{"as_of":"2026-08-05T03:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aaa6801244af7718c36bdd5a7e470c69c6cfa55bbee0937feb6665d6ffe40282","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-13T05:54:24.248910Z","state":"measured"},{"denominator":26,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":26,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-14T15:30:23.485228Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.09430","snapshot_observed_at":"2026-07-14T15:30:23.485228Z","title":"arXiv , author =:2605.09430v2 , primaryclass =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.09803","last_updated":"2026-07-09T17:52:16Z","snapshot_observed_at":"2026-07-16T23:18:02.281790Z","submitted_at":"2026-07-09T17:52:16Z","title":"Spectral Origins of the Self-Correction Blind Spot in Autoregressive Generation","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-07-14T15:30:23.485228Z"},"links":{"cited_paper":"/paper/2605.09430","citing_paper":"/paper/2607.09803"},"observation_digest":"sha256:6eb37767bd635f61bf54d8c64f321ec80184f6d3fd4cdcbb576258fb12774cd4","observation_id":"d1ca4ecb-7b30-4800-9a5d-c9bf0f4190f4","resolution":{"observed_at":"2026-07-14T15:30:23.485228Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.09430","snapshot_observed_at":"2026-07-14T04:10:14.360463Z","title":"Flashar: Efficient post-training acceleration for autoregressive image generation, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.11643","last_updated":"2026-07-13T14:57:58Z","snapshot_observed_at":"2026-08-03T10:58:25.857415Z","submitted_at":"2026-07-13T14:57:58Z","title":"Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-07-14T04:10:14.360463Z"},"links":{"cited_paper":"/paper/2605.09430","citing_paper":"/paper/2607.11643"},"observation_digest":"sha256:728968bc7016573cf67e65c39978180ad43b6d381df5e9bab47a32694adddd8a","observation_id":"0414151a-9e34-412c-a634-0586e1233a1f","resolution":{"observed_at":"2026-07-14T04:10:14.360463Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2605.09430/citation-record","integrity":"/paper/2605.09430/integrity","json":"/paper/2605.09430/citation-record.json","paper":"/paper/2605.09430"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.09573","last_updated":"2025-05-17T21:15:02Z","snapshot_observed_at":"2026-08-03T23:49:05.512328Z","submitted_at":"2025-03-12T17:43:40Z","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","version":3},"cited_work":{"arxiv_id":"2503.09573","doi":"10.48550/arxiv.2503.09573","metadata_source":"pith","pith_arxiv_id":"2503.09573","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","venue":"cs.LG","work_id":"b34ab928-6ffb-4028-b13c-395a8924d76b","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2503.09573","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:0bd36f50d7e92810211bee8b5a827420108cda8cc8abad77bae093b17cc0761d","observation_id":"58df8b08-5569-4e19-b870-2de04b899fb2","resolution":{"observed_at":"2026-05-15T10:59:41.530185Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16609","last_updated":"2023-09-28T17:07:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-28T17:07:49Z","title":"Qwen Technical Report","version":1},"cited_work":{"arxiv_id":"2309.16609","doi":"10.48550/arxiv.2309.16609","metadata_source":"pith","pith_arxiv_id":"2309.16609","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Qwen Technical Report","venue":"cs.CL","work_id":"bb1fd52f-6b2f-437c-9516-37bdf6eb9be8","year":2023},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2309.16609","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:d630aa1033b851b7506449a7f4ec6cd8a0dcf8b8e091e78a7cea139839381eae","observation_id":"01e36f9c-31a2-4afd-aa22-b482b9038559","resolution":{"observed_at":"2026-05-13T06:02:23.723037Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-15T23:50:15.620681+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T23:50:15.620681+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.18095","last_updated":"2025-06-22T16:51:09Z","snapshot_observed_at":"2026-07-06T21:45:57.248156Z","submitted_at":"2025-06-22T16:51:09Z","title":"ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation","version":1},"cited_work":{"arxiv_id":"2506.18095","doi":"10.48550/arxiv.2506.18095","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.18095","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Sharegpt-4o-image: Aligning multimodal models with gpt-4o-level image generation","venue":"arXiv (Cornell University)","work_id":"089b1c33-975f-4482-9c6f-590a1181c2dd","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2506.18095","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:a68a49689bac0d87dacb83b4328abb95962665e283fee82132347dae3eb7e352","observation_id":"0c7faca6-810c-47fd-a7bb-81d967daa41a","resolution":{"observed_at":"2026-05-13T06:02:23.630811Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2509.24900","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T20:32:37.617033Z","title":"Opengpt-4o-image: A compre- hensive dataset for advanced image generation and editing","venue":null,"work_id":"f07ca17f-4c08-44bb-ad68-8cc8d865bf89","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:4165214f099516945073ef67d94320de600e4e04336a9f22d8e422c7dfd323c2","observation_id":"4895c73c-42b5-4497-af09-ef72cc4f9346","resolution":{"observed_at":"2026-05-13T06:02:23.688588Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2510.24717","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-05T11:41:02.742677Z","title":"Uniform discrete diffusion with metric path for video generation","venue":null,"work_id":"46e2b2d9-625d-40fc-9e32-3a068b28e74f","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:50f17ae3e69e0cb14fa548f8ae22e0cae9bc0b55937782fdcb154e56f50a473f","observation_id":"24c30f45-c64c-4dc8-86c7-adf4a7e67b5a","resolution":{"observed_at":"2026-05-13T06:02:23.652337Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.05496","last_updated":"2024-12-07T01:46:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-07T01:46:38Z","title":"Flex Attention: A Programming Model for Generating Optimized Attention Kernels","version":1},"cited_work":{"arxiv_id":"2412.05496","doi":"10.48550/arxiv.2412.05496","metadata_source":"pith","pith_arxiv_id":"2412.05496","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Flex Attention: A Programming Model for Generating Optimized Attention Kernels","venue":"cs.LG","work_id":"692b9d44-343b-4635-a0dc-1ee8fe539aa3","year":2024},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2412.05496","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:6ca44b89d08c2524da7ba8a90ac475f2200dc79ac612c19b3b1ad6c3d08f74fe","observation_id":"0a7e3915-f12f-4216-9621-199304ffeb80","resolution":{"observed_at":"2026-05-17T21:27:16.810492Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-05-24T05:54:39.898364+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T05:54:39.898364+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22058","last_updated":"2025-07-29T17:59:04Z","snapshot_observed_at":"2026-08-03T01:06:06.514446Z","submitted_at":"2025-07-29T17:59:04Z","title":"X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again","version":1},"cited_work":{"arxiv_id":"2507.22058","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.22058","snapshot_observed_at":"2026-07-04T13:39:51.493261Z","title":"X-omni: Reinforcement learning makes discrete autoregressive image generative models great again","venue":null,"work_id":"3ee0ee57-31b9-49d4-98fc-c12c499a14b9","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2507.22058","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:485e8c691d2ecb204db38ae641c4fdd870e58c72be0e520f09f0f0966c3bde02","observation_id":"6fbafad0-7943-4e3c-a57c-805ae01e18ad","resolution":{"observed_at":"2026-05-13T06:02:23.706601Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":"2207.12598","doi":"10.1109/cvpr52733.2024.02494","metadata_source":"pith","pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Classifier-Free Diffusion Guidance","venue":"cs.LG","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","year":2022},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:6de9ea9132f840ae1594dcb4ef74979ad3270614a0b752a8df47fb8e39518c9a","observation_id":"77989242-f5db-4178-b5aa-5fbe956d59ce","resolution":{"observed_at":"2026-05-13T06:02:23.719981Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.03355","last_updated":"2025-03-02T07:45:09Z","snapshot_observed_at":"2026-07-06T19:27:37.936219Z","submitted_at":"2024-10-04T12:21:03Z","title":"LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding","version":3},"cited_work":{"arxiv_id":"2410.03355","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.03355","snapshot_observed_at":"2026-07-02T12:36:56.878710Z","title":"Lantern: Accelerating visual autoregressive models with relaxed speculative decoding.arXiv preprint arXiv:2410.03355","venue":null,"work_id":"ee85ac36-3a42-40af-b226-b338bc2180d3","year":2024},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2410.03355","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:b83c35dbc8f680f4005335643511789560786c0d4e009f3c2808d3f5ac704473","observation_id":"3bc7113d-5ac9-496b-bf3f-364882fc2d2d","resolution":{"observed_at":"2026-05-13T06:02:23.677292Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2503.10568","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T12:26:57.152022Z","title":"Autoregressive image generation with randomized parallel decoding.arXiv preprint arXiv:2503.10568","venue":null,"work_id":"98f984f3-b06f-43f2-80e7-69d0c53c99f8","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:af993876b1086bc807c8a2a97b55d2e251105e791289772853a62f38847de42f","observation_id":"bcaf70f0-2236-4510-8b1c-90e55658aaf2","resolution":{"observed_at":"2026-05-13T06:02:23.695333Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.02657","last_updated":"2025-04-24T16:16:27Z","snapshot_observed_at":"2026-07-06T18:57:05.603342Z","submitted_at":"2024-08-05T17:46:53Z","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","version":3},"cited_work":{"arxiv_id":"2408.02657","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2408.02657","snapshot_observed_at":"2026-07-04T03:49:30.628376Z","title":"Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multimodal gener- ative pretraining, 2024a","venue":null,"work_id":"c0d2d00b-1774-4161-8f99-a6e142cfa281","year":2024},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2408.02657","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:9d1e3ad9dd8d509ae84faed56443c0fface1f2c3b8facd545089ee9bd71bee2f","observation_id":"23a5030c-42ef-4c75-8a0a-fd9a0293c645","resolution":{"observed_at":"2026-05-13T06:02:23.659868Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.23606","last_updated":"2026-04-13T07:14:16Z","snapshot_observed_at":"2026-07-06T21:33:02.686798Z","submitted_at":"2025-05-29T16:15:48Z","title":"Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model","version":4},"cited_work":{"arxiv_id":"2505.23606","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.23606","snapshot_observed_at":"2026-07-04T16:09:57.601747Z","title":"Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model","venue":"cs.LG","work_id":"d9362ac2-4e03-4696-ab0c-aa7f2419766a","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2505.23606","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:50f7817880a787f3ec6c28a1b836a29d62f0dd61366b132e19cef9e168b25dff","observation_id":"fe295582-0207-4928-8f43-03047967a51c","resolution":{"observed_at":"2026-05-13T06:02:23.663453Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.02013","last_updated":"2025-06-15T18:27:17Z","snapshot_observed_at":"2026-08-01T16:50:50.645857Z","submitted_at":"2025-02-04T05:03:42Z","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","version":2},"cited_work":{"arxiv_id":"2502.02013","doi":"10.48550/arxiv.2502.02013","metadata_source":"pith","pith_arxiv_id":"2502.02013","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","venue":"cs.LG","work_id":"7b4ac06a-e804-4f0a-8305-c45f2735afb5","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2502.02013","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:de8fff9c3b3856105525078f3f4b6873090cbd9abfe579701eab75d8e03911ef","observation_id":"216d043b-7da5-4d20-9463-6e1dae92f61c","resolution":{"observed_at":"2026-05-15T16:30:37.615120Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06525","last_updated":"2024-06-10T17:59:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-06-10T17:59:52Z","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","version":1},"cited_work":{"arxiv_id":"2406.06525","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.06525","snapshot_observed_at":"2026-07-10T11:37:03.266757Z","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","venue":"cs.CV","work_id":"41efe203-9377-4c63-b1d6-e499cd6e46f6","year":2024},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2406.06525","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:402eb5bee510c8472ed917626f026edffd08a53168e149e8bd74aab50e1f28ac","observation_id":"8969a9c6-bf9a-4a1f-8966-acfd79a99ebb","resolution":{"observed_at":"2026-05-13T06:02:23.713752Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10812","last_updated":"2024-10-14T17:59:42Z","snapshot_observed_at":"2026-07-06T19:33:16.949210Z","submitted_at":"2024-10-14T17:59:42Z","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","version":1},"cited_work":{"arxiv_id":"2410.10812","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.10812","snapshot_observed_at":"2026-07-04T19:30:07.385096Z","title":"Hart: Efficient visual generation with hybrid autoregressive transformer","venue":null,"work_id":"f23a6c6a-d9ec-429a-ae86-a7c2eb330bfe","year":2024},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2410.10812","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:7dfefe615e096b1158bf6f84c09269543d4444af9e049fa6ed7fc12a38e49bc8","observation_id":"fa2313cd-6497-4c9e-b290-a757d6e2f27f","resolution":{"observed_at":"2026-05-13T06:02:23.674076Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":"2312.11805","doi":"10.1038/nrn2888","metadata_source":"pith","pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Gemini: A Family of Highly Capable Multimodal Models","venue":"cs.CL","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","year":2023},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:09b53a2aaa0dea017ef61a97bb0c8aa1530846de0e092fc7ec3d196c838fd2f4","observation_id":"4e9329a1-62bc-44bf-89c2-14961553bc73","resolution":{"observed_at":"2026-05-13T06:02:23.698720Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.10711","last_updated":"2025-08-18T15:55:23Z","snapshot_observed_at":"2026-07-06T22:13:00.029560Z","submitted_at":"2025-08-14T14:54:22Z","title":"NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale","version":2},"cited_work":{"arxiv_id":"2508.10711","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.10711","snapshot_observed_at":"2026-07-04T00:39:17.418338Z","title":"Nextstep-1: Toward autoregressive image generation with continuous tokens at scale","venue":null,"work_id":"729ea32c-8dd9-4636-a635-97e1ebb2dcd7","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2508.10711","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:83e5d210947f3cba59fb5d543ebce95e96896074cb9e735cdf1136b3c814804d","observation_id":"36307d51-2891-4ee9-a280-0fe07ea3e4e9","resolution":{"observed_at":"2026-05-13T06:02:23.624188Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01699","last_updated":"2025-03-04T04:33:27Z","snapshot_observed_at":"2026-07-06T19:26:12.102947Z","submitted_at":"2024-10-02T16:05:27Z","title":"Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding","version":2},"cited_work":{"arxiv_id":"2410.01699","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.01699","snapshot_observed_at":"2026-06-29T19:13:53.264576Z","title":"Ac- celerating auto-regressive text-to-image generation with training-free speculative jacobi decoding","venue":null,"work_id":"8d0a1748-adf2-411e-a794-e89498c7f06f","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2410.01699","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:1b278a8d16e275b6f176b031178b450775a919957c6b35b61d179df02986de7b","observation_id":"f7c93f33-e7ce-4cb3-9aa4-65e1fc0b4d70","resolution":{"observed_at":"2026-05-13T06:02:23.710551Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":"2302.13971","doi":"10.48550/arxiv.2302.13971","metadata_source":"pith","pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"LLaMA: Open and Efficient Foundation Language Models","venue":"cs.CL","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","year":2023},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:a5fcde8d1ed0b5bb12058c3380f644d1356efbdb7b069f112f1e097a35b87db9","observation_id":"0c4869ac-8db9-4b36-9e3d-97bcb9f6fc7c","resolution":{"observed_at":"2026-05-13T06:02:23.716776Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-01T11:08:05.851253+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-01T11:08:05.851253+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.11455","last_updated":"2025-04-15T17:59:46Z","snapshot_observed_at":"2026-07-06T21:09:55.394184Z","submitted_at":"2025-04-15T17:59:46Z","title":"SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL","version":1},"cited_work":{"arxiv_id":"2504.11455","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.11455","snapshot_observed_at":"2026-07-05T11:41:02.764172Z","title":"Simplear: Pushing the frontier of autoregressive visual generation through pretraining, sft, and rl","venue":"cs.CV","work_id":"facbbd34-503d-4c9a-b758-a9b88c18d9c6","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2504.11455","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:f8199ffa50770d8490dab01b8805cc5cf77e09ee126dbca71d435b396c0d5b58","observation_id":"7e4053d4-2612-4068-b274-78a090f03660","resolution":{"observed_at":"2026-05-13T06:02:23.667247Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.17801","last_updated":"2025-07-23T17:42:13Z","snapshot_observed_at":"2026-07-06T22:01:54.769256Z","submitted_at":"2025-07-23T17:42:13Z","title":"Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling","version":1},"cited_work":{"arxiv_id":"2507.17801","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.17801","snapshot_observed_at":"2026-07-02T12:26:57.121388Z","title":"Lumina-mgpt 2.0: Stand-alone autoregressive image modeling","venue":null,"work_id":"2896fd3e-8491-4e55-9d46-cb03727f853f","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2507.17801","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:19bf11b5a228d06ecd1cd70db3206b0e7083bc99cc5a53acb14a13b430d984fe","observation_id":"286ac545-9494-45ae-8642-fff3ef966c8a","resolution":{"observed_at":"2026-05-13T06:02:23.702712Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":"2505.09388","doi":"10.1016/j.aiopen.2022.12","metadata_source":"pith","pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Qwen3 Technical Report","venue":"cs.CL","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:501f8906e7af487eee59225e503ac6d65bc394a8b551060497ad71544a59d4b4","observation_id":"6f56ecbc-cf62-415c-9272-9e26aecc2636","resolution":{"observed_at":"2026-05-13T06:02:23.684977Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10789","last_updated":"2022-06-22T01:11:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-06-22T01:11:29Z","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":"2206.10789","doi":"10.48550/arxiv.2206.10789","metadata_source":"pith","pith_arxiv_id":"2206.10789","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","venue":"cs.CV","work_id":"0a105815-ff2e-43ce-8566-966cdcae1af4","year":2022},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"cited_paper":"/paper/2206.10789","citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:da0731395e02b1611122fe010eef2c2455323c732f07bc79837f6fe086621dc6","observation_id":"9ff55bda-251c-4cfb-8aba-df5b878a3218","resolution":{"observed_at":"2026-05-13T06:02:23.670463Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2507.01957","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T03:49:30.595267Z","title":"Locality-aware parallel decoding for efficient autoregressive image generation.arXiv preprint arXiv:2507.01957","venue":null,"work_id":"d815f197-ea83-417a-b567-76a2eddc3863","year":2025},"citing_paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-13T05:54:24.248910Z"},"links":{"citing_paper":"/paper/2605.09430"},"observation_digest":"sha256:633426b888b81f98ef656fc8f6e3b0ae3aa557cb566cd1b429db7bc7fa197548","observation_id":"93467342-a379-476c-b658-492ecec8926c","resolution":{"observed_at":"2026-05-13T06:02:23.691848Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.09430","last_updated":"2026-05-12T03:20:13Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T23:21:30.897592Z","submitted_at":"2026-05-10T09:07:20Z","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":0,"verified_exact":23,"verified_fuzzy":0},"total_outbound_references":24},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 2 inbound Pith citation observations for arXiv:2605.09430."}