{"as_of":"2026-08-07T06:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1d5b4b315af199192bab5606d72cfb6baa6797bfdcf727b1b1388cd24ffbe3ed","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T18:48:48.581852Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.04484/citation-record","integrity":"/paper/2607.04484/integrity","json":"/paper/2607.04484/citation-record.json","paper":"/paper/2607.04484"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1612.00410","last_updated":"2019-10-23T22:47:44Z","snapshot_observed_at":"2026-07-06T05:21:01.935928Z","submitted_at":"2016-12-01T20:12:40Z","title":"Deep Variational Information Bottleneck","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.00410","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:1612.00410 (2016)","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/1612.00410","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:904e17e5b1c2b100134be5bc9860d04328d9254bf28b1b139dea2126d21ed17e","observation_id":"050b405e-0928-481f-81ad-baaa2cf75609","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16609","last_updated":"2023-09-28T17:07:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-28T17:07:49Z","title":"Qwen Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16609","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:2309.16609 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2309.16609","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:85d32e98b9fa282d7074cf58568309d8c8090201f7c6ee1a507c216faeb671c9","observation_id":"afc3e874-2df4-4d36-87da-7babe0609a82","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12966","last_updated":"2023-10-13T02:41:28Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-08-24T17:59:17Z","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12966","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:2308.12966 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2308.12966","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:dc8bca3d53e9e0f5cebf6c9a4b3df3a09736e70cb6fa57937d309cb1b0d05a51","observation_id":"75e46d9b-3402-442b-bf64-e6d41e086dbe","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: 32nd USENIX Security Symposium (USENIX Security ’23)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:c12f984bc99aac02abf42e092095db70aa5d52aae0ed01067a4010a50ffa07fb","observation_id":"eb1bf3f2-5f70-4983-b137-3b70d5d52bda","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the Computer Vision and Pattern Recognition Conference","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:7c9c5fe0f4739be06600ceee23e646cd52ace1ad4b31942ce7ffd35a8c133e7e","observation_id":"ffa09d69-d9a7-4052-853b-c7fed2011a55","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.00756","last_updated":"2026-05-21T07:46:00Z","snapshot_observed_at":"2026-07-06T22:06:24.923510Z","submitted_at":"2025-08-01T16:32:48Z","title":"LeakyCLIP: Extracting Training Data from CLIP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.00756","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:2508.00756 (2025),https://arxiv.org/abs/2508","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2508.00756","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:f499e1661fa051d698988668b3bd80580cbb34e01fa82e902e5f7901783b51cb","observation_id":"bb1fef16-a011-425c-800a-382b59992f57","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: CVPR","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:e91c08419253c13b9a8f9683aefc9c2d0d748d8bf480a2d90f3a7ff9d8819d6a","observation_id":"5db47425-3dc3-48ec-8a1b-0806172db931","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"Advances in neural information processing systems34, 8780–8794 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:09ce88615f1fc333911c866f0c479efdf2e037bd276303be3ea9ce912434e604","observation_id":"72ae7ddb-3287-4fa0-82b6-a13b102cfffe","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: CVPR","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:584d5b842f1c353df62ff748408ac1ea455bfedbdbe3bc032e644f58babce535","observation_id":"bb3286e3-4ca5-475b-a1b8-793b4e948dfc","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:3b98fd497f7bb1ad619404ba258446891efcddfac67f624392023f3aa8774d82","observation_id":"f8340c55-6531-45ee-bbe7-d7cc41bcdded","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.05897","last_updated":"2016-03-04T11:01:34Z","snapshot_observed_at":"2026-07-06T04:36:58.505806Z","submitted_at":"2015-11-18T18:06:24Z","title":"Censoring Representations with an Adversary","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.05897","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:1511.05897 (2015)","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/1511.05897","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:b62ad90821d35b5a6ab972e7f41e910d8dfa30faeaeea29d3bb65e32a9ba5cbe","observation_id":"51c74350-29a6-47d1-99d3-408b844e0488","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"Electronics14(7), 1282 (2025).https://doi.org/10.3390/ electronics14071282","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:fd2cae0d09f980392a87579f4ccb7d79daae0aaae622990db927c88ef181eb8b","observation_id":"408b9a1d-3dc3-45a7-b101-6e56f2127264","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security (CCS)","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:db33b6b630979721044aa153f9137a410d53459a8fc0704175d929f597775ff1","observation_id":"6d181e1e-9826-4597-8a86-53a0d5bc9e38","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.13394","last_updated":"2025-10-24T02:45:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-23T09:22:36Z","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.13394","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:2306.13394 (2023),https://arxiv.org/abs/2306.13394","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2306.13394","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:8dda5e56f5ada1fb6c8ff128189818c3ca2a182ead0bb24d8f85a81290bc8611","observation_id":"aa481cb7-be3d-4ef7-a7df-929a428d6e6a","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Advances in Neural Information Processing Systems","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:cbf438c6d55d11153f55841d6643485abd70880a1abe2fa1e0d42209bb327c50","observation_id":"ca380b56-386a-4bad-af1c-d1e66901dab3","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: CVPR","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:d558def8b32affa111814c5c6382f19c3fd106fb97063d4d49a29cc0ba17a47b","observation_id":"17c879ec-222c-479a-a75e-046a60a1f2fa","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:a15101119136e00f4014616bc7e5f1a58911c8e425d2b7ac3853a45894f0e0ce","observation_id":"7c1e7b23-658b-4cf4-a57d-4d57ca85b8bb","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:919de568649f03f91929030b2bcc6b0b0b53fe0686ca9dbad79f426b1148b970","observation_id":"98fd02e6-9cfe-447b-99cb-4f6e94757bc4","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: NeurIPS","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:062f32aa5562f34b81d9d51975e7471dcbc5b7e6e10748f75b28d47dc6738608","observation_id":"aacf54f1-5f4b-4163-b10a-f96abc544163","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: International conference on machine learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:a17ecb4998151ad1a6b09be3c534fdb00393c00d991c47fd1ac8315df458eaa1","observation_id":"a0c8d365-1a76-4332-abf7-3f2c23b227e4","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08173","last_updated":"2024-03-01T04:24:04Z","snapshot_observed_at":"2026-07-06T15:42:18.360486Z","submitted_at":"2023-06-13T23:32:09Z","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08173","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:2306.08173 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2306.08173","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:5fafef0e4b85ed25e6b68b126f0b82005810ea6b1aba45694256420847e69387","observation_id":"731366d6-6860-4b75-89b7-9713c0cc022b","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:5e7e05b1ec222801d648cd27cf527fa55595865cc9fcd5f3b267e0e3efaeb282","observation_id":"5a670c59-a240-412f-8eeb-f3e32777f86a","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"com/mlfoundations/open_clip(2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:21ad85fb074d11e369a1834741d5a1b9d24dab02d1887bde31cb584d34f528ec","observation_id":"0789dab0-1d8c-4014-b7af-bd9f06e458f9","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: CVPR (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:c7bcd778490966650f5e7af1971f3dcbb21f8845d87f80b30e42eb784c06b9d5","observation_id":"a96a4e37-0dfd-4c4b-bc11-c4888edd35fc","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02580","last_updated":"2024-03-05T01:32:29Z","snapshot_observed_at":"2026-07-06T17:39:37.064843Z","submitted_at":"2024-03-05T01:32:29Z","title":"What do we learn from inverting CLIP models?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02580","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2403.02580","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:36ad99a44cb5c633984a106ffe15b12ce519acb709c21a247d0fe0829378c974","observation_id":"5e06df4b-9dac-4207-b2d0-eb9e6647b4e6","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:a965b88492b14ffae702652ef3d57c4e42edf1fc0f60fedcb59a401b32cfee28","observation_id":"4634b428-7569-47db-ba06-021dd29466ce","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:18f5f39482a1be8d643437d41d153465c4874ae7b1b72fc876990690d454edb3","observation_id":"7b691386-c651-4064-a2d2-38a878f1bdd9","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the IEEE/CVF International Conference on Computer Vision","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:b4c4c0232c0ffe9c0e6623e0fc8b1214831676be35f4aa5c29b0444231b73d45","observation_id":"37e89067-6f75-483f-915c-27888a9d9b91","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10355","last_updated":"2023-10-26T02:52:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-17T16:34:01Z","title":"Evaluating Object Hallucination in Large Vision-Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10355","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the 2023 Con- ference on Empirical Methods in Natural Language Processing (EMNLP) (2023), https://arxiv.org/abs/2305.10355","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2305.10355","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:294bca055ff8996012d666d2b288c9aea221130be29c0dd757fa7774a777c7aa","observation_id":"ec282ca4-02db-4097-8e5d-dcff23605ce8","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03744","last_updated":"2024-05-15T19:22:44Z","snapshot_observed_at":"2026-07-06T16:28:22.350574Z","submitted_at":"2023-10-05T17:59:56Z","title":"Improved Baselines with Visual Instruction Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03744","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv:2310.03744 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2310.03744","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:77bd9f550d73e2591c2c24b542be4dc079ccbb88d5771a10d1f3a3ce3419ee67","observation_id":"35ed8ced-f7ef-4d57-bca5-f0e1b3d99e55","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:647f564ad5d6a007ccdb9a143c7dbf2538405b86e4e4321439a292d17c13677f","observation_id":"3a5c2645-5eb0-4ce3-b05c-c622fb5da42a","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.08485","last_updated":"2023-12-11T17:46:14Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-04-17T17:59:25Z","title":"Visual Instruction Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.08485","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:2304.08485 (2023),https://arxiv.org/abs/2304.08485","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2304.08485","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:cd39d990ffa1bd0ccd6871b01ef23a2cb2a8ab3878512eb5b7397c74ffceb033","observation_id":"f16648be-d1e8-49ff-a061-c888588e8cf6","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:3a57ebfcc4e5780628ff4ec21de15cdb9ba36bacd8a570ef1ae24dc86c7f76de","observation_id":"e4c352a3-2579-4b51-bf1b-63894c0fca70","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.09513","last_updated":"2022-10-17T07:46:47Z","snapshot_observed_at":"2026-08-02T03:10:19.073297Z","submitted_at":"2022-09-20T07:04:24Z","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.09513","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2209.09513","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:6541b5067442048549eaedb354db29eb82f8ac576a584520210a32246a186dd3","observation_id":"ee547ed2-3524-4963-b471-0d541cdeef6e","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: CVPR","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:8f3142239b426e66b8dcd6cd29595d2063b3c37f6870b27204ac19581ee1b714","observation_id":"9ba613a1-3982-437c-a7ac-99e56717a97b","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.01073","last_updated":"2022-01-05T00:07:35Z","snapshot_observed_at":"2026-07-06T11:34:54.333802Z","submitted_at":"2021-08-02T17:59:47Z","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.01073","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:2108.01073 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2108.01073","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:4609e4645e79a747dfdd366d9a983de1647b9ecae0ce85457f829400c8df5432","observation_id":"88eb3e27-1bb8-4ad1-a1d2-66b9e49cb60f","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:4a5ac81cb6c9629124974d78764e5188b4ed1776f6d098a6f9be103491320f4a","observation_id":"6c910bf7-c98b-467e-8c68-4525fa9abb1d","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: CVPR","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:eea479af9ac32a7037a4021fa7d9aa2014ae29657a50572cc42a0d4c39d05bd0","observation_id":"c82be3be-1bf9-4381-8ad4-2a93b5dcd105","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the AAAI Conference on Artificial Intelligence","venue":null,"work_id":null,"year":1965},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:3ba2e32c4734bba5a328032ae89988db69a6c865c977f8b26357b9dd24604abf","observation_id":"5558f867-ab73-43c2-971d-353e1d0085ec","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: CVPR","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:479aa4cef29a8a1d338ee420450c74f994dcf0f91af6956ab5fe0b10a007b0ca","observation_id":"1a786f81-31d4-4538-8f1c-fced0fd2e799","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-06T05:58:29.182448Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:2304.07193 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:b4c70019cad37dee01a22cda207e0b88d6898b8f2feda145ae8cebe5abb800e7","observation_id":"46417a52-36df-482d-8278-61d3bd1d4ce3","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:7eaae1b808371ee715c1754581f62dcdb2628f611ddac6e95d2a30fb72821bb1","observation_id":"3ee68746-d630-441b-9570-4f2156989d97","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: International Conference of Machine Learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:48731654e0343666101b9baaebe334a18f46d21db5b5511706eacbb95439e05c","observation_id":"cb312a49-f72a-4053-8c3e-c095334cabef","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:89183718aa12a485ca1e3baec4182b09cb8359d8714938b1baf3f1f8b341c5a2","observation_id":"d57e9fa8-7652-488a-8001-f21f80458152","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:5b3b28360db4035f6a02aede49dbc60755e66330be5624debeabcd7d69c99546","observation_id":"89f70ad3-a956-4264-87e2-dd2fb193b146","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"IEEE Internet of Things Journal (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:9862f61174a18f65faa6c5033301427abb92252346f8bbd946412a17fe402d71","observation_id":"fff967ff-f7c9-4826-9b31-8fe7bb627306","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.08920","last_updated":"2019-05-13T23:28:48Z","snapshot_observed_at":"2026-07-06T07:47:04.116217Z","submitted_at":"2019-04-18T17:55:37Z","title":"Towards VQA Models That Can Read","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.08920","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the TrustCLIP 19 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019),https://arxiv.org/abs/1904.08920","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/1904.08920","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:3abc18ec8cf7fc070b80a9eef28ad1f3a3c07aa3b4397f3194aa95a5af5d5060","observation_id":"5206297c-dea9-48ea-929b-a52ba970d5ba","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: ICLR (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:fa8a8e79593b834154fcd849ed03b23818464756d08708288095a5acde724622","observation_id":"1c1b0445-538f-4f08-b186-abdda7f0222b","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: CVPR","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:c423a0fbc4ec63ee7b9c87914a78b3d0496d4bd7da66b352af540214404a7c08","observation_id":"0333b0eb-2b3f-4c39-a476-169e39528af2","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: International Conference of Machine Learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:9e145550a6ca23ac2dded83514ebd9fe5399196edcb53587865e2214d5aeea67","observation_id":"a5e778a0-6cc9-4052-8169-c4ad477f614c","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:8e342aefc36c0534f87870155001ad208fc0358a2460f08cba3b1a8b922117cb","observation_id":"4852d3e1-4a15-478b-9b61-3b132456b99f","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:150b4d619fadd8e97e76fb619a19a07c58ecc2cbde0787fd73b281df0576268a","observation_id":"7cf0a8d3-9715-4b81-b2e5-8dc6a4cd401e","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:d1b3fd15be8903640dbd324f905e341967e94053029a55ba52068e46fdb732aa","observation_id":"24660065-7454-4521-a562-3fe21a5478c5","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:1712fa0695d49b4b1bf55ba27c77a931846b91bfadcee52c1260d57e85fc6394","observation_id":"2e8f9268-6cad-471c-8b39-9ab15eefc29f","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"6027.375520","doi":"10.1145/3746027.3755203","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"In: Proceedings of the 33rd ACM In- ternational Conference on Multimedia (MM ’25)","venue":null,"work_id":"43fc59f0-a0f6-40a3-a5d9-66c47af2ab49","year":2025},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:d615c4f1e1f18d576aa6dc9fd9bea62f074beb2ab7a6e2457e42ac40a2f2027a","observation_id":"2914a6ff-eac8-486f-896e-aa5802da8e48","resolution":{"observed_at":"2026-07-11T18:58:11.489033Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-07-12T07:49:14.756384+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T07:49:14.756384+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:2308.06721 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2308.06721","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:59ba56c4440d9936dea4c57765b191cdb1990fb71401af3c8ef41054452aeed6","observation_id":"f7bd1adf-06cf-48ac-b46e-f319301c6999","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.02490","last_updated":"2024-12-01T05:46:03Z","snapshot_observed_at":"2026-08-06T13:03:19.727877Z","submitted_at":"2023-08-04T17:59:47Z","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.02490","snapshot_observed_at":"2026-07-11T18:48:48.581852Z","title":"arXiv preprint arXiv:2308.02490 (2023),https://arxiv.org/abs/2308.02490","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"cited_paper":"/paper/2308.02490","citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:2abe6b8fadb29cbb052aa5c81a916633b553a87802010a6aea99f81fda9492e8","observation_id":"1cd8d24f-b774-45dd-aa00-d256fa1c99db","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: Proceedings of the IEEE/CVF international conference on computer vision","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:2153d8361bcc2d295c8e2881f26ab11375ca2225ff80a6e47694dc70b45fd851","observation_id":"242108f7-98ff-4e1f-9c04-31b1c966f4b9","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: ICCV (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:8bcd42958f0d096bc9d93bb22e4add9676fa26620cb7a946c43c6b82bdea10fd","observation_id":"73dda727-3f25-41e4-b5c1-4452856c75d9","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":"In: CVPR (2018)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:67213ed89567631ce73529d0e4b6aa27a48a6f9eac293104a136fd2ec57a4648","observation_id":"71531dd3-3d17-449c-8c66-8518b6f440cf","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","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":"2026-07-11T18:48:48.581852Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-07-11T18:48:48.581852Z"},"links":{"citing_paper":"/paper/2607.04484"},"observation_digest":"sha256:b0c3987c435823bc455e7da3c1db736c3fde2f00f61d9aaed8e622f98430d7a5","observation_id":"cff58b55-e198-4ea6-aa20-fb62d9a02fc3","resolution":{"observed_at":"2026-07-11T18:48:48.581852Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.04484","last_updated":"2026-07-05T20:11:00Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T08:14:49.273656Z","submitted_at":"2026-07-05T20:11:00Z","title":"TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":58,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":61},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 0 inbound Pith citation observations for arXiv:2607.04484."}