{"as_of":"2026-08-07T08:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fed58037293fb19f1ec7ff818fa9a577955d9a3f3c20cda0230eb57ac5855ec9","coverage":[{"denominator":71,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":71,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T21:55:14.694995Z","state":"measured"},{"denominator":71,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":71,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.23074/citation-record","integrity":"/paper/2506.23074/integrity","json":"/paper/2506.23074/citation-record.json","paper":"/paper/2506.23074"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:55:25.840912Z","title":"com / iperov / DeepFaceLab","venue":null,"work_id":"6abc8655-e233-4c97-955a-fbc3f920f095","year":2023},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:07.948213Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:260cf085610dc916bb68852a6e800ec7d2c434e5fb2a4c7aaa731f2caf76e858","observation_id":"b7fe6abb-8ef1-4622-ac1c-82129fe98235","resolution":{"observed_at":"2026-08-06T21:55:25.967136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:25.636276Z","title":"com / deepfakes / faceswap","venue":null,"work_id":"28737a0c-9659-4ee1-b824-2e9fe057a9a9","year":2023},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:08.014659Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:b23f3cc14b590c0f708caaff7adb78cb827832157f0fd8805fe7874b0c8c0ad5","observation_id":"56b5d8a7-4f55-42f8-b1ff-e3e6079002b9","resolution":{"observed_at":"2026-08-06T21:55:25.724634Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.03602","last_updated":"2022-12-26T19:42:50Z","snapshot_observed_at":"2026-07-06T10:57:34.353038Z","submitted_at":"2021-04-08T08:34:04Z","title":"SiT: Self-supervised vIsion Transformer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.03602","snapshot_observed_at":"2026-08-06T21:55:08.112520Z","title":"Sit: Self-supervised vision transformer.arXiv preprint arXiv:2104.03602, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:08.112520Z"},"links":{"cited_paper":"/paper/2104.03602","citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:fd6d46fbea7fe1dff842e6cd8177a7786c77d5464054ce26aa1ba72330e5d966","observation_id":"357d7c57-74e8-4922-8dd1-10141a3cb1e0","resolution":{"observed_at":"2026-08-06T21:55:08.112520Z","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":"2026-08-06T21:55:25.410795Z","title":"Repmix: Represen- tation mixing for robust attribution of synthesized images","venue":null,"work_id":"543f763e-cfd8-4cbc-b776-d7af9e8d6ad8","year":2022},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:08.194652Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:dc9913a97c0c356e0a1f3c64944f4fc404c4547e52b93de5058e3a48b95d254d","observation_id":"bf89eee9-c647-4707-b8cd-228964d11dad","resolution":{"observed_at":"2026-08-06T21:55:25.533211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:25.186332Z","title":"Open-world semi-supervised learning","venue":null,"work_id":"44748022-87c3-4859-8c18-808666cbde3b","year":2022},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:08.312813Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:b04d59afa9d8d2d13d521b5faaabc7120f92edd7368069caa4c380fab1ccfaad","observation_id":"699872ed-2b8d-420f-9a94-855deeab1058","resolution":{"observed_at":"2026-08-06T21:55:25.300587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:24.942126Z","title":"Stargan: Unified genera- tive adversarial networks for multi-domain image-to-image translation","venue":null,"work_id":"443bfd38-69d3-412f-95ea-abebff2974bb","year":2018},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:08.451728Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:1432d9b9dd4020985bf2806d8cfb4a6e5a7986fa2b6cbd240779402c6c9b72d1","observation_id":"a40b012d-a3dc-42f1-9dd6-e82cde7ed44b","resolution":{"observed_at":"2026-08-06T21:55:25.078972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:24.701947Z","title":"Xception: Deep learning with depthwise separable convolutions","venue":null,"work_id":"77f1f736-d021-4b1b-a870-4bf64732ca3f","year":2017},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:08.528640Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:45d21113a19448246e32353cb6a80511f48582d4b8cc062d3caa3c4e154ef9a2","observation_id":"3abaaee8-2a0e-4306-baab-837cca155340","resolution":{"observed_at":"2026-08-06T21:55:24.790552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:24.439314Z","title":"On the detection of digital face manipulation","venue":null,"work_id":"03cdfc3c-0351-4cd4-a4e8-aaa3786da341","year":2020},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:08.643349Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:308c1f9b79037c110c28b85af7b25a7e1572b30242e3696bd91ef2a075dba6d3","observation_id":"7576df52-3fc5-475b-8f13-02f768f840c5","resolution":{"observed_at":"2026-08-06T21:55:24.581443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:24.175120Z","title":"Arcface: Additive angular margin loss for deep face recognition","venue":null,"work_id":"def080b4-3502-4f9e-9c92-83b3a25eef06","year":2019},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:08.747034Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:0a3ed485d105929c6b6f45c9c8b635d5444231eedea90f8be45e699cea5cb554","observation_id":"4d62ace8-dbd2-4b83-9ab1-bdc0d45fcba9","resolution":{"observed_at":"2026-08-06T21:55:24.279137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:23.961568Z","title":"Reducing network agnostophobia","venue":null,"work_id":"d57b9dfc-14d2-474e-aab2-606af4f92c69","year":2018},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:08.850671Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:ba1ccbb313acf501348ca36d929ad309def4e95fd19a2b4dbebc2c59e5d7ffcf","observation_id":"4fff7638-bb5e-48e5-81f8-da09c17a0158","resolution":{"observed_at":"2026-08-06T21:55:24.025651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:09.008913Z","title":"Diffusion mod- els beat gans on image synthesis.NeurIPS, 34:8780–8794,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:09.008913Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:44bd4f0de1250548fd92c40d3c73bf6696ff78dc88b3e4c3f0e65fef345300e1","observation_id":"324bfb6c-ecc6-4e6c-b5f0-092208f628fa","resolution":{"observed_at":"2026-08-06T21:55:09.008913Z","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":"2026-08-06T21:55:23.727774Z","title":"Taming transformers for high-resolution image synthesis","venue":null,"work_id":"732a1b3d-d873-437b-bcf4-64d5e19b4560","year":2021},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:09.154201Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:17e1c9f7baf1db8252c33385b49493c2e7da209f5ac5a7503d0c0f08a8cb8b00","observation_id":"702c3de9-9ccc-46d9-8fd8-3e216a4bd29b","resolution":{"observed_at":"2026-08-06T21:55:23.824094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:23.514874Z","title":"Leveraging fre- quency analysis for deep fake image recognition","venue":null,"work_id":"9a32f216-c390-4361-abf7-ef59ecd60384","year":2020},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:09.247331Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:e27cd3363ca9a64880f91b6cbe6afee9a95aac60eb4d9c88c33dddc7a81ea106","observation_id":"59f8e67c-3d1f-493c-9cd8-43533ecc5319","resolution":{"observed_at":"2026-08-06T21:55:23.604593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:23.287050Z","title":"Towards discovery and attribution of open-world gan generated images","venue":null,"work_id":"c51276e8-17c3-46ce-9057-c37d92cb37ab","year":2021},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:09.380871Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:12e7fedef039478b5cb4293f0cc6ea8d6e44dda5c9b5aced3982b7827cac74d9","observation_id":"ed0b32ab-1e40-46a1-8578-0a3997792e12","resolution":{"observed_at":"2026-08-06T21:55:23.428098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:23.092738Z","title":"Generative adversarial nets.NeurIPS, 27,","venue":null,"work_id":"820dbcc1-1e33-4760-af64-6f3be3e6ac8e","year":null},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:09.484762Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:3ee53bcd622df79c89361cdc2165d933fc90f868f15af813e7edd6b9b4a3cb74","observation_id":"a348685f-2fc9-4de9-8919-59d872e5f8e8","resolution":{"observed_at":"2026-08-06T21:55:23.190030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:22.875610Z","title":"On the exploitation of deepfake model recognition","venue":null,"work_id":"2ed43e5d-67d5-4d30-9b3e-42d5fe03e464","year":2022},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:09.567612Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:9d3d7421e806ae8308155cbde64628da72d0af343fc7d1f67f91688ecb4b56df","observation_id":"17540bf0-dd8f-4493-8372-0e89099fb8bd","resolution":{"observed_at":"2026-08-06T21:55:22.963863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:22.607024Z","title":"Robust semi-supervised learning when not all classes have labels","venue":null,"work_id":"a75463fa-79b7-49ec-92fc-8426fadb4597","year":2022},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:09.612756Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:28e24be07b8056d5e2c9a86f541fae869be8c259872613f778df4936ee677a57","observation_id":"6c87ac08-e50a-4c54-ae33-f752299a435b","resolution":{"observed_at":"2026-08-06T21:55:22.723259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:22.419312Z","title":"Automatically discov- ering and learning new visual categories with ranking statis- tics","venue":null,"work_id":"38f787ef-c8e4-4478-ae9c-c8282352ab59","year":2020},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:09.658693Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:02f68568740222a99c238851389d13610f7f00387bf7ee1ee6edd5731cfc01fd","observation_id":"3622f50f-5902-4c29-b130-0c605ecbc1e3","resolution":{"observed_at":"2026-08-06T21:55:22.494947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:22.266433Z","title":"Ghostnet: More features from cheap opera- tions","venue":null,"work_id":"1d71ba0b-61eb-4ffe-aeec-5d8c379bfe93","year":2020},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:09.837553Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:e8f807ae2ad9e798fa9e52081d13a17be08786e3fd0c0f9e09e9388c27a19b8b","observation_id":"4ccb6dbd-5693-4933-b33f-e370e6771053","resolution":{"observed_at":"2026-08-06T21:55:22.309107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:22.162955Z","title":"Forgerynet: A versatile benchmark for comprehensive forgery analysis","venue":null,"work_id":"e2036eba-bb26-4591-bf62-68733a244cae","year":2021},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:09.895020Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:7eb7996911cdfd2a49a8f9c15e83334c416fc3328740f2b8d767c94f6465fa98","observation_id":"2b684e6d-e0f6-4671-a48e-3be6b57a01d1","resolution":{"observed_at":"2026-08-06T21:55:22.211527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:22.003504Z","title":"Denoising dif- fusion probabilistic models.NeurIPS, 33:6840–6851, 2020","venue":null,"work_id":"ba50b1e3-bc95-435d-b1e9-22ba595bbff9","year":2020},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:09.927725Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:4f5fc6fb48f37fd1c151f0fd3151198e8e1b0f5d982c3eb6a9ab995bf8d518f0","observation_id":"235bf9fc-a726-42a3-83dd-37b659382208","resolution":{"observed_at":"2026-08-06T21:55:22.083784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:21.819494Z","title":"Pfa-gan: Progressive face aging with gen- erative adversarial network.TIFS, 16:2031–2045, 2020","venue":null,"work_id":"5b6e2cae-23e6-45f6-bf71-7a9cb933278c","year":2020},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:10.023155Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:27c4db88a5d7adc3f85251bebabccbcd6cbfb5d3ef47f403b74769c9ab680d43","observation_id":"fd0bdffa-9eef-4b9e-843e-fa2650e23c78","resolution":{"observed_at":"2026-08-06T21:55:21.931752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:21.650701Z","title":"Sc-fegan: Face editing gen- erative adversarial network with user’s sketch and color","venue":null,"work_id":"c13282a1-fae9-4d62-9612-8f0ee0993ae4","year":2019},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:10.129921Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:2232f6cf91b2871de79b1eb5da116778cf036804c8860a512f54625e63864244","observation_id":"169b16f2-f75c-4f9a-bbcc-17661d0f3fca","resolution":{"observed_at":"2026-08-06T21:55:21.712644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:21.504258Z","title":"Towards open world object de- tection","venue":null,"work_id":"1ab8057c-8512-4fab-be7e-7279c49cc8dd","year":2021},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:10.185759Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:345e73eb3cb48813e7547dd3c2227d076acd9803d806ec2cda87a75b31c7724f","observation_id":"67b4b3bd-26f0-4479-af02-c1ae61c43e5e","resolution":{"observed_at":"2026-08-06T21:55:21.582292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:10.309416Z","title":"Progressive growing of gans for improved quality, stability, and variation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:10.309416Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:46725db363d8854e302f596bf31b8c056a5fc9df7d2769e30b92218c5d554342","observation_id":"dda65986-a94c-4515-8121-b11c48c0cfda","resolution":{"observed_at":"2026-08-06T21:55:10.309416Z","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":"2026-08-06T21:55:21.360798Z","title":"A style-based generator architecture for generative adversarial networks","venue":null,"work_id":"da5b71d4-a7b8-4758-b4a9-099ae8db3e5d","year":2019},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:10.419238Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:d3ad7acba8961d9156a999675a6d6bb1afe4553dbb4a94def4dce3d6a81e1691","observation_id":"1732295a-cb28-4293-9841-6283edabd1ad","resolution":{"observed_at":"2026-08-06T21:55:21.442009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:21.265868Z","title":"Decentralized attribution of generative models","venue":null,"work_id":"31bf9660-27a2-46aa-831d-5a73155872e3","year":2021},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:10.548231Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:dcf9c8d677377b92ebc75e2716af58e9860a011bf68d9a363e97c1f668f0e6e0","observation_id":"2bd953dd-73f1-4d07-9472-313a04eb5b89","resolution":{"observed_at":"2026-08-06T21:55:21.306793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:10.618413Z","title":"Auto-encoding varia- tional bayes","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:10.618413Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:5c2ff88ea06196c950585e955bea6ab2c8bc1d68df1202a2d38a2f1158588936","observation_id":"1f553863-fd92-48e6-8752-5ede495e1ff7","resolution":{"observed_at":"2026-08-06T21:55:10.618413Z","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":"2026-08-06T21:55:21.047007Z","title":"The hungarian method for the assignment problem.NRL, 2(1-2):83–97, 1955","venue":null,"work_id":"07651824-1696-4ee4-a348-381cd61b6889","year":1955},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:10.707122Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:5ae42a1cdfd27c170c2d89eea7e8fcb2cf580dbd3fd394fa3a0fb5f663285246","observation_id":"17fb892f-9343-43da-af59-ef269a45ade8","resolution":{"observed_at":"2026-08-06T21:55:21.137148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:20.934955Z","title":"Are handcrafted filters helpful for attributing ai-generated images? InACM MM, pages 10698–10706, 2024","venue":null,"work_id":"976ddd97-bd1d-4cdc-8dd0-09d6a70f03bd","year":2024},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:10.766563Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:9146601e6f1a7ba606057d26a0cb1f70792831bc82ff3755283f9cce17ddb8c4","observation_id":"168a12f4-b232-4241-9fe7-d621fd2123a2","resolution":{"observed_at":"2026-08-06T21:55:20.990432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.13457","last_updated":"2020-09-15T07:43:58Z","snapshot_observed_at":"2026-07-06T08:47:53.346676Z","submitted_at":"2019-12-31T17:57:46Z","title":"FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.13457","snapshot_observed_at":"2026-08-06T21:55:10.823022Z","title":"Faceshifter: Towards high fidelity and occlusion aware face swapping.arXiv preprint arXiv:1912.13457, 2019","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:10.823022Z"},"links":{"cited_paper":"/paper/1912.13457","citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:c48b39ec571b4089945d4d985d0af0308221aa59deb65c27ae23a1ef173b89f7","observation_id":"ec3d932f-2d68-438c-938c-2595792a5068","resolution":{"observed_at":"2026-08-06T21:55:10.823022Z","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":"2026-08-06T21:55:20.746196Z","title":"Face x-ray for more general face forgery detection","venue":null,"work_id":"325b1534-99cf-47fc-ace0-bd6973116a76","year":null},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:10.916791Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:ee0544d5528715e3d39dafb822d0e2a57015f51561c7f1a86e326c29f0e2bdf9","observation_id":"33e643e6-fc2b-49a6-80cc-e5dd14a80d2c","resolution":{"observed_at":"2026-08-06T21:55:20.829917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:20.568422Z","title":"Counterfactual intervention feature transfer for visible- infrared person re-identification","venue":null,"work_id":"e749890b-133e-4993-8570-a45802ac2e77","year":null},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:10.990586Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:9f78fdaf4a6a93b4331ac8b27c0776670828e94ed1faf8fb947d9e4b735eaac1","observation_id":"6096a439-84e0-4d67-b3eb-7272409bf4a9","resolution":{"observed_at":"2026-08-06T21:55:20.645029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:20.428905Z","title":"Celeb-df: A large-scale challenging dataset for deep- fake forensics","venue":null,"work_id":"89bb724d-ce57-44e4-8fe4-08b7a63a8df6","year":2020},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:11.038646Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:cc7013b531b09557fc358c924569620952b3221c83f9eebc62c1f93f51ca3bda","observation_id":"442400d4-c8ee-4a6c-a909-06db057d2f4b","resolution":{"observed_at":"2026-08-06T21:55:20.485249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:20.258642Z","title":"Detecting generated images by real images","venue":null,"work_id":"db615a8e-eae2-4ddd-ac1b-944fe08cff05","year":2022},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:11.100621Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:a16eebe8457079cc3dd66c1c66cee2ebabacb7e1c1c908ef17a468605a9bc279","observation_id":"44ac51a2-69e7-433c-a2b5-9a3df246a305","resolution":{"observed_at":"2026-08-06T21:55:20.339699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:20.115827Z","title":"Which model generated this image? a model- agnostic approach for origin attribution","venue":null,"work_id":"60054731-2c06-41e4-a922-af2b9e2b38b8","year":2024},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:11.217442Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:12f3c2f906137007b8d89277065b186ba82bf51b88b7e7285031e1de4f6f2e33","observation_id":"265653bd-c668-49cc-a834-000697fda67e","resolution":{"observed_at":"2026-08-06T21:55:20.170884Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:19.894654Z","title":"Residual denoising diffu- sion models","venue":null,"work_id":"58d742a5-315b-4ab1-8401-32cc2763f9c0","year":2024},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:11.267760Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:5ed89c1b94d8abb6942e72d5ac6787aac3f3046c805ddc0ffcda80e3baa3d254","observation_id":"0daa1473-bef3-42d9-857b-701a7d67e546","resolution":{"observed_at":"2026-08-06T21:55:20.024000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:19.761000Z","title":"Discovering causal signals in images","venue":null,"work_id":"f756e83e-5620-4db3-a2d5-d72e4b297605","year":2017},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:11.395210Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:24bc77e09869f39a584f9e0dd5628770c06e91e25eac6ed03647a76bb919d522","observation_id":"0ae2866c-b28f-4457-b2e1-4b6dd8fcd15e","resolution":{"observed_at":"2026-08-06T21:55:19.820450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:19.615029Z","title":"Do gans leave artificial fingerprints? In MIPR, pages 506–511, 2019","venue":null,"work_id":"20185544-28bc-41a9-ad48-86fb8e404b1b","year":2019},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:11.452126Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:fe7403f0e35c15995ef51cf4764368b239d96b5adb57ba4989fca4d715ab686a","observation_id":"d77b088f-558c-4ff9-b201-a667118b27bb","resolution":{"observed_at":"2026-08-06T21:55:19.687450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:19.481364Z","title":"Causality: models, reasoning, and inference, by judea pearl, cambridge university press, 2000","venue":null,"work_id":"cd56ffe1-98b0-4f03-a2e9-cb410b8ad935","year":2000},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:11.504282Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:e9c0f55695c2a6ba56e54fec38eb1f7d28bc889cf6702be1bcc0d20912d95ad3","observation_id":"26eeac3e-cddb-4623-a83b-4b035c13a85a","resolution":{"observed_at":"2026-08-06T21:55:19.505462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:19.331043Z","title":"FSGAN: Subject agnostic face swapping and reenactment","venue":null,"work_id":"4efc6565-92d0-4a09-b6da-e89690cbaee7","year":2019},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:11.590686Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:0442c86ba56a07cd6260675daf600fc840ee41c6c20e5cb3bfbff0c7c9d139fe","observation_id":"81b0571d-bcfe-4eed-96ca-846458575f84","resolution":{"observed_at":"2026-08-06T21:55:19.397022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:19.191014Z","title":"Towards uni- versal fake image detectors that generalize across generative models","venue":null,"work_id":"548ff1b5-aeb9-4e35-b161-4eea2c54355d","year":2023},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:11.662091Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:49a1b129141e2efb379a60e75080f1f5e2a8c5b8f0a011d10c6c0cbfd28e1862","observation_id":"03902edd-4893-420a-b809-1d4430f02be4","resolution":{"observed_at":"2026-08-06T21:55:19.254375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:19.033798Z","title":"Basic books, 2018","venue":null,"work_id":"74020424-921f-4d80-8bd8-0f280f5f86b6","year":2018},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:11.718905Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:a6f2dfd85d62ee2c3c346ca5e422afd8b384b05974f4f07d18339e76f2c102ce","observation_id":"db6039fe-a3e7-4a60-8b87-c787e75a439e","resolution":{"observed_at":"2026-08-06T21:55:19.097035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:18.842289Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":"48192cc8-3bbd-4e07-8842-5b3ec819ee7a","year":2023},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:11.791445Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:b7b5b60673769db1a3962bf5628c06d0559c3c4f597fc26da812c551cf74d9ef","observation_id":"24d3ad6d-83c0-4fe0-bd9c-edc5bde51161","resolution":{"observed_at":"2026-08-06T21:55:18.909961Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:18.697994Z","title":"Counterfactual attention learning for fine-grained visual cat- egorization and re-identification","venue":null,"work_id":"0c9b725b-ea28-443e-b8f9-38063da36530","year":2021},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:11.886038Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:c42f4432b8e5bc41aab8751280233341ca791fe15c3d125c87c13b074da3731f","observation_id":"a7dd7439-9e52-4141-99b8-3618a907aed7","resolution":{"observed_at":"2026-08-06T21:55:18.750116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:18.525723Z","title":"Openldn: Learn- ing to discover novel classes for open-world semi-supervised learning","venue":null,"work_id":"b278ee0b-d980-4e32-aed1-d5ee23ef1dca","year":2022},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:12.023187Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:42bbdd794275ec01c5414e644bad56745d445fccb9650345ec35d8dc7518cde7","observation_id":"8e190531-9752-4dc7-bedf-839c2f95adb4","resolution":{"observed_at":"2026-08-06T21:55:18.604721Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:12.136547Z","title":"High-resolution image syn- thesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:12.136547Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:67956c198fd29f504bef9773b07c41624a36e399ec1c0832b7c38c527aefb969","observation_id":"ca04b4b0-bcda-4342-855e-8408d12c3842","resolution":{"observed_at":"2026-08-06T21:55:12.136547Z","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":"2026-08-06T21:55:18.346972Z","title":"Faceforen- sics++: Learning to detect manipulated facial images","venue":null,"work_id":"dbf600ed-0339-4a49-84e4-6b14d53976ae","year":2019},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:12.291040Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:660436614761134e3c3059eda8f42bb5422e2173b8b6328debffd4e4e2f2c901","observation_id":"e0864022-47b6-470a-9ccd-8b8147fad6f5","resolution":{"observed_at":"2026-08-06T21:55:18.425616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:18.166850Z","title":"Open-world semantic segmen- tation including class similarity","venue":null,"work_id":"6e45a9a3-bd16-439d-bbab-1405499c5ab8","year":null},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:12.434482Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:659741cd53807c685d36452923d64040300aebdbf7621114fad45c720875228f","observation_id":"55413348-8be2-4e28-8dce-a5b37625af67","resolution":{"observed_at":"2026-08-06T21:55:18.270786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:18.015890Z","title":"Learning structured output representation using deep conditional gen- erative models.NeurIPS, 28, 2015","venue":null,"work_id":"748d3a01-0faf-479c-84f0-66fe03a02875","year":2015},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:12.545270Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:ae3ebb3571fccdb2a46d8c519d6335203b29c2e98b163406aa0326ddd909afe1","observation_id":"960bb34f-eb6b-4e0b-9daa-4edf93701157","resolution":{"observed_at":"2026-08-06T21:55:18.064461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:12.671501Z","title":"Denois- ing diffusion implicit models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:12.671501Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:13a00510e0e2a83ab69cce342599f7a227088d7a61fe3aa372298351c38a761d","observation_id":"ea1202a9-ecee-41d1-814e-dcb7f2877e72","resolution":{"observed_at":"2026-08-06T21:55:12.671501Z","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":"2026-08-06T21:55:17.833230Z","title":"Contrastive pseudo learning for open-world deepfake attribution","venue":null,"work_id":"b5a41e62-e952-42cf-9f92-b5bfc8526bc1","year":2023},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:12.771543Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:e759fe99d5d3bc511e30669cf34099c115e4ffd881c36a56ac0a7ebcc47e830b","observation_id":"6fb250c5-80f1-4931-a8e7-88f80542ddcd","resolution":{"observed_at":"2026-08-06T21:55:17.937995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:17.649889Z","title":"Rethinking open-world deepfake attribution with multi-perspective sensory learning.IJCV, pages 1–24, 2024","venue":null,"work_id":"8415fc1c-a8a6-4e80-8e23-7970a901c17a","year":2024},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:12.900818Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:2ac070167a9b3fac9eeadd31bc6595760a7cb7f31675650f5499de1402ee9790","observation_id":"59ea4e36-c2fd-4261-8c30-8be590bbc011","resolution":{"observed_at":"2026-08-06T21:55:17.731117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:17.501777Z","title":"Rethinking the up-sampling operations in cnn-based generative network for generalizable deepfake detection","venue":null,"work_id":"97bc2956-49e9-4d61-8507-929742b79e26","year":2024},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:13.011276Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:70d71b4926bda076147c87094bae6ec1177a1ba93169ee8fdd5ce66e38a43e76","observation_id":"c938b217-3469-4bf8-9a50-ffabab114419","resolution":{"observed_at":"2026-08-06T21:55:17.566950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:13.149053Z","title":"Visual autoregressive modeling: Scalable image gen- eration via next-scale prediction.NeurIPS, 37:84839–84865,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:13.149053Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:9423aa96b8e567bef42f1399b43c94a36d6b2dbdbd5160b53ee079089ac38239","observation_id":"e80b36b7-3a71-4c5a-9c9d-a2657060a51a","resolution":{"observed_at":"2026-08-06T21:55:13.149053Z","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":"2026-08-06T21:55:17.338903Z","title":"Neural discrete representation learning.NeurIPS, 30, 2017","venue":null,"work_id":"6cfe6349-c419-4f45-90a8-d647a27ec82c","year":2017},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:13.308949Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:344eade4ba34d2359867366e91823c894bd8f77ea3fd7a545ab26178d92db53f","observation_id":"552b7148-a6c2-4fdd-a68c-2bbd2cd8e22a","resolution":{"observed_at":"2026-08-06T21:55:17.415606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:17.194592Z","title":"Visualizing data using t-sne.JMLR, 9(11), 2008","venue":null,"work_id":"48037423-ad05-4443-ae46-be427f66790f","year":2008},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:13.402576Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:58524374bddd1dc629c2bda264ade26c8e32bcc912302635d201147ec35ce871","observation_id":"26e8ac1a-b090-416f-8079-854eb9e4a968","resolution":{"observed_at":"2026-08-06T21:55:17.257153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:16.999761Z","title":"Counterfactual cycle-consistent learn- ing for instruction following and generation in vision- language navigation","venue":null,"work_id":"2b8c564c-bcb6-4da3-88a7-9fd5007d9842","year":2022},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:13.466953Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:ed705932163a45faf9e0746ad897ac558fb100ec36c176570ab2b370d6dcb239","observation_id":"fbebfaa2-ec00-4a38-aa9f-171b0a11f7c6","resolution":{"observed_at":"2026-08-06T21:55:17.078694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:16.896761Z","title":"Visual commonsense r-cnn","venue":null,"work_id":"2fc37666-0099-4ca1-8f09-b596e5f7da3c","year":2020},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:13.565983Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:ca8f05b9e580c671a5bc794a0c1f7c1773cf1edaec34616da98bad4df46a8624","observation_id":"900e01a2-113b-47fb-939d-d4362dc21be6","resolution":{"observed_at":"2026-08-06T21:55:16.940208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:16.813935Z","title":"Forgerynir: deep face forgery and detec- tion in near-infrared scenario.TIFS, 17:500–515, 2022","venue":null,"work_id":"93c6dd8f-a38d-4130-b115-4af06f8b46f3","year":2022},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:13.628019Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:39ecc82792a0dc097d9587e3b2fc4dcaa7e86bc5c0df7773e401578ba3db5eaf","observation_id":"8bab137c-1d08-4f7a-95f2-ce462237c184","resolution":{"observed_at":"2026-08-06T21:55:16.848460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:16.701318Z","title":"Where did i come from? origin attribution of ai-generated images.NeurIPS, 36:74478–74500, 2023","venue":null,"work_id":"bd997062-f185-43af-a0fb-908c7380a732","year":2023},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:13.711768Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:fffd0a379fbc40b507302ecb6c542f961d375ad223bae7222850635697db143d","observation_id":"1a60cbe8-bc21-4392-a341-5493a1bc9189","resolution":{"observed_at":"2026-08-06T21:55:16.740725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:16.568678Z","title":"Df40: Toward next- generation deepfake detection","venue":null,"work_id":"de14b1ea-9480-4e29-8008-903940e8ab8b","year":2024},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:13.785961Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:d04d06528c084a70105b45731bede951b3c023ec964f8c9a4a56323c4095e5c9","observation_id":"16ed33a6-fedd-4692-a208-5bbdac6bc124","resolution":{"observed_at":"2026-08-06T21:55:16.625404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:16.415948Z","title":"Deepfake network architecture attribution","venue":null,"work_id":"33e9a2dd-eb23-4364-819c-e4aa65fe287f","year":2022},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:13.909208Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:28d17ae8cc0ef88e9e9d99e95336e03d42202096143635b574c93e7ffe0c0d67","observation_id":"7ed28e9c-fa3b-45f0-9906-c9647bbef336","resolution":{"observed_at":"2026-08-06T21:55:16.476964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:16.272235Z","title":"Progressive open space expan- sion for open-set model attribution","venue":null,"work_id":"e8b2c090-a155-43ac-b230-34cc8d9f3ec2","year":2023},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:14.016997Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:fc0d019bf94ac08c0e8ab4bf4a5a469c65133a4886fbcbfad60aadb409f3df48","observation_id":"23a6dd3f-0bfd-41db-a9bd-f45daf544866","resolution":{"observed_at":"2026-08-06T21:55:16.322672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:16.117723Z","title":"Attributing fake images to gans: Learning and analyzing gan fingerprints","venue":null,"work_id":"6c63651b-6728-4bab-b67e-218c289f8f4a","year":2019},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:14.144824Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:5da683bd26ccbeba671f28b35c13e2e917098d0c81a3a54ff74cdf7a9091b1fa","observation_id":"2ce0d751-cfa1-4454-9237-cc0d539c062b","resolution":{"observed_at":"2026-08-06T21:55:16.172747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:15.905001Z","title":"Artificial fingerprinting for generative models: Root- ing deepfake attribution in training data","venue":null,"work_id":"c3e4ce6f-7162-493b-b674-2a0b99713691","year":2021},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:14.217603Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:a07ce961e16369d35df6e0fd2b4aa13de2f4aa8d1f8f1681b2fff31a0c88fcb6","observation_id":"6df55b51-aa8d-46ca-9699-1b47a3dc5465","resolution":{"observed_at":"2026-08-06T21:55:16.007678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:15.655209Z","title":"Responsible disclosure of generative mod- els using scalable fingerprinting","venue":null,"work_id":"5e0c68b4-e33f-4d3a-a14f-dcc4fe969215","year":2021},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:14.348671Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:657f5204681718d54fc1dc830c6e162011e36e59bf487d52ac6b1d27d4d46e95","observation_id":"486bbc4e-5b23-400e-94ed-a67ec7c030c2","resolution":{"observed_at":"2026-08-06T21:55:15.793022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:15.488960Z","title":"Counterfactual zero-shot and open-set vi- sual recognition","venue":null,"work_id":"16c90964-5e34-4ebb-9480-58804fc10f51","year":2021},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:14.435987Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:181017d63e8677c4babd8b50e8e586d6a3f4f6fa395ad00420ecb63ed442604f","observation_id":"4dd8794e-93e2-4960-b9a5-bc0e52cc2821","resolution":{"observed_at":"2026-08-06T21:55:15.565784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:15.293991Z","title":"Multi-attentional deep- fake detection","venue":null,"work_id":"fc9b968e-3688-4597-ad57-1405ee207173","year":2021},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:14.503201Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:bb7b7d88600a4c3b1681d13b349dfc3fb375906663f7c6ff95e6ee96c7c68889","observation_id":"0b9a64ba-fcb7-45de-a8ca-bf61e04d5113","resolution":{"observed_at":"2026-08-06T21:55:15.405026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:15.054401Z","title":"Learning deep features for discrimi- native localization","venue":null,"work_id":"d0c414ba-bcfa-471c-ae30-23770803e5b3","year":2016},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:14.605608Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:ef0777e90d94c095659e6c3179c2fb76164cc21223ae9bb758da9614ad453e12","observation_id":"906f820d-1e5e-4e31-b269-269edbdf9da7","resolution":{"observed_at":"2026-08-06T21:55:15.187063Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T21:55:14.855357Z","title":"Unpaired image-to-image translation using cycle- consistent adversarial networkss","venue":null,"work_id":"0d3204c0-29b4-46e6-a409-b9eb1d5c85bb","year":2017},"citing_paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:14.694995Z"},"links":{"citing_paper":"/paper/2506.23074"},"observation_digest":"sha256:65c1533a6f8fed5aa0e4f7c459796d0c55a827b339a3a07cf6070dcebd2338aa","observation_id":"6285a43a-c464-486b-bf44-e4001fdf06db","resolution":{"observed_at":"2026-08-06T21:55:14.915457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.23074","last_updated":"2025-06-29T03:25:45Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T21:48:11.337174Z","submitted_at":"2025-06-29T03:25:45Z","title":"Learning Counterfactually Decoupled Attention for Open-World Model Attribution"},"reference_resolution":{"displayed":71,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":63},"total_outbound_references":71},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 0 inbound Pith citation observations for arXiv:2506.23074."}