{"as_of":"2026-08-18T16:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:70db6d4c51c42d271725375d9925c66b5ac6ea2c450bb6c9a8e0f14caa829a15","coverage":[{"denominator":94,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":94,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:24:10.960879Z","state":"measured"},{"denominator":95,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":95,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-12T01:10:21.661074Z","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":"2026-05-12T08:26:24.408688Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"cited_work":{"arxiv_id":"2505.13327","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.13327","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Benchmarking unified face attack detection via hierarchical prompt tuning","venue":null,"work_id":"b1585408-8108-4fc4-b5ad-fa85c748564e","year":2025},"citing_paper":{"arxiv_id":"2605.08709","last_updated":"2026-05-09T05:44:29Z","snapshot_observed_at":"2026-08-14T18:41:33.111684Z","submitted_at":"2026-05-09T05:44:29Z","title":"UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-12T01:10:21.661074Z"},"links":{"cited_paper":"/paper/2505.13327","citing_paper":"/paper/2605.08709"},"observation_digest":"sha256:68f192404b26bc330eebc3b7c2c1adefb53a45171ca4435d4621ef8b8215c71b","observation_id":"0b023961-e0ea-488e-a159-ef2694c46a8f","resolution":{"observed_at":"2026-05-12T08:26:24.410665Z","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/2505.13327/citation-record","integrity":"/paper/2505.13327/integrity","json":"/paper/2505.13327/citation-record.json","paper":"/paper/2505.13327"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:24:10.582801Z","title":"Casia-surf: A large-scale multi-modal benchmark for face anti-spoofing,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.582801Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:973dcef090499ab87e3394ae3da021ec4e13f4f5964fe3ea8707406cd1b75af4","observation_id":"5e4fd2be-169b-4679-bcbd-f5b258329c14","resolution":{"observed_at":"2026-08-15T20:24:10.582801Z","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":"2026-08-15T20:24:10.588041Z","title":"On the effectiveness of local binary patterns in face anti-spoofing,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.588041Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:87236ebe141495612039a31d95e9f91da8def68736d4f1c7ddfb212b8fa32309","observation_id":"0bdf1916-cdb7-4ccd-978e-52f861719ca2","resolution":{"observed_at":"2026-08-15T20:24:10.588041Z","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":"2026-08-15T20:24:10.592644Z","title":"Contrastive context-aware learning for 3d high-fidelity mask face presentation attack detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.592644Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:e6cc1655537ee1795c5d9fe4ffceaa65fb640ce3fa4020f333958de26d0061ff","observation_id":"9297f6f3-6861-4f4b-84c3-a935fd86b9c9","resolution":{"observed_at":"2026-08-15T20:24:10.592644Z","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":"2026-08-15T20:24:10.596909Z","title":"Biometric face presentation attack detection with multi-channel convolutional neural network,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.596909Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:55fef216847125a1b46baabcbf5f1901a6418d43c254bbffe77a5a55fddfa01a","observation_id":"c402bb91-f929-4788-b5b8-7d56a8f2d205","resolution":{"observed_at":"2026-08-15T20:24:10.596909Z","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":"2026-08-15T20:24:10.601482Z","title":"Learning deep models for face anti-spoofing: Binary or auxiliary supervision,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.601482Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:5a156b6d45620c4042298f2b178743714f1df99b2ba6ca50ae54fa9040081e37","observation_id":"f46fa24b-b310-4edb-b150-dd9bcc4cf45d","resolution":{"observed_at":"2026-08-15T20:24:10.601482Z","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":"2026-08-15T20:24:10.606248Z","title":"Deep pixel-wise binary supervision for face presentation attack detection,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.606248Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:6470e96a41e9da94a235cc71b61e6f5e1e185ef641ec369526a01da5a1e65bc7","observation_id":"756469e6-b8a5-44bd-b964-4e522d1e61b3","resolution":{"observed_at":"2026-08-15T20:24:10.606248Z","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":"2026-08-15T20:24:10.611228Z","title":"Face anti-spoofing via disentangled repre- sentation learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.611228Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:4265403328c414a2d981e26150f7f9b7fcf92688c93165ede485948097c25779","observation_id":"b52a4aa0-63b4-4527-b2db-a143cd7aabbf","resolution":{"observed_at":"2026-08-15T20:24:10.611228Z","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":"2026-08-15T20:24:10.615453Z","title":"Nas-fas: Static- dynamic central difference network search for face anti-spoofing,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.615453Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:626420f6a7bed2dc470f1d628cced40aa011016cc3612b7d7fe2461ac8a882f5","observation_id":"06f54330-fe63-4f93-9323-2d532b9492fc","resolution":{"observed_at":"2026-08-15T20:24:10.615453Z","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":"2026-08-15T20:24:10.619702Z","title":"Drl-fas: A novel framework based on deep reinforcement learning for face anti- spoofing,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.619702Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:74641fd449dfd4a2076b833080d6c3866a94f1041e5dd6ee3a340398a171d2de","observation_id":"efe0aac0-7765-4858-a7c7-9275a40b2f4d","resolution":{"observed_at":"2026-08-15T20:24:10.619702Z","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":"2026-08-15T20:24:10.623771Z","title":"Disentangling facial pose and appearance information for face anti-spoofing,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.623771Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:27f29329552158256b0404f3ee82d3b7b8120a92f955da1d0a8681eee848293d","observation_id":"1d244dca-8af5-4a9d-af1b-ad1aabac518c","resolution":{"observed_at":"2026-08-15T20:24:10.623771Z","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":"2026-08-15T20:24:10.627976Z","title":"Patchnet: A simple face anti-spoofing framework via fine-grained patch recognition,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.627976Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:ec95b4d8b87b513f23ff76c57e0d67c201cc48c0cfd735e5d3c6f8269f2044ba","observation_id":"f6afa2b9-e60c-4aea-b69f-cb133091e7ba","resolution":{"observed_at":"2026-08-15T20:24:10.627976Z","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":"2026-08-15T20:24:10.632118Z","title":"Towards unsupervised domain generalization for face anti-spoofing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.632118Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:84bd2739947a5d25cc4e3d8f51b24bac1f90b564cea1c94fc3821a9888935c1a","observation_id":"3c955854-0f72-470b-92b6-e193f429db31","resolution":{"observed_at":"2026-08-15T20:24:10.632118Z","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":"2026-08-15T20:24:10.636418Z","title":"Rethinking domain generalization for face anti-spoofing: Separability and alignment,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.636418Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:901c7133d490ad1c4960cc476bddf71be1da565a503e2fd74a4ca61bdef00a00","observation_id":"2f6823eb-a13f-4c80-99d7-b56524b3ca79","resolution":{"observed_at":"2026-08-15T20:24:10.636418Z","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":"2026-08-15T20:24:10.640455Z","title":"Instance-aware domain generalization for face anti-spoofing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.640455Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:edb2181da70ec2aa9d0c26d9a8029d6b6f7c8b26b5b148082da097a355abdcc2","observation_id":"5a54c9cf-51c4-47d8-9442-c17f0e6e3134","resolution":{"observed_at":"2026-08-15T20:24:10.640455Z","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":"2026-08-15T20:24:12.065949Z","title":"Flip: Cross-domain face anti-spoofing with language guidance,","venue":null,"work_id":"2acb69f0-9909-4b47-936c-9620e92a1235","year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.644538Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:34bc60fd02f1a86fa01514eacf4899c7fbc513aa8ec4703a7e9ad0fd0a940b5e","observation_id":"a4a94bed-0c26-4a8c-b47b-d93685dcb317","resolution":{"observed_at":"2026-08-15T20:24:12.070517Z","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":"2026-08-15T20:24:12.052454Z","title":"Gradient alignment for cross-domain face anti-spoofing,","venue":null,"work_id":"98a9751c-a628-4d83-b4e7-8996a013adf2","year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.648995Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:b539abbc69c069b58cb77e2c358350600e20266e2bf6f670019540e80292b1aa","observation_id":"0783909f-670e-4ca0-a37c-6585df65da95","resolution":{"observed_at":"2026-08-15T20:24:12.056964Z","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":"2026-08-15T20:24:12.038855Z","title":"Test-time domain generalization for face anti-spoofing,","venue":null,"work_id":"7939376c-608a-4b9e-8f4e-414a1881a399","year":2015},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.653298Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:c11a6c56b39d95f161ea8ddbf557bbfa35a6b2008560fbc87a679dafa800a14e","observation_id":"3f1b872a-92ff-4e90-8d24-4a3e0dde57f7","resolution":{"observed_at":"2026-08-15T20:24:12.043296Z","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":"2026-08-15T20:24:12.024012Z","title":"Safa: Structure aware face anima- tion,","venue":null,"work_id":"f2289396-a88c-4397-be62-92f2b388ca94","year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.657340Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:360be8abc6302de8d56ee575dc7014d39c0401ce3d772e453bbe9c2d7f5616d6","observation_id":"7a2b81d6-a56b-4eed-bdbc-64826baeff64","resolution":{"observed_at":"2026-08-15T20:24:12.029510Z","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":"2026-08-15T20:24:12.010256Z","title":"Star- gan: Unified generative adversarial networks for multi-domain image-to-image translation,","venue":null,"work_id":"9bea862d-cbdc-417a-ab23-8b24e2d854c1","year":2018},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.661643Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:bdaf0dd4aa7b8fefcc8c08b55260dfc58992a1ae6dbb2834370e0199e056f618","observation_id":"ead7b4d9-ab36-4cf0-8c16-151b1cc79a51","resolution":{"observed_at":"2026-08-15T20:24:12.014961Z","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":"2026-08-15T20:24:11.997158Z","title":"Facedancer: Pose-and occlusion-aware high fidelity face swap- ping,","venue":null,"work_id":"b9087c44-d7cc-424a-b516-17d4d4e113e4","year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.665725Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:5adaa66f0e4613458bae4768e99d77f600956c5a0cc67a769f0931bd0ab6083c","observation_id":"347472d6-4ba1-472b-b1ec-4d0fe24abe2d","resolution":{"observed_at":"2026-08-15T20:24:12.001290Z","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":"2026-08-15T20:24:11.983211Z","title":"Simswap: An efficient framework for high fidelity face swapping,","venue":null,"work_id":"16800b21-dabe-4c16-bf62-5444fa2be379","year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.669243Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:ed6b61d90b6a77d492c974d1fbda52245e80099e94c167989f4ba448af29f0f6","observation_id":"743aa02e-fdea-4dc6-abbc-1e2426570fa7","resolution":{"observed_at":"2026-08-15T20:24:11.987992Z","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":"2026-08-15T20:24:11.968333Z","title":"Depth-aware gener- ative adversarial network for talking head video generation,","venue":null,"work_id":"4fddbeb9-5f6d-4a10-83bf-ba5c9ba54646","year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.672731Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:b4537269ecf42afb66346162af5b3a1ccdc9b57672f7134903f03e27e39ff624","observation_id":"cc97760a-f614-4e6f-bc29-23b26171e642","resolution":{"observed_at":"2026-08-15T20:24:11.973464Z","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":"2026-08-15T20:24:11.953922Z","title":"One-shot free-view neural talking-head synthesis for video conferencing,","venue":null,"work_id":"5cf3c790-afc2-492f-aff2-e2619568354c","year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.676210Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:3fc59861d689bc3dad57f6697dbb2a2bd61b5cd68b93b03cdb152359e17356a4","observation_id":"e7cf9b27-8a81-45c5-b128-ad7811e3aedd","resolution":{"observed_at":"2026-08-15T20:24:11.957856Z","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":"2026-08-15T20:24:11.941355Z","title":"Making adversarial examples more transferable and indistinguishable,","venue":null,"work_id":"906c92b2-a710-4779-9616-f192d495d6e5","year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.679642Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:1c9efb4caf616328c31971e58363d6bbfc1391fafd6da5b9dc9f12f41bb23a25","observation_id":"6618d3ae-6963-4965-b1ac-4af0c3761510","resolution":{"observed_at":"2026-08-15T20:24:11.945320Z","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":"2026-08-15T20:24:11.926146Z","title":"Ila-da: Improving transferability of intermediate level attack with data augmenta- tion,","venue":null,"work_id":"c6b739f0-95f1-4aa3-89af-b134140aac33","year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.683051Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:10893b1c3e28862ce0e60eaa036c8e3646ef7dded0827683ed4849d940be1b8d","observation_id":"37bf2508-a689-4444-a412-61c9744da30b","resolution":{"observed_at":"2026-08-15T20:24:11.931565Z","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":"2026-08-15T20:24:11.911864Z","title":"Boosting adversarial transferability across model genus by deformation-constrained warping,","venue":null,"work_id":"8e77e097-e392-4518-848e-b6436400896f","year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.686521Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:26facc0632dceda53ee6889587997d3035a31c2eaa9539eb84b4caee6fcd9f6b","observation_id":"30ad67c3-5556-4cac-9b58-ae08a51b7acc","resolution":{"observed_at":"2026-08-15T20:24:11.917082Z","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":"2026-08-15T20:24:11.898040Z","title":"Ex- ploring misclassifications of robust neural networks to enhance adversarial attacks,","venue":null,"work_id":"7098d204-ba88-4f15-bf6d-92803263b345","year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.690186Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:8507c0ad8da5403740be50ca1ff15aa542b1f171125a07606544abd7dc895f59","observation_id":"60a53d64-ad95-4047-8c97-66ae7e3e8d65","resolution":{"observed_at":"2026-08-15T20:24:11.902857Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:24:10.693655Z","title":"Frequency- driven imperceptible adversarial attack on semantic similarity,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.693655Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:d196494f17e3910bbdc409c77f7bb90cdb00995e2ab4b856f408aa43dc68f691","observation_id":"9e0bbed3-d702-4ad8-bd24-68cfb95f93ab","resolution":{"observed_at":"2026-08-15T20:24:10.693655Z","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":"2026-08-15T20:24:11.876757Z","title":"Towards transferable adversarial attacks on vision transformers,","venue":null,"work_id":"65aace26-88da-4689-9124-8ce9142625a0","year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.697694Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:8fb7cc44d5eb33ad28cbe7037c16a973f8d88843b58f7dab5eb8b879b49fab8d","observation_id":"5a790a62-2e74-44b0-b131-06c3d6a5c318","resolution":{"observed_at":"2026-08-15T20:24:11.880593Z","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":"2026-08-15T20:24:11.862890Z","title":"Transferable adversar- ial attacks on vision transformers with token gradient regulariza- tion,","venue":null,"work_id":"7929a6b2-9843-45ed-b590-f6ca97915fea","year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.701719Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:5be34dba770d90f52eb3574fc59a7c7c180b56e245a3ac08a6363236a3fdbe9c","observation_id":"80dfedd4-9ace-4c75-88bc-d924d9bc62b7","resolution":{"observed_at":"2026-08-15T20:24:11.867417Z","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":"2404.16771","last_updated":"2024-12-28T17:42:44Z","snapshot_observed_at":"2026-08-16T13:57:48.601133Z","submitted_at":"2024-04-25T17:23:43Z","title":"ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16771","snapshot_observed_at":"2026-08-15T20:24:10.705623Z","title":"Consistentid: Portrait generation with multimodal fine-grained identity preserving,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.705623Z"},"links":{"cited_paper":"/paper/2404.16771","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:b3d78db2dbd32cb6420b30617057615c04d039591a66eac899972d7a2ed05632","observation_id":"5ef91e0a-4485-46ac-bf4c-0fdaa7b5b118","resolution":{"observed_at":"2026-08-15T20:24:10.705623Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16022","last_updated":"2024-10-31T12:17:39Z","snapshot_observed_at":"2026-08-16T13:58:08.710994Z","submitted_at":"2024-04-24T17:55:33Z","title":"PuLID: Pure and Lightning ID Customization via Contrastive Alignment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16022","snapshot_observed_at":"2026-08-15T20:24:10.710163Z","title":"Pulid: Pure and lightning id customization via contrastive alignment,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.710163Z"},"links":{"cited_paper":"/paper/2404.16022","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:e2549fa672da602cfd68ef44abd52739c1a778eb03993d341bdea1a3cf79b62e","observation_id":"b7f0384a-e930-4f51-82f8-d68cb49564b6","resolution":{"observed_at":"2026-08-15T20:24:10.710163Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-15T20:24:10.714549Z","title":"Instantid: Zero-shot identity-preserving generation in seconds,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.714549Z"},"links":{"cited_paper":"/paper/2401.07519","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:01a0a996b4f01d6e6f2a72cb56b01aa9496940cf6d1b28881a4732c04669b914","observation_id":"5cf79cd4-87ba-47f6-9e2e-3be12e7270c6","resolution":{"observed_at":"2026-08-15T20:24:10.714549Z","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":"2026-08-15T20:24:11.849118Z","title":"Real appearance modeling for more general deepfake detection,","venue":null,"work_id":"2e2d84c8-7263-4d24-a791-8334840ab45e","year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.718968Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:7baed4f629ad46db53d29f9c28666d08eb8385c2efeaf90fbd7069d1cc8e2d09","observation_id":"e394419d-7b64-4663-b865-9c0efe68c025","resolution":{"observed_at":"2026-08-15T20:24:11.853565Z","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":"2026-08-15T20:24:11.834594Z","title":"Implicit identity leakage: The stumbling block to improving deepfake detection generalization,","venue":null,"work_id":"c2ddc5c9-5767-47bb-8516-65e06db10c13","year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.723780Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:1ec1f3741328700a468f3bc5fb937e8e7a92b40131a488e59db328c4ddec8b13","observation_id":"4ee71a75-65e6-4ed1-bfe9-bf1da03f70be","resolution":{"observed_at":"2026-08-15T20:24:11.840087Z","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":"2026-08-15T20:24:11.821485Z","title":"Exploiting style latent flows for generalizing deepfake video detection,","venue":null,"work_id":"9bea9a79-3760-4b71-9743-dc6ea4e96706","year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.727776Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:d4dde68549bf2f7388be1751abfa2984ba125e2dbbdb06ba43573b5f1a15a82e","observation_id":"da368243-3a5f-49e4-98b9-922c847e2681","resolution":{"observed_at":"2026-08-15T20:24:11.825304Z","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":"2026-08-15T20:24:11.808698Z","title":"Unified detection of digital and physical face attacks,","venue":null,"work_id":"4486d047-7d9f-43ce-97bc-790deb70197a","year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.731761Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:69e7fcaa3a4b7c607fa9cc5b1b9d2277b2f7a721bf1b28f63952377079218709","observation_id":"09f0c66d-39fc-49d8-a375-1068bb1b67f8","resolution":{"observed_at":"2026-08-15T20:24:11.813236Z","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":"2026-08-15T20:24:11.794784Z","title":"Benchmark- ing joint face spoofing and forgery detection with visual and physiological cues,","venue":null,"work_id":"e4f8f979-b2ee-4f77-978f-9acae65780f4","year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.735800Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:20446ee6d177f3ab488db09224a940e05c7a679eaa1331f49ec49804ae74006b","observation_id":"4614928a-af72-485d-80de-bb2c9e659907","resolution":{"observed_at":"2026-08-15T20:24:11.799599Z","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":"2401.17699","last_updated":"2024-01-31T09:38:44Z","snapshot_observed_at":"2026-08-16T14:22:56.506324Z","submitted_at":"2024-01-31T09:38:44Z","title":"Unified Physical-Digital Face Attack Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.17699","snapshot_observed_at":"2026-08-15T20:24:10.739799Z","title":"Unified physical-digital face attack detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.739799Z"},"links":{"cited_paper":"/paper/2401.17699","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:dbd5effae295ddd3fec10f9a01a3ed3c45fa12390769237692dc1e44a28ffc3c","observation_id":"865444df-f9b0-415e-a7ed-ccb59055c0be","resolution":{"observed_at":"2026-08-15T20:24:10.739799Z","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":"2026-08-15T20:24:11.779597Z","title":"A face antispoofing database with diverse attacks,","venue":null,"work_id":"bafbc001-2961-4883-9caf-ac1b90995ff7","year":2012},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.744055Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:7ab178c68d13c1ecf5d0207724488b328c194effa979a7510e9f2f9177358192","observation_id":"abdeb26e-2600-46c7-a6d1-ce798521d80b","resolution":{"observed_at":"2026-08-15T20:24:11.784820Z","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":"2026-08-15T20:24:11.767120Z","title":"Face spoof detection with image distortion analysis,","venue":null,"work_id":"60c23ac4-640c-407f-b9a2-774d19beaaf5","year":2015},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.748188Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:f09b7cf55c5d8b2640b65cb864d21d46b12fee136dff30b2df0a0d030ae5b797","observation_id":"8ead54f1-f9ad-436d-9d32-871d3eee6a19","resolution":{"observed_at":"2026-08-15T20:24:11.771122Z","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":"2026-08-15T20:24:11.752377Z","title":"A 3d mask face anti- spoofing database with real world variations,","venue":null,"work_id":"239ffe8f-4cad-4eb3-aa40-508e79e8750e","year":2016},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.752027Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:7637047005165dc39e54ef87b04efa9030787b1130d35dc404c7156cb1f3cc3a","observation_id":"fbd636fb-ddd9-40f6-bd34-badd2bf13431","resolution":{"observed_at":"2026-08-15T20:24:11.757607Z","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":"2026-08-15T20:24:11.739165Z","title":"Oulu-npu: A mobile face presentation attack database with real- world variations,","venue":null,"work_id":"4b077d6d-4dd1-4429-9eda-17bd57c450b3","year":2017},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.756070Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:300fcab77b042f8dd97f207648b98b351e33d7ec9ed68f0a756d528da3eff55b","observation_id":"63fe7a64-29d0-496d-a2f1-6f23ce062647","resolution":{"observed_at":"2026-08-15T20:24:11.743513Z","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":"2026-08-15T20:24:11.725810Z","title":"Unsu- pervised domain adaptation for face anti-spoofing,","venue":null,"work_id":"f3f807f2-f6ca-464f-96d1-a39317415cfd","year":2018},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.760108Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:43db241a453bbcc75b0d6af338d2f16138f2af1edcb811ca8d48105b99ae2b7e","observation_id":"9af6c87c-034f-477b-9e09-103ee025bbaf","resolution":{"observed_at":"2026-08-15T20:24:11.730296Z","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":"2026-08-15T20:24:11.711490Z","title":"Celeba-spoof: Large-scale face anti-spoofing dataset with rich annotations,","venue":null,"work_id":"fb25844d-1557-41c8-b7f7-6c27fa296a1e","year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.763970Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:c04fbe8e94fcbd3631e273ade17b14b84c5ddee769856418020fe8291c75626b","observation_id":"a597a770-8a27-4a98-8877-97ac70345983","resolution":{"observed_at":"2026-08-15T20:24:11.716389Z","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":"2026-08-15T20:24:11.699319Z","title":"Nas-fas: Static- dynamic central difference network search for face anti-spoofing,","venue":null,"work_id":"06a72692-1267-40cb-bfd9-9e435b5690fa","year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.767871Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:36c6cbaf9048bace81071763b312de0eb3d905bb78a45711e8fac0211494a109","observation_id":"19b956e1-0e2e-4129-8252-eda4b5ab13ff","resolution":{"observed_at":"2026-08-15T20:24:11.703086Z","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":"2026-08-15T20:24:11.686832Z","title":"Multi-domain learning for updating face anti-spoofing models,","venue":null,"work_id":"8082b754-ac08-457a-825e-bb92673419cf","year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.771737Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:f349342f048a2b75eb3da4b792f73c56f25ed6a8eeed9ec9b2adbc7e828c5173","observation_id":"98a69a12-e650-49e2-baa0-0c9a40d3c4da","resolution":{"observed_at":"2026-08-15T20:24:11.690857Z","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":"2026-08-15T20:24:11.673343Z","title":"Detection and continual learning of novel face pre- sentation attacks,","venue":null,"work_id":"e0e16e5f-b78b-4304-939f-17f716034a7a","year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.775639Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:987c0652c8db16682b6810dc8bb93dbcf4a6e0388b211226167bc644c54769ba","observation_id":"bf997ed5-b718-4f4b-a3af-71adf2e5b140","resolution":{"observed_at":"2026-08-15T20:24:11.677833Z","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":"2026-08-15T20:24:11.659703Z","title":"Deepfakes detection dataset,","venue":null,"work_id":"bf995124-9c9c-458e-9c32-0177d3f6fce6","year":2019},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.779520Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:011003c8ed0c52cad462b077f8aff959b2ff95164721f2742a3c30674edd0d93","observation_id":"7fe43758-eb20-4cab-bfb8-85ab739f7600","resolution":{"observed_at":"2026-08-15T20:24:11.664273Z","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":"1910.08854","last_updated":"2019-10-23T18:47:35Z","snapshot_observed_at":"2026-08-15T13:04:24.885978Z","submitted_at":"2019-10-19T22:35:52Z","title":"The Deepfake Detection Challenge (DFDC) Preview Dataset","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.08854","snapshot_observed_at":"2026-08-15T20:24:10.783354Z","title":"The deepfake detection challenge (dfdc) preview dataset,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.783354Z"},"links":{"cited_paper":"/paper/1910.08854","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:0853a395227b70126419b1e9b624ab3ad425de937ed97cc2856bd23c09276807","observation_id":"daa6af44-74e7-4707-a1c4-bbc1ef8a6f2b","resolution":{"observed_at":"2026-08-15T20:24:10.783354Z","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":"2026-08-15T20:24:11.645622Z","title":"Faceforensics++: Learning to detect manipulated fa- cial images,","venue":null,"work_id":"8bd8ccd0-265f-4a4f-b117-e63681454540","year":2019},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.787696Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:0c884776b0a1c2a7529aa4239a6bf34dd68cd156c8514d1a1ee97b292c35a724","observation_id":"333f23a8-d329-4cd3-bfd5-062617cea4f6","resolution":{"observed_at":"2026-08-15T20:24:11.650256Z","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":"2026-08-15T20:24:11.631605Z","title":"Celeb-df: A large-scale challenging dataset for deepfake forensics,","venue":null,"work_id":"33be7ef1-a49c-42a4-bf81-f6d3b9d74fa5","year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.791095Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:29b7f5344fe474f39c175bd0dea81d29f2574ec767805e4ce5b7777f520afc39","observation_id":"1b711f0a-3f18-45fe-a889-133338dcd110","resolution":{"observed_at":"2026-08-15T20:24:11.636198Z","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":"2026-08-15T20:24:11.616321Z","title":"Deeperforensics- 1.0: A large-scale dataset for real-world face forgery detection,","venue":null,"work_id":"403872aa-e0ed-44e7-93e9-bb95f6be8a40","year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.794537Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:f9a6ad9a2cbec84160cb3db7fb8bfd1ab9c5a14670e9f95fc8c7dda82986e929","observation_id":"b655f548-7e75-4bbb-9c7a-d3b3402f87ff","resolution":{"observed_at":"2026-08-15T20:24:11.621215Z","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":"2026-08-15T20:24:11.602087Z","title":"Face forensics in the wild,","venue":null,"work_id":"05211bd1-7065-4009-b275-5a24b98e80a3","year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.797964Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:7e52275cf141cf2175238c3f9a7ed001ded4ec59497020ea9d13f9f55172762d","observation_id":"acfebec3-87d8-481d-a10d-b5d9323adef2","resolution":{"observed_at":"2026-08-15T20:24:11.606648Z","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":"2026-08-15T20:24:11.588166Z","title":"Forgerynet: A versatile benchmark for face forgery detection and localization,","venue":null,"work_id":"e4f44a0e-6390-4bfb-9697-7e0931053088","year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.801309Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:ba413b9dc72b54b324bd9e0d29b86fdcba03cd05f05ee2fcfcfb4512a54bc5ef","observation_id":"fb9779bd-ac04-4e3a-91ea-5c877706e1ab","resolution":{"observed_at":"2026-08-15T20:24:11.592724Z","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":"2026-08-15T20:24:11.573129Z","title":"Casia- surf cefa: A benchmark for multi-modal cross-ethnicity face anti- spoofing,","venue":null,"work_id":"b3001d90-7c99-4787-bb11-011970ac43f5","year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.804813Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:a7c8240f285ca922a7237834d36fe62ebfe9c975a589eade245f0f19a7104495","observation_id":"906b5646-78bd-4390-b603-73a0aa440c5a","resolution":{"observed_at":"2026-08-15T20:24:11.578456Z","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":"2026-08-15T20:24:11.557598Z","title":"La- softmoe clip for unified physical-digital face attack detection,","venue":null,"work_id":"57f3e641-94f9-47ff-89b0-5855948f86d1","year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.808268Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:7eac0e0a45d4fb795e0909d06f5caf5f06990716fb969ef3094f8dd04cfecbad","observation_id":"c027fdd7-16a7-45f5-90ca-70cc6dddacb8","resolution":{"observed_at":"2026-08-15T20:24:11.562071Z","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":"2026-08-15T20:24:11.544807Z","title":"Mixture-of-attack-experts with class regularization for unified physical-digital face attack detection,","venue":null,"work_id":"851c0bd5-e84f-421a-aca2-38f8bc9e254a","year":2025},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.811736Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:e193190d6702f793963b71013b48c6b70f5aa92132c54886c2dee2ad66a781f5","observation_id":"fee6ca0e-18b2-49c4-8f99-298a43ae26f1","resolution":{"observed_at":"2026-08-15T20:24:11.548930Z","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":"2504.00454","last_updated":"2025-04-01T06:19:50Z","snapshot_observed_at":"2026-08-16T12:45:04.409791Z","submitted_at":"2025-04-01T06:19:50Z","title":"FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detection","version":1},"cited_work":{"arxiv_id":"2504.00454","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.00454","snapshot_observed_at":"2026-08-15T20:24:11.116369Z","title":"FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detection","venue":"cs.CV","work_id":"a9243ddc-1272-462f-b871-f1624698f549","year":2025},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.815344Z"},"links":{"cited_paper":"/paper/2504.00454","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:a29cf780e0fe1b2a5136bd30042f3551af5c42143dbc89689644f0739181270b","observation_id":"fc0dc271-082c-4e99-b30d-a8623c2cc262","resolution":{"observed_at":"2026-08-15T20:24:11.121373Z","resolver_source":"local_arxiv","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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:24:11.532039Z","title":"facenet-pytorch,","venue":null,"work_id":"988520c3-a23e-4490-8493-6ae45d57260f","year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.819738Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:fb7db443b04f92281f67bfaa1a65b958a40b55cd9e9e052302a6ec0dec0f2315","observation_id":"1a7ca779-b216-4e25-bdeb-6e1a11e4f5b6","resolution":{"observed_at":"2026-08-15T20:24:11.535853Z","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":"2026-08-15T20:24:11.518532Z","title":"Ghost—a new face swap approach for image and video domains,","venue":null,"work_id":"7f007be2-4aab-4186-939b-ea1e9e2a6bf1","year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.823683Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:76177b403586d06279fd64bb7f86c493fca4e228b75ce42005b16bdb7d19a80a","observation_id":"9f79bb0a-29f7-4890-a4e5-314ec06d29c5","resolution":{"observed_at":"2026-08-15T20:24:11.523194Z","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":"2026-08-15T20:24:11.503895Z","title":"Facial geometric detail recovery via implicit representation,","venue":null,"work_id":"f4f1a901-df49-4ac6-8e71-a36f033169c7","year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.827667Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:47704677fee03edcf9987afc45f91d817afe8aa21be3e2df438896b0b00446b8","observation_id":"6f95c57f-592f-4a79-873b-abf647726d4a","resolution":{"observed_at":"2026-08-15T20:24:11.508780Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:24:10.831580Z","title":"Blendface: Re-designing identity encoders for face-swapping,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.831580Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:6175a3dbd7007a23b6d15a7f8160dfaeaa7a29021592f5b00bce98a163572984","observation_id":"a775233b-e8b5-430f-929b-73a5454a010b","resolution":{"observed_at":"2026-08-15T20:24:10.831580Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.07269","last_updated":"2024-09-11T13:43:53Z","snapshot_observed_at":"2026-08-16T13:19:27.311956Z","submitted_at":"2024-09-11T13:43:53Z","title":"Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.07269","snapshot_observed_at":"2026-08-15T20:24:10.835424Z","title":"Realistic and efficient face swapping: A unified approach with diffusion models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.835424Z"},"links":{"cited_paper":"/paper/2409.07269","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:3b78c22ee90539bb270c1167445dccd560e7698e83535821d8521b924254b362","observation_id":"ecd87a93-8491-4a9a-a4e6-43574d8ac6cf","resolution":{"observed_at":"2026-08-15T20:24:10.835424Z","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":"2026-08-15T20:24:11.480616Z","title":"Motion representations for articulated animation,","venue":null,"work_id":"af28ea4d-6a6b-4d6b-9469-fdf18caa8dca","year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.839740Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:c2d04a612c67e94b57d77e0da150f55be1a229d7b8ad8381b3e57c831406f8ed","observation_id":"acbd282e-2acf-44ac-8cfa-ac551241a81b","resolution":{"observed_at":"2026-08-15T20:24:11.485487Z","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":"2026-08-15T20:24:11.467094Z","title":"Information bottle- neck disentanglement for identity swapping,","venue":null,"work_id":"ffdb000e-90f4-4278-9db3-206a9ceec31d","year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.843993Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:1275fbf11f2b42c44fa34aeed300e7b6ad6cf6e69d7313b95cd86530fad2e0aa","observation_id":"4a06ed1d-1829-4d73-b807-527e44fa32d6","resolution":{"observed_at":"2026-08-15T20:24:11.471524Z","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":"2026-08-15T20:24:11.451950Z","title":"One shot face swapping on megapixels,","venue":null,"work_id":"045ce1fc-63ca-45da-a61e-32a134e9f965","year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.848370Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:46aad92c031e51a5c3c2dd6a5e7b480fa5f26d681f04ae525299e6853c4e47f0","observation_id":"787d1dc3-62fc-4e86-9d7a-8a9d03e43c68","resolution":{"observed_at":"2026-08-15T20:24:11.457440Z","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":"2106.09965","last_updated":"2021-06-18T07:39:09Z","snapshot_observed_at":"2026-08-16T18:16:11.686593Z","submitted_at":"2021-06-18T07:39:09Z","title":"HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09965","snapshot_observed_at":"2026-08-15T20:24:10.853352Z","title":"Hififace: 3d shape and semantic prior guided high fidelity face swapping,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.853352Z"},"links":{"cited_paper":"/paper/2106.09965","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:117fe65fe1057a0d3266bc82b52dc431a6c8b4abeea39d9e87f10f1c4c9749f0","observation_id":"63cba4dd-12b3-46d7-be26-447f6991b2c4","resolution":{"observed_at":"2026-08-15T20:24:10.853352Z","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":"2026-08-15T20:24:11.435743Z","title":"Diffswap: High-fidelity and controllable face swapping via 3d-aware masked diffusion,","venue":null,"work_id":"e9b46341-efb6-42b7-860d-249bbbd71f1e","year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.858084Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:a387f9dc8e9ee1164a01d671f3af1a43d54a6ce6bff7bca8f76e4ac4a24217df","observation_id":"84e3e2af-da4c-4c19-9071-07ded4c81b4b","resolution":{"observed_at":"2026-08-15T20:24:11.441776Z","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":"2026-08-15T20:24:11.420887Z","title":"(2024) Deep-live-cam: Real-time face swapping and animation tool","venue":null,"work_id":"67aa6872-a26b-4b2a-be4a-8fbc9efd2522","year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.862072Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:9eca47f185748dfacdbf73bcbcca6a3d54af36a0ebfd28657333745b174b9735","observation_id":"996cefc1-c1fd-4915-bfc3-e68f96598ba2","resolution":{"observed_at":"2026-08-15T20:24:11.424949Z","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":"2026-08-15T20:24:11.407597Z","title":"Roop: One-image face swap on video,","venue":null,"work_id":"f0678852-b17f-40c2-8c7b-1fdd00d5a031","year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.866413Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:a0b6ccf8761ca400c0666b7470cfba4050612295655fd86b9d33d5142c1df63b","observation_id":"42931281-4216-40a4-824b-0f77b60550ae","resolution":{"observed_at":"2026-08-15T20:24:11.411784Z","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":"2026-08-15T20:24:11.393918Z","title":"Augmented lagrangian adversarial attacks,","venue":null,"work_id":"d45c1087-ef50-4742-b93a-0ba2df891479","year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.870564Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:3e373baaff99cbaf9e5d92c1a4f201450db3771a3f3f5c4b7a70ad7a12c068df","observation_id":"74545675-8148-4acb-ba60-bc095aee737f","resolution":{"observed_at":"2026-08-15T20:24:11.398273Z","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":"2026-08-15T20:24:11.380191Z","title":"Advdrop: Adversarial attack to dnns by dropping information,","venue":null,"work_id":"25b5740b-9b30-4130-998a-8e2bcf4a5381","year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.874684Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:2e1f5d68900b0be6eafc0cd536fe1babb4131cfa8413e0e26e39b93c69a54f08","observation_id":"af6e4775-41d8-4b06-9e3e-2d114f624cb2","resolution":{"observed_at":"2026-08-15T20:24:11.384344Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:24:10.878933Z","title":"Reliable evaluation of adversarial ro- bustness with an ensemble of diverse parameter-free attacks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.878933Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:cd4b630c4caa16459af3e295fa2df474986f8105fc49b64b289a1b264a9202d9","observation_id":"cc3fdde8-fc83-4898-b6fb-d239e29bf90c","resolution":{"observed_at":"2026-08-15T20:24:10.878933Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-15T20:24:10.883345Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.883345Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:829643596ea95e45a7efdb6b802824addaab63645fd382b8e6c71749a6a123fc","observation_id":"e40ec074-6ee6-482b-a5fc-5bbfa69219c0","resolution":{"observed_at":"2026-08-15T20:24:10.883345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.06281","last_updated":"2020-02-03T02:58:31Z","snapshot_observed_at":"2026-08-16T03:15:37.843175Z","submitted_at":"2019-08-17T10:03:05Z","title":"Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.06281","snapshot_observed_at":"2026-08-15T20:24:10.887897Z","title":"Nesterov accelerated gradient and scale invariance for adversarial attacks,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.887897Z"},"links":{"cited_paper":"/paper/1908.06281","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:219d9f116c8e66033d12d887226bda9edcb244727bc2898a45e75630422548f5","observation_id":"dcdea9bc-8419-4abf-8d81-598217a113cb","resolution":{"observed_at":"2026-08-15T20:24:10.887897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.15503","last_updated":"2021-06-08T12:52:44Z","snapshot_observed_at":"2026-08-16T18:55:02.056219Z","submitted_at":"2020-12-31T08:40:42Z","title":"Patch-wise++ Perturbation for Adversarial Targeted Attacks","version":3},"cited_work":{"arxiv_id":"2012.15503","doi":null,"metadata_source":"pith","pith_arxiv_id":"2012.15503","snapshot_observed_at":"2026-08-15T20:24:11.038825Z","title":"Patch-wise++ Perturbation for Adversarial Targeted Attacks","venue":"cs.CV","work_id":"928b2633-4516-4389-80b6-a64769058d02","year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.892089Z"},"links":{"cited_paper":"/paper/2012.15503","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:81c0941a712e8025df4afcdead6203d9d2f38cee110bcc64d6320933482fcc50","observation_id":"7ae63dd9-adb4-4d70-b4b9-11d79fc5482e","resolution":{"observed_at":"2026-08-15T20:24:11.045345Z","resolver_source":"local_arxiv","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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:24:11.356042Z","title":"Pixle: a fast and effective black-box attack based on rearranging pixels,","venue":null,"work_id":"e50f80ed-594d-4c9c-986f-25a09c9dcf32","year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.896618Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:40dd44c884e02f747e0156c3565f0a616c1fd04987ec3ab0cd7cf4171c527c84","observation_id":"ca249589-f7b5-46b4-9f6e-d25dda3c897c","resolution":{"observed_at":"2026-08-15T20:24:11.361464Z","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":"2026-08-15T20:24:11.342022Z","title":"Enhancing the transferability of adversarial attacks through variance tuning,","venue":null,"work_id":"22b47ad1-6eaf-4b7e-b571-5e52d1f0f883","year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.900140Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:d33f6325ab972e2223a113d4c6d5cfd62aa95c63e7d3183876a26f007d631db9","observation_id":"85a86855-a528-4619-99fc-467c3dc28d3f","resolution":{"observed_at":"2026-08-15T20:24:11.346742Z","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":"2107.01396","last_updated":"2021-07-03T10:14:01Z","snapshot_observed_at":"2026-08-16T18:12:35.658968Z","submitted_at":"2021-07-03T10:14:01Z","title":"Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.01396","snapshot_observed_at":"2026-08-15T20:24:10.903717Z","title":"Demiguise attack: Crafting invisible semantic ad- versarial perturbations with perceptual similarity,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.903717Z"},"links":{"cited_paper":"/paper/2107.01396","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:f49a4a18d44cf898e75f5c51c5d91b5a7374c7db7b262af1e1883b42c9ce2694","observation_id":"a9c79061-02fe-4587-a9f8-23a8a970391a","resolution":{"observed_at":"2026-08-15T20:24:10.903717Z","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":"2026-08-15T20:24:11.328147Z","title":"Photomaker: Customizing realistic human photos via stacked id embedding,","venue":null,"work_id":"030641a0-b6b7-41df-852e-ab99296ef7f3","year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.907338Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:ee9a59e34bdf7ad7db3a7e03c215bd451670701d87c1d15324a5b65a90e38826","observation_id":"353588f6-8ee4-46b3-9408-bc0c6164887e","resolution":{"observed_at":"2026-08-15T20:24:11.332654Z","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":"2308.06721","last_updated":"2023-08-13T08:34:51Z","snapshot_observed_at":"2026-07-06T16:05:39.158819Z","submitted_at":"2023-08-13T08:34:51Z","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.06721","snapshot_observed_at":"2026-08-15T20:24:10.910851Z","title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.910851Z"},"links":{"cited_paper":"/paper/2308.06721","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:d237dd983bd6cbdf1e1407a9a22942cc1952f1400c5720594e6da0a54bcd9394","observation_id":"b6b1054a-d3be-440f-a4b7-026c777adee4","resolution":{"observed_at":"2026-08-15T20:24:10.910851Z","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":"2026-08-15T20:24:10.914837Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.914837Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:13920509480a879bccd5fd9f0e618732d95ec4d6c601b4098696b8062b767183","observation_id":"61060bde-4de8-4df4-934d-de2635dc30d4","resolution":{"observed_at":"2026-08-15T20:24:10.914837Z","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":"2026-08-15T20:24:10.918337Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.918337Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:b13d3b1a4ad3aab7ad7206f54accb214812823ac02ec94dc7fecc0c2d2fc36f0","observation_id":"b8053a13-60dc-4bef-9177-62afbc143c29","resolution":{"observed_at":"2026-08-15T20:24:10.918337Z","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":"2026-08-15T20:24:10.923478Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.923478Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:a16b2ce95d432154fafa1b2ff20656f76508f0539fd5b5adb39cc822e0f69e26","observation_id":"41807c5f-9f05-4b30-80f9-8f56c347f8c5","resolution":{"observed_at":"2026-08-15T20:24:10.923478Z","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":"2026-08-15T20:24:10.927534Z","title":"Learning to prompt for vision-language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.927534Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:1db07cde77ca5e0a3b33e6335c853f0493eb7dc4ecf5e6aec55119c6ac18f96b","observation_id":"8884a0c1-1640-441f-947e-ad8d2e43b7cc","resolution":{"observed_at":"2026-08-15T20:24:10.927534Z","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":"2026-08-15T20:24:10.931462Z","title":"Visual prompt tuning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.931462Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:41630d370bce254f314104cabf5186517a2c9f235992d2d74fec7e2c8731f0e9","observation_id":"e4c21779-8517-4521-8ccf-2cf5303f0ce0","resolution":{"observed_at":"2026-08-15T20:24:10.931462Z","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":"2026-08-15T20:24:11.269513Z","title":"Visual prompt flexible- modal face anti-spoofing,","venue":null,"work_id":"ee792e3a-672c-4509-be4a-fc8f6a85ebaa","year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.935453Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:a696d185f52781693318acd8ebb8c3b87c850285db8714eab575231313497ed1","observation_id":"c5d9f5f2-b37c-40b7-9375-ddb0b96c1cb0","resolution":{"observed_at":"2026-08-15T20:24:11.274770Z","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":"2026-08-15T20:24:11.255871Z","title":"Searching central difference convolutional networks for face anti- spoofing,","venue":null,"work_id":"58b65e5b-6a70-447d-a631-81a7601f59f9","year":2020},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.939409Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:19fc8729cd6114460ee31676777a54e8c8528f4b03c8dcb332fbba6d6e168707","observation_id":"911520d3-4442-4ef7-8c33-027e85b6b27d","resolution":{"observed_at":"2026-08-15T20:24:11.259788Z","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":"2026-08-15T20:24:11.243291Z","title":"Cfpl-fas: Class free prompt learning for generalizable face anti-spoofing,","venue":null,"work_id":"c5f56cd1-7997-4360-b4ef-89dd2600a8fc","year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.943553Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:d9855701cdb3cca4997c16823ae6c288e609641d498dfebd152b51d6f15fac84","observation_id":"e0e8c2c2-9ebe-4140-a5f4-034392ebc2bf","resolution":{"observed_at":"2026-08-15T20:24:11.247208Z","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":"2404.08452","last_updated":"2025-08-20T10:55:11Z","snapshot_observed_at":"2026-08-16T14:01:26.139874Z","submitted_at":"2024-04-12T13:02:08Z","title":"MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.08452","snapshot_observed_at":"2026-08-15T20:24:10.947931Z","title":"Moe-ffd: Mixture of experts for generalized and parameter- efficient face forgery detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.947931Z"},"links":{"cited_paper":"/paper/2404.08452","citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:711a95d5aecaf2e6d1247162c747ebe8e70cdc5322b5fa83d61e1c08eb074962","observation_id":"018ec813-b59a-4674-9e2a-12148d9edbee","resolution":{"observed_at":"2026-08-15T20:24:10.947931Z","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":"2026-08-15T20:24:11.229829Z","title":"Laa-net: Localized artifact attention network for quality-agnostic and generalizable deepfake detection,","venue":null,"work_id":"3b04a118-5ad9-42cf-92b5-e38d20ed6dfb","year":2024},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.952262Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:6edbd0e86fa79bb0c878aac70e1a10f0a5113e5380931a89e5bb765e310bd001","observation_id":"fb0459e6-d3f2-41c8-b133-7d8a18861c3b","resolution":{"observed_at":"2026-08-15T20:24:11.234249Z","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":"2026-08-15T20:24:11.215826Z","title":"Mesonet: a compact facial video forgery detection network,","venue":null,"work_id":"9eb76f21-f03c-4870-93a2-9f643d5cdff0","year":2018},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.956587Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:1fddab7614195b360364832a1c632f7ec570d3cec493438f34a8e846449908ef","observation_id":"99e98973-8365-4111-af08-9fdc2a9636a1","resolution":{"observed_at":"2026-08-15T20:24:11.220469Z","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":"2026-08-15T20:24:11.201665Z","title":"Xception: Deep learning with depthwise separable convolutions,","venue":null,"work_id":"66aa1ab2-c03c-40e1-871e-d86e5abd46ec","year":2017},"citing_paper":{"arxiv_id":"2505.13327","last_updated":"2025-07-13T16:22:29Z","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","version":3},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-15T20:24:10.960879Z"},"links":{"citing_paper":"/paper/2505.13327"},"observation_digest":"sha256:d38ceb2b93c62c85cca168f757098ed5933c00844f37345dd68cad83f21fd9f8","observation_id":"add5aa00-a030-4026-ac3a-348b09e882a7","resolution":{"observed_at":"2026-08-15T20:24:11.206228Z","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":"2505.13327","last_updated":"2025-07-13T16:22:29Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T03:16:48.903254Z","submitted_at":"2025-05-19T16:35:45Z","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning"},"reference_resolution":{"displayed":94,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":34,"verified_exact":2,"verified_fuzzy":58},"total_outbound_references":94},"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 18 August 2026, this Paper Citation Record lists 94 of 94 outbound references and 1 inbound Pith citation observation for arXiv:2505.13327."}