{"as_of":"2026-08-08T11:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e4253bf5d7f2a8d346c573c2b254240166c3bd45798261041474c7a69918e820","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:33:48.499614Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T10:28:59.577056Z","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":"2026-06-30T10:34:36.605549Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"cited_work":{"arxiv_id":"2505.14673","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.14673","snapshot_observed_at":"2026-06-30T10:34:36.605549Z","title":"arXiv:2505.14673 (2025)","venue":null,"work_id":"6c26151b-6cd7-4e30-95a8-27d2cc48dec3","year":2025},"citing_paper":{"arxiv_id":"2604.11720","last_updated":"2026-04-13T16:56:48Z","snapshot_observed_at":"2026-07-06T23:00:03.762376Z","submitted_at":"2026-04-13T16:56:48Z","title":"On the Robustness of Watermarking for Autoregressive Image Generation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-10T16:14:14.170230Z"},"links":{"cited_paper":"/paper/2505.14673","citing_paper":"/paper/2604.11720"},"observation_digest":"sha256:38c04678c87b0a93fdb52ffda5fc92571192bdb4b4b9ee8246eb2765bdcb4954","observation_id":"4fa2f5f2-5c67-4b47-8103-72345a85a971","resolution":{"observed_at":"2026-05-11T09:06:00.787284Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"cited_work":{"arxiv_id":"2505.14673","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.14673","snapshot_observed_at":"2026-06-30T10:34:36.605549Z","title":"arXiv:2505.14673 (2025)","venue":null,"work_id":"6c26151b-6cd7-4e30-95a8-27d2cc48dec3","year":2025},"citing_paper":{"arxiv_id":"2605.25967","last_updated":"2026-05-25T15:43:20Z","snapshot_observed_at":"2026-08-04T17:39:39.402173Z","submitted_at":"2026-05-25T15:43:20Z","title":"Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-29T23:08:06.858906Z"},"links":{"cited_paper":"/paper/2505.14673","citing_paper":"/paper/2605.25967"},"observation_digest":"sha256:9d599b8fddf59628033f613c366fda73511db75ad1e1fab9de95417c8582da52","observation_id":"b8a8272a-ba1e-4b82-bdbb-ee62653fda3a","resolution":{"observed_at":"2026-06-29T23:14:01.883638Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"cited_work":{"arxiv_id":"2505.14673","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.14673","snapshot_observed_at":"2026-06-30T10:34:36.605549Z","title":"arXiv:2505.14673 (2025)","venue":null,"work_id":"6c26151b-6cd7-4e30-95a8-27d2cc48dec3","year":2025},"citing_paper":{"arxiv_id":"2606.28386","last_updated":"2026-06-22T17:06:05Z","snapshot_observed_at":"2026-08-02T11:08:25.094268Z","submitted_at":"2026-06-22T17:06:05Z","title":"Data Provenance for Image Auto-Regressive Generation","version":1},"reference_index":197,"source":"arxiv_source","source_observed_at":"2026-06-30T10:28:59.577056Z"},"links":{"cited_paper":"/paper/2505.14673","citing_paper":"/paper/2606.28386"},"observation_digest":"sha256:4d47c047011510c3c6ce12ba2172075b1216f8de2682a418b1d5950bccc4cf0f","observation_id":"995dae10-0008-4230-acea-974077a8d0ed","resolution":{"observed_at":"2026-06-30T10:34:36.606880Z","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/2505.14673/citation-record","integrity":"/paper/2505.14673/integrity","json":"/paper/2505.14673/citation-record.json","paper":"/paper/2505.14673"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:33:43.334734Z","title":"Combined dwt-dct digital image watermarking.Journal of computer science, 3(9):740–746, 2007","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:43.334734Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:e45c44fd69ae6a925d2a1ed3c5d4f8f26824cb66b3dd53102acf58a547fa0f7b","observation_id":"6278deea-6d8d-4039-8d64-337d7efd6460","resolution":{"observed_at":"2026-08-07T15:33:43.334734Z","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":"2026-08-07T15:33:43.512135Z","title":"Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:43.512135Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:d30ab5a753edc29c83946c433ea58d950b32e9433e4f002133d644e0c4f21af7","observation_id":"d93f8f3c-7cb3-4f35-9dfd-0bebd04d15d3","resolution":{"observed_at":"2026-08-07T15:33:43.512135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.07228","last_updated":"2024-12-01T17:59:04Z","snapshot_observed_at":"2026-08-07T07:36:23.924329Z","submitted_at":"2018-02-20T18:07:50Z","title":"The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.07228","snapshot_observed_at":"2026-08-07T15:33:43.680801Z","title":"The malicious use of artificial intelligence: Forecasting, prevention, and mitigation.arXiv preprint arXiv:1802.07228, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:43.680801Z"},"links":{"cited_paper":"/paper/1802.07228","citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:bc93ea99d1b5e4b4009e911c13368e6bee675b7564bfbecd5b3c7a81e9956712","observation_id":"651e6a72-5ee3-41bb-9daf-2e4d4e95d65c","resolution":{"observed_at":"2026-08-07T15:33:43.680801Z","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":"2026-08-07T15:33:43.847198Z","title":"Reproducible scaling laws for contrastive language-image learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:43.847198Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:f11cd2b4023df3fc8ab9d126fe2220e3f491dbe7f510617933b0906ec5e2b7da","observation_id":"b8fba076-67e4-4b5b-bb55-c2a2cdb1204d","resolution":{"observed_at":"2026-08-07T15:33:43.847198Z","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":"2026-08-07T15:33:44.019969Z","title":"Morgan kaufmann, 2007","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:44.019969Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:6317b784cf6b094ad8aba404a4ac6ed09d6c7d56a6f8c739b6ca620edef8b5ac","observation_id":"e1f6452b-bfd2-4bc8-b722-8d7303139276","resolution":{"observed_at":"2026-08-07T15:33:44.019969Z","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":"2026-08-07T15:33:44.132806Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:44.132806Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:816df2630f76b5f17213ce5b14ffcfd4d66b35c92a890dc84b9d6ad19d9e37da","observation_id":"bdef4fc2-b879-4719-af2a-a3c4012aa28b","resolution":{"observed_at":"2026-08-07T15:33:44.132806Z","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":"2026-08-07T15:33:44.290828Z","title":"Paths, trees, and flowers.Canadian Journal of mathematics, 17:449–467, 1965","venue":null,"work_id":null,"year":1965},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:44.290828Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:ae9cda8ed54fe73a516e4cdb9ceff8f11a6abb3d7e33ebdf5b663150b1a68923","observation_id":"bf91de7f-5d40-4c48-bdc4-0f7a1172a1d4","resolution":{"observed_at":"2026-08-07T15:33:44.290828Z","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":"2026-08-07T15:33:44.424451Z","title":"Taming transformers for high-resolution image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:44.424451Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:9e9d295293c163665e283dcd42be11568df1d7b0526a308c9b6f85fab1ba5ae1","observation_id":"5f3c9e0d-ce70-443e-9d11-81b80b9adb59","resolution":{"observed_at":"2026-08-07T15:33:44.424451Z","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":"2026-08-07T15:33:52.187227Z","title":"John Wiley & Sons, 1991","venue":null,"work_id":"28787f88-dc0a-4cc1-a7e9-8c6e670672f1","year":1991},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:44.551003Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:e130de6edf335a9c71a5d806ee90e5d9fc60f2f04582a574fe063c571b059b79","observation_id":"61a0f4dd-3fec-487d-92ba-e4f52a462af1","resolution":{"observed_at":"2026-08-07T15:33:52.318213Z","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":"2026-08-07T15:33:51.949840Z","title":"The sta- ble signature: Rooting watermarks in latent diffusion models","venue":null,"work_id":"87452428-5ee7-4df5-96a5-626506612599","year":2023},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:44.715706Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:df74bc4751e77a3add38bb3fe8d991f7aac61e75042ccce6176bd46ff9d1c426","observation_id":"f6b6fb7f-6868-4666-88b5-9a024e44c71b","resolution":{"observed_at":"2026-08-07T15:33:52.053544Z","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":{"arxiv_id":"2503.16194","last_updated":"2025-03-20T14:41:29Z","snapshot_observed_at":"2026-08-07T16:49:00.665982Z","submitted_at":"2025-03-20T14:41:29Z","title":"Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction","version":1},"cited_work":{"arxiv_id":"2503.16194","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.16194","snapshot_observed_at":"2026-08-07T15:33:49.221722Z","title":"Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction","venue":"cs.CV","work_id":"3e9d895a-6a90-4327-806e-c289e8a0a05d","year":2025},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:44.838613Z"},"links":{"cited_paper":"/paper/2503.16194","citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:c25cd4af4a759dd12f541b1b34b8b45bc212b186d131440cd72a2e8f6cfb8390","observation_id":"6f5dcc0f-2881-47b9-b994-9a0a0ebbde96","resolution":{"observed_at":"2026-08-07T15:33:49.409679Z","resolver_source":"local_arxiv","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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:33:44.937866Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:44.937866Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:8a84f5c882322a92e47c247e4b06aec27074eecf4c3fc09c1c0f1737f1c33066","observation_id":"a75ce0b5-e95a-4aff-9b5e-1c4da2e38a4b","resolution":{"observed_at":"2026-08-07T15:33:44.937866Z","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":"2026-08-07T15:33:45.054097Z","title":"Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:45.054097Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:817b553c4d817652aab3cb648d186bf9b41e14e49e12571a340ea1b59befd6c7","observation_id":"eddf57c5-aee6-4776-8572-eb60bcda8222","resolution":{"observed_at":"2026-08-07T15:33:45.054097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.00880","last_updated":"2025-03-15T12:31:42Z","snapshot_observed_at":"2026-07-06T20:15:31.955797Z","submitted_at":"2025-01-01T15:58:51Z","title":"Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.00880","snapshot_observed_at":"2026-08-07T15:33:45.200999Z","title":"Improving autoregressive visual generation with cluster-oriented token prediction.arXiv preprint arXiv:2501.00880, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:45.200999Z"},"links":{"cited_paper":"/paper/2501.00880","citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:f0c44d064bf9e3f16eba337be4ce180f886779bad5be3e9d9f4cbba3a2dd9bb1","observation_id":"e35dfaf5-dc24-4630-b731-ed655de0b07c","resolution":{"observed_at":"2026-08-07T15:33:45.200999Z","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":"2026-08-07T15:33:45.317674Z","title":"Robin: Robust and invisible watermarks for diffusion models with adversarial optimization.Advances in Neural Information Processing Systems, 37:3937–3963, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:45.317674Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:6713eebc765bf7cf6f0d426a528a4f1ba1fd3eed13f95f4874288154b21ef8fa","observation_id":"c92f8eb4-354e-4d26-81ed-96760bdc1433","resolution":{"observed_at":"2026-08-07T15:33:45.317674Z","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":"2026-08-07T15:33:51.694609Z","title":"White house rolls out plan to promote ethical ai, 2023","venue":null,"work_id":"2318829c-98b5-4571-b3ed-2e87b85cab87","year":2023},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:45.430279Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:4ea5a4a1a9ab48de1d86f066a8d48d03d8abcf7b8672ade5e14d3e9f718ae388","observation_id":"e45fd87c-4e14-4a61-a151-6e3e86c1df8d","resolution":{"observed_at":"2026-08-07T15:33:51.784434Z","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":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-07T15:33:45.597539Z","title":"Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:45.597539Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:c350473ef3547b76e4bc73a952adcfd490572fbbe9e0282a50d85afa5f9de7ac","observation_id":"c8b08e88-c499-40b4-bea6-8b5e4eea994d","resolution":{"observed_at":"2026-08-07T15:33:45.597539Z","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":"2026-08-07T15:33:51.440312Z","title":"A watermark for large language models","venue":null,"work_id":"29b69a86-2958-43b7-9ad6-75dc6ecddbc3","year":2023},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:45.703546Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:f10858bf7375eb5d94cf57ba6a5602f4c9ee0d4b963b487fef0ce4a3766326ea","observation_id":"fafaf2e2-4b41-4014-b8b8-98229f7d30ec","resolution":{"observed_at":"2026-08-07T15:33:51.501829Z","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":"2026-08-07T15:33:45.816667Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:45.816667Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:ffb86e711e0edafa57de097f1ff2fc23170b05a69c57b9aadcb14e6503221809","observation_id":"d1d76832-697e-488c-91a6-85abfae86f1a","resolution":{"observed_at":"2026-08-07T15:33:45.816667Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.04410","last_updated":"2025-02-09T08:59:19Z","snapshot_observed_at":"2026-08-06T03:43:29.067278Z","submitted_at":"2024-09-06T17:14:53Z","title":"Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.04410","snapshot_observed_at":"2026-08-07T15:33:45.914528Z","title":"Open- magvit2: An open-source project toward democratizing auto-regressive visual generation.arXiv preprint arXiv:2409.04410, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:45.914528Z"},"links":{"cited_paper":"/paper/2409.04410","citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:11ba7cedc682f94571c5e0cc8196be4235a3b3587ffb6c0c1a8b188c8e1b4318","observation_id":"35050779-3373-4db8-86c4-6890e908910d","resolution":{"observed_at":"2026-08-07T15:33:45.914528Z","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":"2026-08-07T15:33:51.157534Z","title":"Dwt- dct-svd based watermarking","venue":null,"work_id":"d0e9a996-1449-49a4-9505-acf29b600fb5","year":2008},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:46.008403Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:6dfadc3c246a3462931c2b2cf3c1517a640b938b93cefafa6244ff8e61225c91","observation_id":"34a1cf44-c923-4a66-ba13-a3985ea95340","resolution":{"observed_at":"2026-08-07T15:33:51.262429Z","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":"2026-08-07T15:33:50.946293Z","title":"The maximum weight perfect matching problem for complete weighted graphs is in pc","venue":null,"work_id":"793c178c-cb41-4a8a-a657-423fcc136f0a","year":1990},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:46.118473Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:e57618d2e5fd7f864b38d8529837ed1d32c7bed6eee2aa86c9945d2c12f32abe","observation_id":"91f58445-e21d-41ec-a7fb-bc517c060a3c","resolution":{"observed_at":"2026-08-07T15:33:51.075944Z","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":"2026-08-07T15:33:46.199223Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:46.199223Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:750fadd97ba2380fbd827d40fadd293921d5790427e5269a5fb4ed14cd9184bc","observation_id":"a1d5165f-e5d9-426c-a04f-1febc8fadbbb","resolution":{"observed_at":"2026-08-07T15:33:46.199223Z","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":"2026-08-07T15:33:46.281619Z","title":"Lawa: Using latent space for in-generation image watermarking","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:46.281619Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:7376f8c0610f5b9cb0f89eb810125bb84a7c7d02f243ac72e25edf15859882f2","observation_id":"3b59532f-f34d-47dd-996f-71433a912a69","resolution":{"observed_at":"2026-08-07T15:33:46.281619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06525","snapshot_observed_at":"2026-08-07T15:33:46.445944Z","title":"Autoregressive model beats diffusion: Llama for scalable image generation.arXiv preprint arXiv:2406.06525, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:46.445944Z"},"links":{"cited_paper":"/paper/2406.06525","citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:ddd5564b0d6e6956bd6be025468b0999930f2a694f73513c8a1497ebb69fb497","observation_id":"6f620d81-b008-4cbb-810a-723fe716375b","resolution":{"observed_at":"2026-08-07T15:33:46.445944Z","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":"2026-08-07T15:33:46.539861Z","title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction.Advances in neural information processing systems, 37:84839–84865, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:46.539861Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:8edd561f2d87a335726f892a6b2c88a39158f62eca98d00c33f84ff08d342819","observation_id":"5b0d2f80-4a9e-4ddb-b69f-a054c2a495e7","resolution":{"observed_at":"2026-08-07T15:33:46.539861Z","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":"2026-08-07T15:33:46.643654Z","title":"Con- ditional image generation with pixelcnn decoders.Advances in neural information processing systems, 29, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:46.643654Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:1dd0b4b321b4bfbf94a44116b64759ae1a8239d069d501674de1a7b537630832","observation_id":"71f23ce2-86d3-41c4-93e3-42be2b9b9dbf","resolution":{"observed_at":"2026-08-07T15:33:46.643654Z","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":"2026-08-07T15:33:46.772770Z","title":"Pixel recurrent neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:46.772770Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:cbd987c9857943690c23d4671c9786dddeb97bd4195c0bc3bc31cdc9cd32b94e","observation_id":"2ea778bc-ebdf-4905-97d7-73d642c8f4fc","resolution":{"observed_at":"2026-08-07T15:33:46.772770Z","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":"2026-08-07T15:33:46.931470Z","title":"Neural discrete representation learning.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:46.931470Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:e29c2c41aa7c46ab5c0acb5b06aa2feba60539c65ff625fd58e44492df1e25e7","observation_id":"2ae94214-a303-45fc-a3ad-3f1e477696be","resolution":{"observed_at":"2026-08-07T15:33:46.931470Z","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":"2026-08-07T15:33:47.050511Z","title":"Attention is all you need.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:47.050511Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:474c1159a511914653c2cc4910bd04d36163bbfbe15e61dcb55adb6284af863e","observation_id":"9df5b52c-41ff-491c-9e43-d201bc6c90cf","resolution":{"observed_at":"2026-08-07T15:33:47.050511Z","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":"2026-08-07T15:33:50.452360Z","title":"An online propaganda campaign used ai-generated headshots to create fake journalists.V erge","venue":null,"work_id":"a9fdc203-cba8-4a0c-bb4f-7c479bbc8a44","year":2020},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:47.174320Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:6a0ceb2137ee4c68db657e77014a054589c982a1b2e8fc9f6b73b62ff5c853fe","observation_id":"ccc888c2-c983-4af4-aeec-86d05c6ca0a5","resolution":{"observed_at":"2026-08-07T15:33:50.594564Z","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":"2026-08-07T15:33:47.237779Z","title":"Image quality assessment: from error visibility to structural similarity.IEEE transactions on image processing, 13(4):600– 612, 2004","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:47.237779Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:d98a460369a45470013a870f9601ff9979c7eeac87246df6025eaed100bab7e6","observation_id":"b1932f1b-fd12-4318-9d77-6cabbca8ba69","resolution":{"observed_at":"2026-08-07T15:33:47.237779Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.11324","last_updated":"2025-03-14T11:45:10Z","snapshot_observed_at":"2026-08-07T17:04:13.235608Z","submitted_at":"2025-03-14T11:45:10Z","title":"Safe-VAR: Safe Visual Autoregressive Model for Text-to-Image Generative Watermarking","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.11324","snapshot_observed_at":"2026-08-07T15:33:47.357961Z","title":"Safe-var: Safe visual autoregressive model for text-to-image generative watermarking.arXiv preprint arXiv:2503.11324, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:47.357961Z"},"links":{"cited_paper":"/paper/2503.11324","citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:7b79e57d768721f7856527b09b5ff7d7c718f854f691e7a289c5996f74bd4bd1","observation_id":"f7058cd2-5b8f-43e5-9ebc-65c8f41ae370","resolution":{"observed_at":"2026-08-07T15:33:47.357961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.20030","last_updated":"2023-07-04T03:52:06Z","snapshot_observed_at":"2026-08-04T13:34:47.513256Z","submitted_at":"2023-05-31T17:00:31Z","title":"Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.20030","snapshot_observed_at":"2026-08-07T15:33:47.493399Z","title":"Tree-ring watermarks: Fingerprints for diffusion images that are invisible and robust.arXiv preprint arXiv:2305.20030, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:47.493399Z"},"links":{"cited_paper":"/paper/2305.20030","citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:445ca95fcaf551b5621bfbec4c6c737e2c5ae5798b0658c73ccd8895987ab606","observation_id":"a37dccbd-b440-4fbb-b894-6dbcc1d9e281","resolution":{"observed_at":"2026-08-07T15:33:47.493399Z","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":"2026-08-07T15:33:50.226813Z","title":"Microsoft pledges to watermark ai-generated images and videos, 2023","venue":null,"work_id":"6394ab6a-f3f3-4e09-865a-d74895863307","year":2023},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:47.623351Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:31ef556cc5a43d2e59771393b424a98bd523f942aa12d99f840eb05fddab5fa8","observation_id":"817e9c4b-5ac3-4355-b71d-a4383e80d03f","resolution":{"observed_at":"2026-08-07T15:33:50.316446Z","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":"2026-08-07T15:33:49.896348Z","title":"Wavelet transform based watermark for digital images.Optics Express, 3(12):497–511, 1998","venue":null,"work_id":"a5dadd99-7f9a-4d6d-8b3a-a33e74fe455f","year":1998},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:47.777498Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:6edd5af240e0743e4bf286c4a3bf6f19958076fcefb9f149911cae709655f59d","observation_id":"52750fa7-4219-4f6f-bd4e-c73bfc1f3cb4","resolution":{"observed_at":"2026-08-07T15:33:50.049141Z","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":{"arxiv_id":"2012.08726","last_updated":"2022-03-17T20:27:04Z","snapshot_observed_at":"2026-07-06T10:24:54.445307Z","submitted_at":"2020-12-16T03:51:54Z","title":"Responsible Disclosure of Generative Models Using Scalable Fingerprinting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.08726","snapshot_observed_at":"2026-08-07T15:33:47.936785Z","title":"Responsible disclosure of generative models using scalable fingerprinting.arXiv preprint arXiv:2012.08726, 2020","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:47.936785Z"},"links":{"cited_paper":"/paper/2012.08726","citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:e6153282c618f9e93f9a642578ae4bca1c4b8ec0795fd92fc8d721386372f0f7","observation_id":"41587b09-fb89-4c78-b0ab-a6827fe576b5","resolution":{"observed_at":"2026-08-07T15:33:47.936785Z","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":"2026-08-07T15:33:48.047309Z","title":"An image is worth 32 tokens for reconstruction and generation.Advances in Neural Information Processing Systems, 37:128940–128966, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:48.047309Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:572b009101765c70baa6d7e91fd21abaaf5f145c18ccf747d18abc02e4437be1","observation_id":"ff21251c-d0dd-490f-a9d5-0d26c72c4448","resolution":{"observed_at":"2026-08-07T15:33:48.047309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.01285","last_updated":"2019-09-03T16:28:40Z","snapshot_observed_at":"2026-08-04T19:48:41.972949Z","submitted_at":"2019-09-03T16:28:40Z","title":"Robust Invisible Video Watermarking with Attention","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.01285","snapshot_observed_at":"2026-08-07T15:33:48.147028Z","title":"Robust invisible video watermarking with attention.arXiv preprint arXiv:1909.01285, 2019","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:48.147028Z"},"links":{"cited_paper":"/paper/1909.01285","citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:776a916129108ff69ce27a94bd8a1e4a052f0a204e759cf78eb23bc5cc292dec","observation_id":"d4c459cc-eac1-4435-86ea-3eff3b4fc23f","resolution":{"observed_at":"2026-08-07T15:33:48.147028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.01068","last_updated":"2022-06-21T17:04:40Z","snapshot_observed_at":"2026-08-06T03:13:37.403059Z","submitted_at":"2022-05-02T17:49:50Z","title":"OPT: Open Pre-trained Transformer Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.01068","snapshot_observed_at":"2026-08-07T15:33:48.270429Z","title":"Opt: Open pre-trained transformer language models.arXiv preprint arXiv:2205.01068, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:48.270429Z"},"links":{"cited_paper":"/paper/2205.01068","citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:b6b7d13a0e8d8e779e2762dcd4d0673267a6ecd88d2a2cf13171435e80f72b34","observation_id":"7c760dc9-75eb-44e4-ba76-58565f1c71b2","resolution":{"observed_at":"2026-08-07T15:33:48.270429Z","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":"2026-08-07T15:33:49.582448Z","title":"Hidden: Hiding data with deep networks","venue":null,"work_id":"9347f7d3-13bc-4f9c-98da-6beea3238a85","year":2018},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:48.378474Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:ce7c799bb6556712771d09066284d0a3ba309a118ac07bfa752ff2193070b367","observation_id":"98e09bb5-8757-43ad-8f06-255ff2c9b328","resolution":{"observed_at":"2026-08-07T15:33:49.735110Z","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":"1110.32626","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:33:48.745845Z","title":"a photo of category","venue":null,"work_id":"4b833e08-a8c9-439f-8440-4b008a0950e1","year":2023},"citing_paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:48.499614Z"},"links":{"citing_paper":"/paper/2505.14673"},"observation_digest":"sha256:dbda515836ad11a084fce2218cc716a5e884b64f66ed25539835414cdfdda0c7","observation_id":"0960e20f-c130-465a-bff5-8b0c067f9b3e","resolution":{"observed_at":"2026-08-07T15:33:48.830738Z","resolver_source":"raw_fallback","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"}}],"paper":{"arxiv_id":"2505.14673","last_updated":"2025-05-20T17:58:02Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T15:27:45.753887Z","submitted_at":"2025-05-20T17:58:02Z","title":"Training-Free Watermarking for Autoregressive Image Generation"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":2,"verified_fuzzy":10},"total_outbound_references":42},"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 42 of 42 outbound references and 3 inbound Pith citation observations for arXiv:2505.14673."}