_id":"9ec4b6cb-412a-4de5-a580-0ff4622bf5a4","resolution":{"observed_at":"2026-08-07T12:46:51.108689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models"},"reference_resolution":{"displayed":78,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":0,"verified_fuzzy":49},"total_outbound_references":78},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 78 of 78 outbound references and 3 inbound Pith citation observations for arXiv:2505.23660."}