{"as_of":"2026-08-08T20:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d01a6f246df5b6285e04c0b27835857932a58486cc5b039d35cffaa297ad1d8f","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:27:20.833525Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T15:27:55.009337Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T22:26:16.863070Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"cited_work":{"arxiv_id":"2506.18226","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.18226","snapshot_observed_at":"2026-07-01T22:26:16.863070Z","title":"Make it efficient: Dynamic sparse attention for autoregressive image generation.arXiv preprint arXiv:2506.18226, 2025","venue":null,"work_id":"69217d51-fc10-4c1d-a2fe-bacfca966451","year":2025},"citing_paper":{"arxiv_id":"2606.02436","last_updated":"2026-06-01T16:08:43Z","snapshot_observed_at":"2026-08-02T13:17:50.493694Z","submitted_at":"2026-06-01T16:08:43Z","title":"Geometry-Aware Implicit Memory for Video World Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-06-28T15:27:55.009337Z"},"links":{"cited_paper":"/paper/2506.18226","citing_paper":"/paper/2606.02436"},"observation_digest":"sha256:c78080ef170819a79fdbf936c313014383992159e381d097d4448b55316b203f","observation_id":"4fcd77ff-6021-49ed-856b-2672110cab3a","resolution":{"observed_at":"2026-07-01T22:26:16.864916Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.18226/citation-record","integrity":"/paper/2506.18226/integrity","json":"/paper/2506.18226/citation-record.json","paper":"/paper/2506.18226"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:27:20.710302Z","title":"Roformer: Enhanced transformer with rotary position embedding.Neurocomputing, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.710302Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:a726c6d04945633e9cb07bbb3f2944b2bf034696fdc1b8d8968c81020a0860c4","observation_id":"a57953e6-d5a0-4555-a578-137d39854d1e","resolution":{"observed_at":"2026-08-06T23:27:20.710302Z","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":"2026-08-06T23:27:21.202755Z","title":"Qwen technical report","venue":null,"work_id":"01c2a4eb-7d8e-471f-8ae5-2921ca6b84d1","year":2023},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.714087Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:fc9761a45bf23ae68dc16722c026ad5f939ea01c98fc3412b1d457b14be35305","observation_id":"6376b9e8-ec9b-41f9-967b-6758eebd25c8","resolution":{"observed_at":"2026-08-06T23:27:21.207103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.192090Z","title":"Llama: Open and efficient foundation language models.CoRR, 2023","venue":null,"work_id":"47751569-11a6-4653-a450-6fd34ced78e7","year":2023},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.717670Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:afeaba956093fc90ab3aaa7c1f5fb80885e23a6891beb966b9bf4087768b2262","observation_id":"55825ece-416b-42ef-add4-380a2c90047f","resolution":{"observed_at":"2026-08-06T23:27:21.195706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.182382Z","title":"Llama 2: Open foundation and fine-tuned chat models.CoRR, 2023","venue":null,"work_id":"54c52a76-2085-4c98-9416-816269673fb7","year":2023},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.721103Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:4448d3730ee037e0d623b027720df88097b93d0f05a6115c09ef9cd663ab6b1d","observation_id":"10bccf2e-5536-458d-95e1-e2474ecf3e08","resolution":{"observed_at":"2026-08-06T23:27:21.185783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.171876Z","title":null,"venue":null,"work_id":"292ddb08-89ac-426b-8160-ccaa5ec5a3c9","year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.724496Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:f93bfa4670f047ef3a5a105cb044585daca2f5c1afd3ab0d72fa85520ae70006","observation_id":"c803ace4-978b-4fa0-8ded-77e938f5b716","resolution":{"observed_at":"2026-08-06T23:27:21.175041Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.161756Z","title":"GPT-4 technical report.CoRR, 2023","venue":null,"work_id":"d968e7f6-15c8-4662-b1dc-0825b632645b","year":2023},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.727814Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:e413ddf305edd99a82e453ebf0f56c8713e1bffa617af5cb18ada8221fec3ffe","observation_id":"3544f0f8-db91-4951-8592-06fac6825064","resolution":{"observed_at":"2026-08-06T23:27:21.165352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.151758Z","title":"Autore- gressive model beats diffusion: Llama for scalable image generation.CoRR, 2024","venue":null,"work_id":"fd39d35c-e3b7-4125-a662-777bb7d2a442","year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.731423Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:68723c5a147c2877a7e997bd39aeb76ecdcc11a0d235e76e9bf04987305eb9d8","observation_id":"1cb0e3ec-ca12-41f2-a96b-eabdf50f7ffb","resolution":{"observed_at":"2026-08-06T23:27:21.155562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.735216Z","title":"Autoregressive image generation without vector quantization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.735216Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:b9fee9b88e52f6c1f6b182fed3a90aa988ad62d294b2026b2c8470cb61dd0c4f","observation_id":"219e9c64-fa8e-4255-b767-c4ecd79eb445","resolution":{"observed_at":"2026-08-06T23:27:20.735216Z","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":"2026-08-06T23:27:20.738395Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.738395Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:6d204397fd336caf2caace3b414df5a0703131a5791e2bc903a16446985c0b3b","observation_id":"3df6ad3b-1128-4bc5-a8e8-ce85bc690382","resolution":{"observed_at":"2026-08-06T23:27:20.738395Z","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":"2026-08-06T23:27:21.130150Z","title":"Freeman, Michael Rubinstein, Yuanzhen Li, and Dilip Krishnan","venue":null,"work_id":"95aea993-6ca5-4784-8738-51f21ae78e7b","year":2023},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.741445Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:1bdbcf2d1ba26adc2f1a65bf4f8880a7dd3a502176181a293188ba47aa7a3278","observation_id":"c825669e-6c9c-43b4-b222-69b5cbe982e7","resolution":{"observed_at":"2026-08-06T23:27:21.133299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.744661Z","title":"Neural discrete representation learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.744661Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:d55068b14dedd6ed74012df4e4000780baec2d589aa30fbc3ab39914f44ef9c0","observation_id":"96c0083c-2ecb-46e3-946b-bf815b604178","resolution":{"observed_at":"2026-08-06T23:27:20.744661Z","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":"2026-08-06T23:27:20.747754Z","title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.747754Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:47b64551e41d3a45bf03012114e5ef066cc1a60fbba6a2d31e28759d17cc1a96","observation_id":"27294b00-80d8-4f4e-a9ec-6622f4e646f5","resolution":{"observed_at":"2026-08-06T23:27:20.747754Z","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":"2026-08-06T23:27:21.108789Z","title":"Semhitok: A unified image tokenizer via semantic-guided hierarchical codebook for multimodal understanding and generation.CoRR, 2025","venue":null,"work_id":"b68ec81c-acea-476c-9edb-130e3cab3025","year":2025},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.750615Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:ae041dc50f49267f67b443979d8d8706f4dd12795223d45af1cce5aa1d01622b","observation_id":"58867405-ad5f-40c5-b608-64e8623d0bfe","resolution":{"observed_at":"2026-08-06T23:27:21.111936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.098961Z","title":"Robust latent matters: Boosting image generation with sampling error synthesis","venue":null,"work_id":"cdd1ec8d-5c18-4c39-9f3e-199e87992350","year":2025},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.753693Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:b4d38672680f2a9da4573b8e2e57453f465b50575b1cacb2f56cf8078bc40650","observation_id":"d117cc41-ce87-4b06-aa30-a7425d56d5a3","resolution":{"observed_at":"2026-08-06T23:27:21.102120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.089971Z","title":"Subobject-level image tokenization.CoRR, 2024","venue":null,"work_id":"f781d940-74e8-4c70-ad1f-b30b0dc7addf","year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.757157Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:accb394a925e47cb51da9cd0a1c629f062b0cd906db0c40a8b2d111658935f52","observation_id":"57962df8-83d7-47b9-8ec1-49ed5a6a3f53","resolution":{"observed_at":"2026-08-06T23:27:21.092735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.079222Z","title":"Unitok: A unified tokenizer for visual generation and understanding.CoRR, 2025","venue":null,"work_id":"1ea7bc08-a67c-4a3d-b09c-b9d9e468bfe1","year":2025},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.760270Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:ac7103470ed8a86a231b9db95a305abf59bc988b06324dd047938f850a95c9d0","observation_id":"eeba3c8f-a8e1-4c06-adb4-78cbed64c72e","resolution":{"observed_at":"2026-08-06T23:27:21.082560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.067736Z","title":"Imagefolder: Autoregressive image generation with folded tokens.CoRR, 2024","venue":null,"work_id":"fe8b0595-1d8b-4434-8db9-bcd995016a66","year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.763312Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:46c78647813600577a2f75a5d29b8bf2e1bafa3b6bc5b42d97ccfee31943c1d5","observation_id":"d54674ac-b4bc-4fbd-b61d-66a976357295","resolution":{"observed_at":"2026-08-06T23:27:21.071626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.057911Z","title":"Infllm: Training-free long-context extrapolation for llms with an efficient context memory","venue":null,"work_id":"90129219-a32a-4d5d-aa49-b3fd1034bbfd","year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.766264Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:bc4e92af41512dafa359138635450384e5c8f230a94cd6fa31ff8b214a69935e","observation_id":"4d8ddda0-34be-4f06-b933-3683a9eb2f49","resolution":{"observed_at":"2026-08-06T23:27:21.061344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.047649Z","title":"Reattention: Training-free infinite context with finite attention scope","venue":null,"work_id":"c374ec98-3e32-469d-b2a3-7df1cc252277","year":2025},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.769494Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:9df73cb89b820f64fbb1370280288fd85778ff4ec4b75be363bfc81a9a147eb0","observation_id":"fcfaf2f2-bfaf-4d76-ab72-236fd107746e","resolution":{"observed_at":"2026-08-06T23:27:21.051400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.772771Z","title":"Efficient streaming language models with attention sinks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.772771Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:e8838fbf9c6389f8529afaeed5eb123b113c81fe02c675e271f5c3e432492444","observation_id":"26bf444c-de2c-4d73-8f7c-1c33077510f6","resolution":{"observed_at":"2026-08-06T23:27:20.772771Z","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":"2026-08-06T23:27:21.031644Z","title":"Generating long sequences with sparse transformers.CoRR, 2019","venue":null,"work_id":"50a64fa5-5567-4851-9e3a-7b9d9439a37c","year":2019},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.775989Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:afc97baee4513fe35863e556c3b046cf79745aa01bf099279303c216cb7d1558","observation_id":"a235ac60-16ce-4429-9601-b8e44b9e8a99","resolution":{"observed_at":"2026-08-06T23:27:21.035383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.020623Z","title":"Zipar: Accelerating auto-regressive image generation through spatial locality.CoRR, 2024","venue":null,"work_id":"04e19f03-96b7-4e55-b149-32031d428e59","year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.779138Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:fc577dd5aaaeec0d981ec1e57201c06a4f3aaa90f4e8621cfdbc6a0a6e5d572c","observation_id":"106cd0a3-751f-451a-8aec-5ef0a0dc22dd","resolution":{"observed_at":"2026-08-06T23:27:21.024395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:21.010455Z","title":"Freeman, and Yu-Xiong Wang","venue":null,"work_id":"0cbf97fa-1e05-4c59-afca-38237f57a24b","year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.782393Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:b5151c21915f3ce319564571ee99066924fa9cbc45a52128b5cdce77436c89a6","observation_id":"b09f64e9-4b65-4091-b261-8dc5ad02924b","resolution":{"observed_at":"2026-08-06T23:27:21.013863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.999174Z","title":"Neighboring autoregressive modeling for efficient visual generation.CoRR, 2025","venue":null,"work_id":"624524c9-94c8-43a8-a940-190a7a441c76","year":2025},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.786404Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:37baa0a853ff960e61343d174890253e332f9029a0534a0a8ba6fa81487b0ff9","observation_id":"a3f57708-e743-4a45-b6cf-dd688903f9fb","resolution":{"observed_at":"2026-08-06T23:27:21.003001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.988615Z","title":"Frequency autoregressive image generation with continuous tokens.CoRR, 2025","venue":null,"work_id":"abc4989f-837d-42bf-ba81-5122adfccb2f","year":2025},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.789224Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:adb586a0956b2aff942186db4f8c97e30b49681aa697041d71374776acbc4cc7","observation_id":"1e1fb317-9b2d-4480-a5ee-adaebc23f8db","resolution":{"observed_at":"2026-08-06T23:27:20.992695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.977134Z","title":"Fluid: Scaling autoregressive text-to-image generative models with continuous tokens.CoRR, 2024","venue":null,"work_id":"33d2c6b1-bec6-49c0-aaca-bab0843bb0b2","year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.792185Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:cef3d3c507e578ba9e0c21be844477eddf699484e556f041e2481ad78b7f9d19","observation_id":"0db071da-37a9-432a-b085-8e55996af523","resolution":{"observed_at":"2026-08-06T23:27:20.980948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.795500Z","title":"Vector-quantized image modeling with improved VQGAN","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.795500Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:3a41b08604681d8150fb30bdd0222524b55cb4ccda5376749657595a1a718993","observation_id":"ef710ed3-e26b-4ada-b6c2-ad8ed9fffb93","resolution":{"observed_at":"2026-08-06T23:27:20.795500Z","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":"2026-08-06T23:27:20.798502Z","title":"Zero-shot text-to-image generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.798502Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:f5ed916dc33da41257f90e0151323c49994ba84ae06cf57c4160301b3f33e66a","observation_id":"811eeea0-07e0-4558-b17f-64129b2e5a21","resolution":{"observed_at":"2026-08-06T23:27:20.798502Z","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":"2026-08-06T23:27:20.954278Z","title":"Autoregressive image generation with randomized parallel decoding.CoRR, 2025","venue":null,"work_id":"c149856d-9a4c-4e4d-b648-97f3741101a3","year":2025},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.801538Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:5279ebb702d28491124db525944814d3aaaf5bacdad46f824060a6fdf050b5a1","observation_id":"eb4e0df4-385b-485e-938e-7a912103a8d9","resolution":{"observed_at":"2026-08-06T23:27:20.958255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.942861Z","title":"Focus directions make your language models pay more attention to relevant contexts.CoRR, 2025","venue":null,"work_id":"da8363e4-638c-4830-95d9-7776a214a9d9","year":2025},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.804516Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:108f439ed7618d018bd968efae652b6a9f2e41ee1166181150dc53106f1eac5c","observation_id":"9054ea29-2404-4562-aae1-75bfb44dd058","resolution":{"observed_at":"2026-08-06T23:27:20.946490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.932367Z","title":"When attention sink emerges in language models: An empirical view.ICLR, 2025","venue":null,"work_id":"63e208de-ecdb-4f49-8300-a5345f0dc724","year":2025},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.807511Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:7844be6d97fa6037c87d7430fa2afece8a05922b7dd7a352e2a6e0ee7ee3a81f","observation_id":"5b82b4a1-31c1-4e12-825a-9ff4d231344c","resolution":{"observed_at":"2026-08-06T23:27:20.936387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.922076Z","title":"Longheads: Multi-head attention is secretly a long context processor.CoRR, 2024","venue":null,"work_id":"97138b3d-ca7b-4ed1-a4ae-bf5416c5b354","year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.810916Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:291df99b175b5bd787914414926dad1a5a3a19307f919821a25a1d788abf7e7a","observation_id":"e0574fcd-8ed5-4bb5-aa53-a8177c21a68f","resolution":{"observed_at":"2026-08-06T23:27:20.925565Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.911632Z","title":"Minference 1.0: Accelerating pre-filling for long-context llms via dynamic sparse attention","venue":null,"work_id":"903d4331-d502-4b53-88b7-19f6ea435904","year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.813975Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:ac774f183aeb05e4de281b99a1e1f1788db0a6717ad0e08ce1f7828ad1647634","observation_id":"60f71def-6b12-4108-96c2-fc609415ee51","resolution":{"observed_at":"2026-08-06T23:27:20.915192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.901496Z","title":"Retrievalattention: Accelerating long-context LLM inference via vector retrieval.CoRR, 2024","venue":null,"work_id":"be2b4ba7-0b2d-4b0e-870c-0c8acf93ccf7","year":2024},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.816939Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:3eda9303f67715dee77ccdbfd7ba5b86f6b31772144f417e7f47b086d83b19b2","observation_id":"a05cb066-f064-41a8-a698-11f3f3c2882b","resolution":{"observed_at":"2026-08-06T23:27:20.905014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.820592Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.820592Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:1e38ccd84952f964496c0220499a7a2382d0283df77af2e91eed1a4173d3599e","observation_id":"99b3be7a-6ee8-4fca-9564-ee128fb8b1ba","resolution":{"observed_at":"2026-08-06T23:27:20.820592Z","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":"2026-08-06T23:27:20.824126Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.824126Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:057e07bde068a6b36fff397916cf0e2093cbd677cd1a36b5996f5b3439b25e6f","observation_id":"e34148a0-8d4e-4e9f-8c5c-30d9c7c04f67","resolution":{"observed_at":"2026-08-06T23:27:20.824126Z","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":"2026-08-06T23:27:20.878740Z","title":"Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen","venue":null,"work_id":"ff87e741-bf49-4c76-bfa9-434932361431","year":2016},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.827252Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:ad468b4ee86fc3d373524be204d447c6e7b008b2aebee32a3a5e4638be47aa87","observation_id":"e680b3b8-e884-424c-b0f5-317688d22db5","resolution":{"observed_at":"2026-08-06T23:27:20.882392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T23:27:20.830482Z","title":"Scaling up gans for text-to-image synthesis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.830482Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:30438a7c5ee7272a297b728b9f6f170ca8a73f068ec1e1861720f6a8911f41b8","observation_id":"4d0a9e11-36d7-4d11-b884-6810086032f8","resolution":{"observed_at":"2026-08-06T23:27:20.830482Z","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":"2026-08-06T23:27:20.858611Z","title":"High-resolution image synthesis with latent diffusion models.CVPR, 2022","venue":null,"work_id":"a555fbd7-2344-4a74-a610-aab42965a5a3","year":2022},"citing_paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:20.833525Z"},"links":{"citing_paper":"/paper/2506.18226"},"observation_digest":"sha256:06a12ebe3dd468ab2c56caa4fe89811b22efd90615f4449b8e8922eedc50a352","observation_id":"5548042f-edc5-490f-9521-3ad89833ff9c","resolution":{"observed_at":"2026-08-06T23:27:20.864282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.18226","last_updated":"2025-06-23T01:27:06Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T23:20:48.408782Z","submitted_at":"2025-06-23T01:27:06Z","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":27},"total_outbound_references":39},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2506.18226."}