{"as_of":"2026-08-19T05:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e6ee4e47e43ffdea49a1bf82df964b1f6d6fa745f0b016a84f53a8e71f95dfc7","coverage":[{"denominator":117,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T13:28:09.563044Z","state":"measured"},{"denominator":102,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":102,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T05:10:38.062251Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-10T23:55:50.839693Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.13155","snapshot_observed_at":"2026-08-16T05:10:38.062251Z","title":"F-bench: Rethinking human preference evaluation metrics for benchmarking face generation, customization, and restoration,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21308","last_updated":"2025-04-30T04:36:56Z","snapshot_observed_at":"2026-08-16T05:04:25.282763Z","submitted_at":"2025-04-30T04:36:56Z","title":"AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Images","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T05:10:38.062251Z"},"links":{"cited_paper":"/paper/2412.13155","citing_paper":"/paper/2504.21308"},"observation_digest":"sha256:c42eb184eda897f0c732157a2a05f4e0e836a805d5701c8fb9591bc147142405","observation_id":"a88a3875-4427-4d53-b042-a9a0a01a5d41","resolution":{"observed_at":"2026-08-16T05:10:38.062251Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"cited_work":{"arxiv_id":"2412.13155","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.13155","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Lu Liu, Huiyu Duan, Qiang Hu, Liu Yang, Chunlei Cai, Tianxiao Ye, Huayu Liu, Xiaoyun Zhang, and Guangtao Zhai","venue":null,"work_id":"8f75dc95-a215-40f8-99e8-f2ea69b77a91","year":2024},"citing_paper":{"arxiv_id":"2604.05523","last_updated":"2026-04-19T09:01:29Z","snapshot_observed_at":"2026-07-06T22:54:12.531121Z","submitted_at":"2026-04-07T07:23:51Z","title":"Market-Bench: Benchmarking Large Language Models on Economic and Trade Competition","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T18:48:02.028929Z"},"links":{"cited_paper":"/paper/2412.13155","citing_paper":"/paper/2604.05523"},"observation_digest":"sha256:c82005a476bc884d5e630b92f2495068f5070a6070c63e9b8d7b06629e4d2b59","observation_id":"35188961-28aa-4fca-a71d-14f7e21dae4e","resolution":{"observed_at":"2026-05-10T23:55:50.843208Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.13155/citation-record","integrity":"/paper/2412.13155/integrity","json":"/paper/2412.13155/citation-record.json","paper":"/paper/2412.13155"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.072867Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.072867Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:2df9e544460d6ec8b0de6e6b35b6f4861a77a5b6dfa3dda64c17f9298b6f4f65","observation_id":"2de9686a-2f86-4450-a012-caefdc1128fa","resolution":{"observed_at":"2026-08-11T13:28:09.072867Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.081078Z","title":"co / dreamlike - art / dreamlike - photoreal - 2","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.081078Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:5361042d3bdf3ac03d1c2e8fa12071dee83fbcf2a9c72c4d700d4b651312ac3f","observation_id":"e3e7d876-274b-44d8-9e62-8d7b78cf7738","resolution":{"observed_at":"2026-08-11T13:28:09.081078Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.087297Z","title":"co / black - forest-labs/FLUX.1-dev, Accessed: 2024-10-03","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.087297Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:fc3e87ef7e3c191e4198590bd3728df94cc31d6de62e0c7d683ace4ea7671108","observation_id":"157288c8-5da5-416d-ab37-9dfd1297211d","resolution":{"observed_at":"2026-08-11T13:28:09.087297Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.092870Z","title":"co/h94/IP-Adapter, Accessed: 2024-10-03","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.092870Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:d251971323534fbfb48afb7219801e7f67ec2a04cac8f2072e0ed84b5c10604b","observation_id":"bef6a3e2-3da2-4a74-8264-034fd9e04123","resolution":{"observed_at":"2026-08-11T13:28:09.092870Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.098397Z","title":"co/h94/IP-Adapter-FaceID, Accessed: 2024-10-","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.098397Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:5a6dc179be3ad4c2e6f72dcc044d3e6a366fe76ba0a4e7ad9363b3b1b79c4b99","observation_id":"171f68c5-e5d1-43c0-b7da-8632e876d174","resolution":{"observed_at":"2026-08-11T13:28:09.098397Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.104129Z","title":"co / Kwai - Kolors/Kolors, Accessed: 2024-10-03","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.104129Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:046d3be5281eb101e5e96a7c7f8e85ae42b8624695a641e6edc65a6bdf4be53d","observation_id":"6676abdf-718a-4581-92d0-75f8d0714d70","resolution":{"observed_at":"2026-08-11T13:28:09.104129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.110322Z","title":"co / stablediffusionapi/protovision- xl- v6.6, Accessed: 2024-10-03","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.110322Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:c08b97828170472660eca67a8fdb0c24e0f4fe69f28536505e27cba1ca69441a","observation_id":"359787bd-ee3f-4627-aeea-db45de070270","resolution":{"observed_at":"2026-08-11T13:28:09.110322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.115662Z","title":"3, 5, 1, 4","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.115662Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:806774ce9bc57bb3055300046f0c2de982e8436c7f07f47928741f59a1fa3c69","observation_id":"f16bebdc-42a5-47aa-b202-49273b8e08f7","resolution":{"observed_at":"2026-08-11T13:28:09.115662Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.121105Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.121105Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:84b24435394bab9d4984b76a3c7bc1aaf1c4bc3cb9d64f63c34c0e2af6254d78","observation_id":"43ca714c-5f8f-46b0-814f-4c6d5904a5ea","resolution":{"observed_at":"2026-08-11T13:28:09.121105Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.126784Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.126784Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:dd2ce6f07de21a39e2eabdb53deb1133ce8f2cf810bc6ac616b5dbdb1c9ef872","observation_id":"2152b3ad-150c-4d1c-9140-1cf77bdcf575","resolution":{"observed_at":"2026-08-11T13:28:09.126784Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13923","last_updated":"2025-02-19T18:00:14Z","snapshot_observed_at":"2026-08-14T04:17:22.593941Z","submitted_at":"2025-02-19T18:00:14Z","title":"Qwen2.5-VL Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13923","snapshot_observed_at":"2026-08-11T13:28:09.132323Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.132323Z"},"links":{"cited_paper":"/paper/2502.13923","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:a216ec3f54551a4665942e53246adbef9f3e6674b0e2bc80a1f22316d60ce87c","observation_id":"76c6e475-906a-413d-8f11-75cbc3c47e18","resolution":{"observed_at":"2026-08-11T13:28:09.132323Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.138285Z","title":"Cr-fiqa: face image quality assessment by learning sample relative classifiability","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.138285Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:8b6f6fe5d3d78cd6e89eca6982dcac2293c3a15ea58f33631529dfdc91d4b219","observation_id":"887537d0-e34a-4d38-93d2-0f2cad11bef4","resolution":{"observed_at":"2026-08-11T13:28:09.138285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.143210Z","title":"An image quality assessment dataset for portraits","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.143210Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:61421f939df8685c80ad8f28f1cc389c961cc0b09631bbac2f8da80cfb0001a9","observation_id":"b836aa07-91fb-4ce5-8cba-088fe8ca22ff","resolution":{"observed_at":"2026-08-11T13:28:09.143210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.148301Z","title":"Promptiqa: Boosting the performance and gen- eralization for no-reference image quality assessment via prompts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.148301Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:a1230dfb03572f3090775f642d8b88db1614a2c32c696e801c24607494db7caa","observation_id":"52a6d98f-c923-48bd-a1a5-89f36d3bd8a1","resolution":{"observed_at":"2026-08-11T13:28:09.148301Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.153338Z","title":"Learning spatial attention for face super-resolution.IEEE Transactions on Image Processing (TIP), 30:1219–1231, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.153338Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:538aedacb1eb8c9415f6261bf9f5d8f4808592144ec7875a05abee45f1661c0d","observation_id":"95a1f55d-2c2f-4d41-a928-37b81d2a9a25","resolution":{"observed_at":"2026-08-11T13:28:09.153338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.158725Z","title":"Progressive semantic- aware style transformation for blind face restoration","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.158725Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:b8c9d63e61180030374774ad6874c322e036660560416078b181ca98b51026d9","observation_id":"e5f5bd37-cf69-49a5-8c0f-4a8074e1d41e","resolution":{"observed_at":"2026-08-11T13:28:09.158725Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00426","last_updated":"2023-12-29T16:42:08Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-30T16:18:00Z","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00426","snapshot_observed_at":"2026-08-11T13:28:09.164313Z","title":"Pixart-α: Fast train- ing of diffusion transformer for photorealistic text-to-image synthesis.arXiv preprint arxiv:2310.00426, 2023","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.164313Z"},"links":{"cited_paper":"/paper/2310.00426","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:221e1fe5f56902af4af18720559cb030a257c095ea6bd30ef5559d3706fef27a","observation_id":"3ec2f03e-cd29-4fad-a54d-58b92aedd931","resolution":{"observed_at":"2026-08-11T13:28:09.164313Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.170301Z","title":"Dsl-fiqa: Assess- ing facial image quality via dual-set degradation learning and landmark-guided transformer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.170301Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:dcea394f258ef9997a683be08d54ab2f7601bb3ed18fadd3a7a9611980934148","observation_id":"c21e3ab1-96a1-48af-88a1-d9bdc2c1c3c7","resolution":{"observed_at":"2026-08-11T13:28:09.170301Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.175598Z","title":"Fsrnet: End-to-end learning face super-resolution with facial priors","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.175598Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:d0fdda901da30827d80db2f1084280ccb638ccda45a3128eb63dfb891056ce40","observation_id":"21b0591a-7360-4d0e-a855-0036aeaf0ae3","resolution":{"observed_at":"2026-08-11T13:28:09.175598Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13535","last_updated":"2024-03-21T02:31:58Z","snapshot_observed_at":"2026-08-16T14:08:04.326272Z","submitted_at":"2024-03-20T12:13:04Z","title":"IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.13535","snapshot_observed_at":"2026-08-11T13:28:09.180191Z","title":"Idadapter: Learn- ing mixed features for tuning-free personalization of text- to-image models.arXiv preprint arXiv:2403.13535, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.180191Z"},"links":{"cited_paper":"/paper/2403.13535","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:0b17b7e62074232cc35e3fe99fb7c4f621e64b29566a8da504d636d93b8b8348","observation_id":"9ce0fdeb-2a76-403d-8e12-961fa919e0fc","resolution":{"observed_at":"2026-08-11T13:28:09.180191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.185040Z","title":"Flashattention-2: Faster attention with better par- allelism and work partitioning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.185040Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:9465a5ec0b54f8b08f8fabcfd53fd0ceacc9862925465d5394e3a5a10b936b58","observation_id":"36f4a836-f726-404c-8b99-dbcf3efaa28f","resolution":{"observed_at":"2026-08-11T13:28:09.185040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.189951Z","title":"Arcface: Additive angular margin loss for deep face recognition","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.189951Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:88297790f26a2556294fab6b743b6065e172197d48ba98edb05dc78aad85e066","observation_id":"a1ecfb00-e557-406a-8a73-23f9dc2dcc07","resolution":{"observed_at":"2026-08-11T13:28:09.189951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.194470Z","title":"Finevq: Fine-grained user generated content video quality assessment","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.194470Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:faa64e56aca35e5ec7206b0c5b9b63c193b405c7fb5a995f5895b2a803b0963d","observation_id":"3e6f2527-da00-4c32-b93c-b3d7ab2bab19","resolution":{"observed_at":"2026-08-11T13:28:09.194470Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.01618","last_updated":"2022-08-02T17:50:36Z","snapshot_observed_at":"2026-08-02T23:40:32.342515Z","submitted_at":"2022-08-02T17:50:36Z","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.01618","snapshot_observed_at":"2026-08-11T13:28:09.198955Z","title":"An image is worth one word: Personalizing text-to- image generation using textual inversion.arXiv preprint arXiv:2208.01618, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.198955Z"},"links":{"cited_paper":"/paper/2208.01618","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:f4db375a324c7fa97da6088f34f6b0d1c03976af0a2796b41d7a93555b976ad8","observation_id":"12915a5e-a520-4178-a38e-8694487ae30a","resolution":{"observed_at":"2026-08-11T13:28:09.198955Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.203788Z","title":"Alireza Golestaneh, Saba Dadsetan, and Kris M","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.203788Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:7f64f6103347cabcbd098aafbcf8deb9693cf0d9b41739f5762ae10bb9185c33","observation_id":"d4e2a0b5-c75c-4b29-942c-d477438ecb43","resolution":{"observed_at":"2026-08-11T13:28:09.203788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.208664Z","title":"Generative adversarial nets","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.208664Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:2ee7b81e26e4f060d3e3140b56caf5cb6d8a66c71f510fd891ee67d84c194821","observation_id":"cf9908a2-17bb-4faf-bb1d-649cbf889a96","resolution":{"observed_at":"2026-08-11T13:28:09.208664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.213253Z","title":"Fisblim: A five-step blind metric for quality assessment of multiply distorted images","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.213253Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:4135058538e69dab08aec3dc8361da9cc8d99aa103840bbf6431d5da2440010d","observation_id":"b47cfa1d-72dd-4706-9dd0-a361a6bb03a4","resolution":{"observed_at":"2026-08-11T13:28:09.213253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.06803","last_updated":"2022-07-27T07:48:29Z","snapshot_observed_at":"2026-08-17T11:47:50.891655Z","submitted_at":"2022-05-13T17:54:40Z","title":"VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.06803","snapshot_observed_at":"2026-08-11T13:28:09.218008Z","title":"Vqfr: Blind face restoration with vector-quantized dictionary and parallel decoder.arXiv preprint arXiv:2205.06803, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.218008Z"},"links":{"cited_paper":"/paper/2205.06803","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:0320a74d5c3b893123f97dd6d940436d6591c8387dba94a790dc4f6b7796e12a","observation_id":"3043b9b5-8322-4f16-b8aa-0f3f36b50645","resolution":{"observed_at":"2026-08-11T13:28:09.218008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.223535Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.223535Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:a15aa9f3f09377970c4f455603d3f006d8f90ca7d8ad908cef5e4608a81ebd41","observation_id":"4d6e0406-e0a3-4a1d-b357-6aef6d034199","resolution":{"observed_at":"2026-08-11T13:28:09.223535Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.15275","last_updated":"2024-06-25T16:57:27Z","snapshot_observed_at":"2026-08-16T13:58:25.984156Z","submitted_at":"2024-04-23T17:59:43Z","title":"ID-Animator: Zero-Shot Identity-Preserving Human Video Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.15275","snapshot_observed_at":"2026-08-11T13:28:09.228261Z","title":"Id- animator: Zero-shot identity-preserving human video gen- eration.arXiv preprint arXiv:2404.15275, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.228261Z"},"links":{"cited_paper":"/paper/2404.15275","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:e6dd57ec6361700273a20acbeeeb8e5f1ece7c87d6b5598b66b21c15ad1cc640","observation_id":"75b86ceb-ac4a-428f-9a24-e79fde513a97","resolution":{"observed_at":"2026-08-11T13:28:09.228261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.233244Z","title":"Faceqnet: Quality assessment for face recognition based on deep learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.233244Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:95ffc9a475167e67204c22d8be3b3b36c5f4864166b7f2dcb57a966bd9da34c7","observation_id":"5e507a53-1dfb-4f33-8ca4-7c97ca5345f3","resolution":{"observed_at":"2026-08-11T13:28:09.233244Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08718","last_updated":"2022-03-23T19:47:21Z","snapshot_observed_at":"2026-07-06T11:01:02.207193Z","submitted_at":"2021-04-18T05:00:29Z","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08718","snapshot_observed_at":"2026-08-11T13:28:09.237758Z","title":"Clipscore: A reference-free evaluation metric for image captioning.arXiv preprint arXiv:2104.08718, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.237758Z"},"links":{"cited_paper":"/paper/2104.08718","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:703c0264c0912ce61946bac4f690635df964f86f5224eb97d75a723fd5b2cdd9","observation_id":"e674d951-f96c-4053-9cc5-eafd2b5d6599","resolution":{"observed_at":"2026-08-11T13:28:09.237758Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.242427Z","title":"Denoising dif- fusion probabilistic models.Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), 33: 6840–6851, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.242427Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:87e2a0488873362f23094f71cf18f89c774bb3fb6c0fddcdcfa2e8f7ae15c185","observation_id":"bb5b75fa-9eae-4412-be42-4dd606ac57c2","resolution":{"observed_at":"2026-08-11T13:28:09.242427Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.247056Z","title":"Image quality metrics: Psnr vs","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.247056Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:d99fec8ac6f39f7c103d217c0b0b656d176901fce403d6e5cde4b7975d546b04","observation_id":"5e3d9385-c9a5-465f-8c11-17f194a870b6","resolution":{"observed_at":"2026-08-11T13:28:09.247056Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.251615Z","title":"Lora: Low- rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.251615Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:96a7e6567584b87ae61efdd98f89bd72313a1c09ee4d3fd860f20dc505df348b","observation_id":"5fad82be-a3cd-45ad-9fde-c3d9d670371d","resolution":{"observed_at":"2026-08-11T13:28:09.251615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.256136Z","title":"Varfvv: View- adaptive real-time interactive free-view video streaming with edge computing.IEEE Journal on Selected Areas in Communications, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.256136Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:b4a86e2afd6fe41fcc806947b22d3b2e8a65025c1f9443f922fd0f4db0ffdf57","observation_id":"f96c54e3-1763-4f17-b63e-735b5b8ac6cf","resolution":{"observed_at":"2026-08-11T13:28:09.256136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.260536Z","title":"4dgc: Rate-aware 4d gaussian compression for efficient streamable free-viewpoint video","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.260536Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:87a1febb012806d22ae5fd3341d7c46a46568e1c24dcdbcfce874db6a4a05f01","observation_id":"4bc8f7c8-960c-4f54-a7c4-d95cfc56ebe3","resolution":{"observed_at":"2026-08-11T13:28:09.260536Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.265019Z","title":"Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.265019Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:84019c1017f6625e2adadf2a2c537958b69a98cc0ab38c32911eb291b91307f7","observation_id":"14638eb4-2d75-4abe-9e3e-b520e20e22c7","resolution":{"observed_at":"2026-08-11T13:28:09.265019Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.269620Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.269620Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:b430feed10e8381ab14d87dfe181a31b408e7e1b835d6f0a9e2b2122a96dc10d","observation_id":"585cde9a-cc47-4199-ade4-b7a49ff3522b","resolution":{"observed_at":"2026-08-11T13:28:09.269620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.274365Z","title":"Catekv: On sequential consistency for long-context llm inference acceleration","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.274365Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:ce37e55e02c976b0f55c6fef6a527883e45f8542a5ebb3390b448ca7d7f5078c","observation_id":"f85184b0-3ca5-4243-8b46-79a54bd882ca","resolution":{"observed_at":"2026-08-11T13:28:09.274365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.278975Z","title":"Ifqa: Interpretable face quality assessment","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.278975Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:9505a95668c106347a188bf6b7394f443b9f6bc90f8ea3f3264c2980f759ff59","observation_id":"fc78bd49-14b6-4ad4-bf7c-0015c979138c","resolution":{"observed_at":"2026-08-11T13:28:09.278975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.283814Z","title":"Convo- lutional neural networks for no-reference image quality as- sessment","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.283814Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:95f08cc731090bef4138fb506cb830d269560d56583c9a835f511b7bbbb42fdc","observation_id":"e35ae30a-2e70-4798-a26d-a4d8638ccb7e","resolution":{"observed_at":"2026-08-11T13:28:09.283814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.288373Z","title":"A style-based generator architecture for generative adversarial networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.288373Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:1f03c7f5ccaab47768c407255d9baa5226d82aa8bda8abfa34c58433053c6034","observation_id":"bc92b4ee-beed-46c6-b9d7-678bf868e447","resolution":{"observed_at":"2026-08-11T13:28:09.288373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.293124Z","title":"Imagic: Text-based real image editing with diffusion mod- els","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.293124Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:79cac184d1f0fb9e591d6e35e1300fa5b0f5e21023d0052832dbcff0ab9cfeb6","observation_id":"857382f2-a8b3-4c51-991d-fee616764dc0","resolution":{"observed_at":"2026-08-11T13:28:09.293124Z","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":"2026-08-11T13:28:11.174839Z","title":"The megaface benchmark: 1 million faces for recognition at scale","venue":null,"work_id":"59f4f60c-93b9-4cb1-8878-53d5fa092255","year":2016},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.297554Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:789a8ac79b124694e89e83248139bf731afe6042d5f82e8265cb8456783f88c4","observation_id":"52843336-8489-411c-93b9-a65034e3fa96","resolution":{"observed_at":"2026-08-11T13:28:11.179397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08239","last_updated":"2019-08-22T07:50:41Z","snapshot_observed_at":"2026-08-16T20:57:30.149002Z","submitted_at":"2019-08-22T07:50:41Z","title":"Progressive Face Super-Resolution via Attention to Facial Landmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08239","snapshot_observed_at":"2026-08-11T13:28:09.302057Z","title":"Progressive face super-resolution via attention to fa- cial landmark.arXiv preprint arXiv:1908.08239, 2019","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.302057Z"},"links":{"cited_paper":"/paper/1908.08239","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:aeb75fa11bd5fed74bf9751ba953c7e220d2c4ee60530027c79d4977636c6a9b","observation_id":"1a958f52-a223-41ab-9f21-09f7629f1a6b","resolution":{"observed_at":"2026-08-11T13:28:09.302057Z","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":"2026-08-11T13:28:11.159851Z","title":"Auto-encoding variational bayes","venue":null,"work_id":"7d7cacc2-5a17-428e-96ca-3851d44ad341","year":2013},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.306995Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:f6d1a4b182d92ebefa61645e5cd9d7d0887554900011909847c1391c151c81bc","observation_id":"684fd1b8-d0d7-4876-96a1-aa1899e84fba","resolution":{"observed_at":"2026-08-11T13:28:11.164254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:11.143818Z","title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","venue":null,"work_id":"6bdd7e88-6cdc-4cd8-94a2-6045fe92adca","year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.311614Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:ba6938305625ecc7a3966ce4cdea5f8686a1baa9c0ce5374ff2302c79197aea6","observation_id":"de25b419-b2fe-4198-9b3d-6710ea795323","resolution":{"observed_at":"2026-08-11T13:28:11.148996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:11.128306Z","title":"Multi-concept customization of text-to-image diffusion","venue":null,"work_id":"9af54433-ef82-4e7f-8333-c765fc96707d","year":1931},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.316154Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:e42ff5d0e14db2741f2e7ed08cb42e30a353c527c24693d849731e465b2717d8","observation_id":"9ea3eedc-4829-42eb-af89-dd1f23372705","resolution":{"observed_at":"2026-08-11T13:28:11.133601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.04717","last_updated":"2023-06-12T16:42:59Z","snapshot_observed_at":"2026-08-18T16:34:27.835353Z","submitted_at":"2023-06-07T18:28:21Z","title":"AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.04717","snapshot_observed_at":"2026-08-11T13:28:09.326328Z","title":"Agiqa-3k: An open database for ai-generated image quality assessment.arXiv prepreint arXiv: 2306.04717,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.326328Z"},"links":{"cited_paper":"/paper/2306.04717","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:607c62a66fc121c409f518bc940db94d0076470138013ce397e2c950b937dc0a","observation_id":"171c281f-5efc-462a-8ca5-7e4cbdd4b9cc","resolution":{"observed_at":"2026-08-11T13:28:09.326328Z","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":"2026-08-11T13:28:11.113208Z","title":"Playground v2.5: Three in- sights towards enhancing aesthetic quality in text-to-image generation, 2024","venue":null,"work_id":"7829545a-d036-4917-835d-819c753ca826","year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.331985Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:59d1aaf11e9ba74b0c88e0898235e3f766cd4f937599a8f9837adb88a041f49c","observation_id":"b2d53351-3fc1-47f8-8915-6b9682c2b3c1","resolution":{"observed_at":"2026-08-11T13:28:11.118411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:11.098304Z","title":"Blip: Bootstrapping language-image pre-training for uni- fied vision-language understanding and generation","venue":null,"work_id":"64fa1f36-2e12-4d0d-881a-7bb05e8bc0ea","year":2022},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.336649Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:9d79e4fdf62df56c0e9ddc47c466b005a7fc82b99bd3b2654d67786b7761cff1","observation_id":"da05146a-8064-4abf-9c5e-c6131491e166","resolution":{"observed_at":"2026-08-11T13:28:11.103386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:11.083979Z","title":"Learning warped guidance for blind face restoration","venue":null,"work_id":"a4c68903-5969-49bf-a9d5-e57f2877a05c","year":2018},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.341336Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:56b7ac71b5a44492908f1a80bc5680f9773063115a8cfe0bb78d17b889a137a0","observation_id":"904e80b3-4654-404e-8d95-293f16e3e292","resolution":{"observed_at":"2026-08-11T13:28:11.088744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:11.068352Z","title":"Enhanced blind face restoration with multi-exemplar images and adaptive spatial feature fusion","venue":null,"work_id":"b18da257-303e-423c-80dc-1e202a18d870","year":2020},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.345917Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:0b5b824fb608787ff9f161ebb1c53646aa134027304cbad819a5f3e1cc1decb5","observation_id":"29e06a82-962a-450d-a100-f919021289f2","resolution":{"observed_at":"2026-08-11T13:28:11.073289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:11.051770Z","title":"Learning dual memory dic- tionaries for blind face restoration.IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022","venue":null,"work_id":"c929a338-56dd-4a43-9a49-609a89000a60","year":2022},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.350780Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:5041583f1b35becb0e90926b9aea2362fcabe71e2fd4c42f486a8af2bbf186b9","observation_id":"1f76afff-8075-4ccc-bba0-ed2d66ab3299","resolution":{"observed_at":"2026-08-11T13:28:11.056550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.04461","last_updated":"2023-12-07T17:32:29Z","snapshot_observed_at":"2026-08-16T14:36:46.011897Z","submitted_at":"2023-12-07T17:32:29Z","title":"PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.04461","snapshot_observed_at":"2026-08-11T13:28:09.355450Z","title":"Photomaker: Cus- tomizing realistic human photos via stacked id embedding","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.355450Z"},"links":{"cited_paper":"/paper/2312.04461","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:c55c359b83d6d21766777283793e41b6db78fefbb4057524ea64ab73f1d27ffb","observation_id":"c62b50b8-e0ee-4cfe-a1e4-86293ca17358","resolution":{"observed_at":"2026-08-11T13:28:09.355450Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08748","last_updated":"2024-05-14T16:33:25Z","snapshot_observed_at":"2026-07-06T18:14:16.386835Z","submitted_at":"2024-05-14T16:33:25Z","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08748","snapshot_observed_at":"2026-08-11T13:28:09.360430Z","title":"Hunyuan- dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding.arXiv preprint arXiv:2405.08748, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.360430Z"},"links":{"cited_paper":"/paper/2405.08748","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:fc0f42c15a085b58eb6ff72d07c4409b06a3e7129e49ffcbb187acf976d97acd","observation_id":"cbb84cfd-0e08-491d-b4e3-b9c6eb9be24d","resolution":{"observed_at":"2026-08-11T13:28:09.360430Z","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":"2026-08-11T13:28:11.035011Z","title":"Rich human feedback for text-to-image generation","venue":null,"work_id":"9d50d125-4192-438c-affc-d294b4c66313","year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.365191Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:c6ee33a626352bd15f01b52174664dfff2ac6fe1777eca1110bb7adb54af4fe5","observation_id":"e77acbb4-375d-4d97-a053-ace6682d59c9","resolution":{"observed_at":"2026-08-11T13:28:11.040248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:11.018211Z","title":"Multi-branch face quality assess- ment for face recognition","venue":null,"work_id":"06ab7e25-119d-47fe-9283-49f3381f4c0f","year":2019},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.369799Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:f11440cd52e1bbfe39e6e189060a5394539ea00ad9ab435107372a26c59991b5","observation_id":"f7985be2-099e-41ac-b15c-69375fc1fb51","resolution":{"observed_at":"2026-08-11T13:28:11.023241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:11.002813Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":"fd0c6099-905d-4090-9b1e-bb38f6cf458a","year":2014},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.374322Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:89e430442458abc4e6231e8255f696982a5f0ad59625323240be3e5b6038f282","observation_id":"c2d3026f-a922-463e-8e7a-d1730cc15240","resolution":{"observed_at":"2026-08-11T13:28:11.008040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.15070","last_updated":"2024-04-12T05:26:59Z","snapshot_observed_at":"2026-08-16T15:05:03.053812Z","submitted_at":"2023-08-29T07:11:52Z","title":"DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.15070","snapshot_observed_at":"2026-08-11T13:28:09.379022Z","title":"Diff- bir: Towards blind image restoration with generative diffu- sion prior.arXiv preprint arXiv:2308.15070, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.379022Z"},"links":{"cited_paper":"/paper/2308.15070","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:21a70a8a149fcbc1101925f7f6e1080f30f3e3b6332906200c3c9af73f32ce4a","observation_id":"b0f7b278-3ef2-4f80-a4cf-994cadb217f2","resolution":{"observed_at":"2026-08-11T13:28:09.379022Z","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":"2026-08-11T13:28:10.987031Z","title":"Visual instruction tuning","venue":null,"work_id":"503cfb24-df9f-48db-903e-336aa19baab8","year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.383801Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:28fa54cb6a9813824f55bf35d17bd8f4613285c50771f564ced65022067e7d9f","observation_id":"3ba76694-cbe8-45d0-b8a1-65ad87f314e2","resolution":{"observed_at":"2026-08-11T13:28:10.992201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.970324Z","title":"Blind quality assessment based on pseudo-reference image.IEEE Transactions on Multimedia (TMM), 20(8):2049–2062, 2018","venue":null,"work_id":"465eb2ad-7c8a-4c65-871e-2c5bb5b555c0","year":2018},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.388302Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:995fe3ceb5fa960472e00f6a6e2e7b5d4593530e47342da77408a3b4eedff8b1","observation_id":"5fb7f03f-f539-49df-be64-b1f1a5de6f05","resolution":{"observed_at":"2026-08-11T13:28:10.976178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.952833Z","title":"Blind image quality estimation via distortion aggravation.IEEE Transactions on Broadcasting, 64(2): 508–517, 2018","venue":null,"work_id":"4480cf45-4525-4bde-8e5b-323ad67d008c","year":2018},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.393000Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:dac970facd3f21793ffd3265c507b1978fd00f0d0b84aeb6f44dd55910b1fde1","observation_id":"05ee05b2-f3f8-4538-aba8-85685c0bae48","resolution":{"observed_at":"2026-08-11T13:28:10.958111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.936939Z","title":"Perceptual video quality assessment: A survey.Science China Information Sciences, 67(11): 211301, 2024","venue":null,"work_id":"bb0ec3c4-233c-434e-92a9-f85cbbcd1a71","year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.398133Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:ff5dea71bd488bef7ab89b31fe2c284e6eeebc4ca43ba3ca8f3070455b26ede5","observation_id":"e496d7ac-65e4-4d7e-b1ed-87ea68cab0af","resolution":{"observed_at":"2026-08-11T13:28:10.942036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.921291Z","title":"completely blind","venue":null,"work_id":"2cc439f8-a291-41ae-866f-39db45202774","year":2013},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.402865Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:46145da4bff19a18491a677e0fff98ac5494e7515d00315bf2d78786fcfa99ea","observation_id":"8fa0ef26-b8dc-4bde-8d73-32d14d506a2b","resolution":{"observed_at":"2026-08-11T13:28:10.926036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.905328Z","title":"Agedb: the first manually collected, in-the-wild age database","venue":null,"work_id":"37f8fce9-bc65-4a8f-9363-a68638075ab4","year":2017},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.407476Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:c4f8b369bc4b40f459f56f7f82369ac0f21a96eeb2f51000f54a7fd83d5387f5","observation_id":"3f150026-b016-4346-9169-01eb48018e9d","resolution":{"observed_at":"2026-08-11T13:28:10.910619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.889267Z","title":"Sdd-fiqa: Unsupervised face image quality assess- ment with similarity distribution distance","venue":null,"work_id":"c4b8ed82-781b-445b-bae1-9bd02a689e23","year":2021},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.412239Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:6fcbafcb3ab972164cbda902055f6058dcbfbec5301be210d5e6626749957564","observation_id":"a5c7c3aa-ab98-4628-9989-88672910132d","resolution":{"observed_at":"2026-08-11T13:28:10.894286Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.00637","last_updated":"2023-09-29T05:32:46Z","snapshot_observed_at":"2026-08-16T15:27:32.220354Z","submitted_at":"2023-06-01T13:00:53Z","title":"Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.00637","snapshot_observed_at":"2026-08-11T13:28:09.416801Z","title":"W ¨urstchen: An efficient architecture for large-scale text-to-image diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.416801Z"},"links":{"cited_paper":"/paper/2306.00637","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:167f9ab9ffcb9897b0b2bcb43f19d912e2a81a8808f3d506da31efe6ac7aeb00","observation_id":"5dc5d659-b074-4d50-b477-a71a5578b50e","resolution":{"observed_at":"2026-08-11T13:28:09.416801Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01952","last_updated":"2023-07-04T23:04:57Z","snapshot_observed_at":"2026-08-14T22:54:08.184266Z","submitted_at":"2023-07-04T23:04:57Z","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01952","snapshot_observed_at":"2026-08-11T13:28:09.421652Z","title":"Sdxl: Improving latent diffusion mod- els for high-resolution image synthesis.arXiv preprint arXiv:2307.01952, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.421652Z"},"links":{"cited_paper":"/paper/2307.01952","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:f4fcce96ae8b889d5743118618821692717da7ca2045651c12ca2a8ab64115ad","observation_id":"a5eff706-fcc0-4971-98d5-96b679583d4e","resolution":{"observed_at":"2026-08-11T13:28:09.421652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.426584Z","title":"Zero-shot text-to-image generation, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.426584Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:fdf160577faa1116813e70650a214c6ef64bd4fe3889eeb065be41fd24b441c1","observation_id":"e9ba476b-3721-4e51-a78d-973ff897679a","resolution":{"observed_at":"2026-08-11T13:28:09.426584Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-08-15T12:50:58.405488Z","submitted_at":"2022-04-13T01:10:33Z","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.06125","snapshot_observed_at":"2026-08-11T13:28:09.431321Z","title":"Hierarchical text-conditional image generation with clip latents.arXiv preprint arXiv:2204.06125, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.431321Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:e5153ad8ef33833923d481540559573c0b4c2a9f4fd6f94266bb2bbadf5ce1bb","observation_id":"430798b7-59a4-41f3-a2a1-7130a6ad91ce","resolution":{"observed_at":"2026-08-11T13:28:09.431321Z","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":"2026-08-11T13:28:10.863085Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":"7d1482df-328a-4ebc-91a5-0bedca62075d","year":2022},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.436447Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:382bbe5b7e3bc9f805d5f5ce6a174ed4a5e070d9edc253d1a4745e1ae3f47c4b","observation_id":"0b219e2a-d6bb-43f2-912f-2aac25e6c5fd","resolution":{"observed_at":"2026-08-11T13:28:10.868274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.847764Z","title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","venue":null,"work_id":"7d81ee90-7cdd-4784-9392-5a6130d5d51d","year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.440954Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:352b37e47ca9f36c8a9e95281bbe6f0172aca26d87b546ff3e8731a70cc3b1cd","observation_id":"10a8ebb6-1c63-408e-ae41-f0d1efc0ae37","resolution":{"observed_at":"2026-08-11T13:28:10.853227Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.831910Z","title":"Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J Fleet, and Mohammad Norouzi","venue":null,"work_id":"c174e2c0-41ae-421f-a38d-19e8677adc3b","year":null},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.445418Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:06c51039f37629157d3a8343d0423afb42075cf486b0dd19022340da2b7fb432","observation_id":"17eac0fe-1216-400b-b494-f066942df403","resolution":{"observed_at":"2026-08-11T13:28:10.837296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.816859Z","title":null,"venue":null,"work_id":"f7c41d7d-4dd5-4bd9-bcd0-b49b710b30b0","year":2022},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.450124Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:37474b2b0a6e21e20bad0b0800f146755ca9320dccc038d4377a5db863da344d","observation_id":"8043c049-3521-4c8f-8d34-71d3832c1b75","resolution":{"observed_at":"2026-08-11T13:28:10.821478Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.802348Z","title":"Methodology for the subjective assessment of the quality of television pictures.Recommendation ITU-R BT, 500(13), 2012","venue":null,"work_id":"552f4ec9-c4af-4a81-b788-f2ce92a838b0","year":2012},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.454894Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:85b76b34f3310a0d62ea5777034acbaa028b01510c42dc563e879db170858d48","observation_id":"97d11490-da67-45ec-a919-a8c511bf78c1","resolution":{"observed_at":"2026-08-11T13:28:10.807374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.788085Z","title":"Photo uncrop","venue":null,"work_id":"ab660d64-801c-4cd9-8d5d-ce2702cc7dcf","year":2014},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.459578Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:2e7450976497296e2f6af5634802aaf3d6ac6508b52f407e5989ce75fd5ea612","observation_id":"a6904c97-8a60-4420-a220-32bbd693ab35","resolution":{"observed_at":"2026-08-11T13:28:10.792593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.773006Z","title":"Responsible re- search with crowds: pay crowdworkers at least minimum wage.Communications of the ACM, 61(3):39–41, 2018","venue":null,"work_id":"a020ea9a-fb60-4f7c-b76d-c635b1c5b054","year":2018},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.464445Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:1d5f4ec38c7d0f58b66f090c5fec2fff6e73d3d600dcda747cd42185bbb041a1","observation_id":"1b25537d-cc10-4411-81ff-7d3383eaac75","resolution":{"observed_at":"2026-08-11T13:28:10.778021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-17T19:17:06.411141Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-11T13:28:09.468897Z","title":"Very Deep Con- volutional Networks for Large-Scale Image Recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.468897Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:bf0db58fb4f872621e3ee2ffc24b5a5e94695043a5487243c90805406a7faedb","observation_id":"03e9a3e7-41f5-407d-a2ef-363325f98b4c","resolution":{"observed_at":"2026-08-11T13:28:09.468897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-08-11T15:38:14.931716Z","submitted_at":"2020-10-06T06:15:51Z","title":"Denoising Diffusion Implicit Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02502","snapshot_observed_at":"2026-08-11T13:28:09.473947Z","title":"Denois- ing diffusion implicit models.arXiv:2010.02502, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.473947Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:662675448d8cf9765c18b28b5e19b55038d73d9a9c26bf7e7d936b2ab742ac46","observation_id":"89abb9ad-b564-4d6c-8cbf-8c4d9f17ba3c","resolution":{"observed_at":"2026-08-11T13:28:09.473947Z","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":"2026-08-11T13:28:10.758111Z","title":"Blindly assess image qual- ity in the wild guided by a self-adaptive hyper network","venue":null,"work_id":"d2851994-cff7-4388-9d1f-e5dfd8e92130","year":2020},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.478976Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:d80361ea4058468f4dd06601beccff6991faa1493c4be946ceb5f06760c02e1e","observation_id":"63564549-019d-4c0f-b732-75ebf3a0f87e","resolution":{"observed_at":"2026-08-11T13:28:10.763114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.743137Z","title":"Going the extra mile in face image quality assess- ment: A novel database and model.IEEE Transactions on Multimedia, 2023","venue":null,"work_id":"e209e17b-8eb1-4abb-9a75-21a5320db354","year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.483759Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:51d04cfab07641b4c522f77d297befa5ac5980bce1e76f352f5a0831a3eb1e5d","observation_id":"b8e09704-cafb-48c3-a194-12daec45bb1c","resolution":{"observed_at":"2026-08-11T13:28:10.748106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.729016Z","title":"Ser-fiq: Unsupervised estimation of face image quality based on stochastic embed- ding robustness","venue":null,"work_id":"244653ba-eda4-4a01-b457-63d8febd28f8","year":2020},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.488311Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:b9e00d2b37d6d8a697ed9fd1ed33174d6188d34a441ecd01e55883a526ac493b","observation_id":"27856703-bcc6-48d4-8e9f-bbf4787d07ef","resolution":{"observed_at":"2026-08-11T13:28:10.733770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.714604Z","title":"Towards all-in-one medical image re-identification","venue":null,"work_id":"69db4efc-aa1f-47cf-8608-bae89afd501c","year":2025},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.492751Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:f5574f3979828984fe6a1105ccd58d0a751062846ec67b0a2d95e156d1a7a9fc","observation_id":"b0480844-51a8-417c-a3b3-91a9262310b5","resolution":{"observed_at":"2026-08-11T13:28:10.719244Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.700096Z","title":"Stylegan2 distillation for feed-forward image manipulation","venue":null,"work_id":"0c4876b6-f0b6-4af2-88c6-e45b27a8bd16","year":2020},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.497278Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:384f05c8c40d48ae6f71f73623d6273c54282d605b8cb7e1b49b6bbd952b9789","observation_id":"9a429446-321c-4795-8103-08a3df7947f1","resolution":{"observed_at":"2026-08-11T13:28:10.704648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.685627Z","title":"Aigciqa2023: A large-scale im- age quality assessment database for ai generated images: from the perspectives of quality, authenticity and corre- spondence","venue":null,"work_id":"68e37ffc-4ffe-40af-a6e3-09ccb4c59907","year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.501845Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:3e73407b90a781a6558dbe4add6c2be6399849fb8f3485a141316232a686b42a","observation_id":"1db0fb2a-5463-4095-9e15-0c525effa9b5","resolution":{"observed_at":"2026-08-11T13:28:10.690350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.670414Z","title":"Aigciqa2023: A large-scale im- age quality assessment database for ai generated images: from the perspectives of quality, authenticity and corre- spondence","venue":null,"work_id":"b1c8a7f0-25fb-4b6b-85db-fff86fb04605","year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.506358Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:76df71e0b301b1db9401cc23073b535dc7d4ec8b76eded6c898942c8b0b0c658","observation_id":"6a6d2ec4-ec1c-4725-b63b-969c7bad0bec","resolution":{"observed_at":"2026-08-11T13:28:10.675866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.07015","last_updated":"2024-06-28T17:14:13Z","snapshot_observed_at":"2026-08-16T15:33:46.445264Z","submitted_at":"2023-05-11T17:55:25Z","title":"Exploiting Diffusion Prior for Real-World Image Super-Resolution","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.07015","snapshot_observed_at":"2026-08-11T13:28:09.511223Z","title":"Exploiting diffusion prior for real-world image super-resolution.arXiv preprint arXiv:2305.07015, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.511223Z"},"links":{"cited_paper":"/paper/2305.07015","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:df2c5551b056360340d2404e0da0adc90cc48aaefc9f2f64d551b64a19af3293","observation_id":"ca570237-a40b-418a-ab7c-5d309b683ab0","resolution":{"observed_at":"2026-08-11T13:28:09.511223Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07346","last_updated":"2025-02-02T08:58:09Z","snapshot_observed_at":"2026-08-16T18:34:27.629299Z","submitted_at":"2024-05-12T17:45:11Z","title":"Quality Assessment for AI Generated Images with Instruction Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07346","snapshot_observed_at":"2026-08-11T13:28:09.516085Z","title":"Understanding and evaluating human preferences for ai generated images with instruction tuning.arXiv preprint arXiv:2405.07346, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.516085Z"},"links":{"cited_paper":"/paper/2405.07346","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:7246d41849513538ffb2395898e60d6c0a7aba99e55094473df32ae4c24e1849","observation_id":"1693e052-5e6c-4277-b79c-a00331e13b7a","resolution":{"observed_at":"2026-08-11T13:28:09.516085Z","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":"2026-08-11T13:28:10.655731Z","title":"Chan, and Chen Change Loy","venue":null,"work_id":"40861ecb-43b3-41eb-944c-7dc6796d1301","year":null},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.520875Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:7a4c991b9e27d4aa4e200dd0669158e10c55c4d2d4ad36158e3070ffaee3a54f","observation_id":"ec95d0f6-8897-455e-bf65-aaa801fb1f97","resolution":{"observed_at":"2026-08-11T13:28:10.660440Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.641524Z","title":"Xintao Wang, Honglun Zhang, Chao Dong, and Ying Shan","venue":null,"work_id":"82cf1b77-8d1c-4e5b-8d83-a996af36b4f9","year":2022},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.525518Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:3517ed545a24f9c9b05aa0aadc2dff741d00c195a66cc1836fe66ad85bd23441","observation_id":"2499f1e3-77a4-44d5-a7fe-3292e6a04245","resolution":{"observed_at":"2026-08-11T13:28:10.645998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.07519","last_updated":"2024-02-02T16:15:22Z","snapshot_observed_at":"2026-08-16T06:18:35.139211Z","submitted_at":"2024-01-15T07:50:18Z","title":"InstantID: Zero-shot Identity-Preserving Generation in Seconds","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.07519","snapshot_observed_at":"2026-08-11T13:28:09.530098Z","title":"Instantid: Zero-shot identity-preserving gen- eration in seconds.arXiv preprint arXiv:2401.07519, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.530098Z"},"links":{"cited_paper":"/paper/2401.07519","citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:15dbfc0c2ba4441a20b1f1e547da52cbebcaba86aa0cb42fa0fc9a71b1c8ba0c","observation_id":"74eb4c1a-26fa-4bce-8e42-472a7469a856","resolution":{"observed_at":"2026-08-11T13:28:09.530098Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T13:28:09.535100Z","title":"A survey of deep face restoration: Denoise, super-resolution, deblur, artifact re- moval.arXiv preprint arXiv:2211.02831, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.535100Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:cedc796108fbadfbdb05826c4d2908aed32ef7d1663fe302b52acc3954f662d4","observation_id":"bf4b8864-95f0-4fbd-9571-81b248ee9d98","resolution":{"observed_at":"2026-08-11T13:28:09.535100Z","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":"2026-08-11T13:28:10.626776Z","title":"Real-esrgan: Training real-world blind super-resolution with pure synthetic data","venue":null,"work_id":"017ba5f8-1272-42b0-adb5-051169172c66","year":null},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.539668Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:d9364a18dd6c83ffe46e13b8f31d7ec42c99324979abf8726213efee0bbb7af1","observation_id":"dea9e9d8-5210-480f-99d1-72a8fcf62338","resolution":{"observed_at":"2026-08-11T13:28:10.632037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.612363Z","title":"To- wards real-world blind face restoration with generative fa- cial prior","venue":null,"work_id":"b745b43c-e3c5-408a-957d-b9328e270ac4","year":2021},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.544347Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:e308786500281c97420ba9d487b805d0445fd036d0463deade347e9ff8314682","observation_id":"6ea9ac46-4b48-4f52-b74b-87ab8685b886","resolution":{"observed_at":"2026-08-11T13:28:10.617145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.597033Z","title":"To- wards real-world blind face restoration with generative fa- cial prior","venue":null,"work_id":"99525ae4-8a1c-4558-b421-45ac5e42008a","year":2021},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.549308Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:6a12dabaff4ca45805c13d2fd20186c097875fb81c04bc73dfdc67ea3a7b8352","observation_id":"5fae0384-2418-4eff-99c2-fe94ec794551","resolution":{"observed_at":"2026-08-11T13:28:10.602051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.581997Z","title":"Image quality assessment: from error visibility to structural similarity.IEEE Transactions on Image Pro- cessing (TIP), 13(4):600–612, 2004","venue":null,"work_id":"bb70dc86-fd12-4298-a84c-7edee909af4b","year":2004},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.553938Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:635479485985c24d78495281e05b68f7bfc60d32d882003ed80c6f816b404b72","observation_id":"a76a67ef-d970-46fe-826f-a93172ae61a9","resolution":{"observed_at":"2026-08-11T13:28:10.586803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.567470Z","title":"Dr2: Diffusion-based robust degradation remover for blind face restoration","venue":null,"work_id":"ed545429-e157-4069-9bfe-d1aa39d57e02","year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.558459Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:0b9d5fe60d7b12a6406b4b0c90b0d3b9369bb97da0503e8ceca43d843c5aa125","observation_id":"35a27293-0041-47f0-a6a4-601dea5f851c","resolution":{"observed_at":"2026-08-11T13:28:10.572380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T13:28:10.552738Z","title":"Elite: Encoding visual con- cepts into textual embeddings for customized text-to-image generation","venue":null,"work_id":"800300d4-c8d1-43ee-93a0-d2f4b8ed40fe","year":2023},"citing_paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","version":2},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-11T13:28:09.563044Z"},"links":{"citing_paper":"/paper/2412.13155"},"observation_digest":"sha256:6a78ebac3828dafa43685e651bc8f2c77b3e857c47bfbf7bf6fac794486b7efa","observation_id":"91221b86-57f7-42ba-a94e-2695d509b31c","resolution":{"observed_at":"2026-08-11T13:28:10.557602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.13155","last_updated":"2025-09-10T13:21:10Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T10:02:56.866170Z","submitted_at":"2024-12-17T18:28:48Z","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":60,"verified_exact":0,"verified_fuzzy":40},"total_outbound_references":117},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 100 of 117 outbound references and 2 inbound Pith citation observations for arXiv:2412.13155."}