{"as_of":"2026-08-09T07:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fe676ea8728c03509636fe50515612c5af1b9316f5f82ee4a4aec6be75c46409","coverage":[{"denominator":55,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":55,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T15:56:45.318431Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2607.18142/citation-record","integrity":"/paper/2607.18142/integrity","json":"/paper/2607.18142/citation-record.json","paper":"/paper/2607.18142"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2511.21631","last_updated":"2025-11-27T12:16:54Z","snapshot_observed_at":"2026-07-06T22:37:03.716474Z","submitted_at":"2025-11-26T17:59:08Z","title":"Qwen3-VL Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.21631","snapshot_observed_at":"2026-08-01T15:56:40.934325Z","title":"arXiv preprint arXiv:2511.21631 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:40.934325Z"},"links":{"cited_paper":"/paper/2511.21631","citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:a761c659b446f103c3aa6af9c0c9bc305b014193cbc205001730afd8bf1b76e0","observation_id":"0eab0721-423f-4110-a56e-81e029fad937","resolution":{"observed_at":"2026-08-01T15:56:40.934325Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.16719","last_updated":"2026-03-28T16:54:56Z","snapshot_observed_at":"2026-08-07T05:59:39.049027Z","submitted_at":"2025-11-20T18:59:56Z","title":"SAM 3: Segment Anything with Concepts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.16719","snapshot_observed_at":"2026-08-01T15:56:41.024239Z","title":"arXiv preprint arXiv:2511.16719 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.024239Z"},"links":{"cited_paper":"/paper/2511.16719","citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:b9cd47215b5261dcee024ad652e908bdb6675e26e8034cd2b0f4516bf76845b1","observation_id":"2e637c64-a5cf-4643-be4e-6a5a810f2936","resolution":{"observed_at":"2026-08-01T15:56:41.024239Z","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":"2026-08-01T15:56:41.034990Z","title":"In: Proceedings of the Computer Vision and Pattern Recognition Conference","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.034990Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:95394dc5008d35e34a06b785d2916c3f734af20ec0848a756038e84cc1f4fbcf","observation_id":"8d130dd6-e2e8-4ec2-9239-37016a61c3d4","resolution":{"observed_at":"2026-08-01T15:56:41.034990Z","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":"2026-08-01T15:56:41.139131Z","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":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.139131Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:3aacf5115af7a1226473cc64bdfb3639bec5e91390ad0ce3bb8d1868fd8b0e4e","observation_id":"2ff2117a-0580-45fe-985a-1de238e89ff3","resolution":{"observed_at":"2026-08-01T15:56:41.139131Z","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":"2026-08-01T15:56:41.255754Z","title":"Expert Systems with Applications271, 126581 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.255754Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:7bede524e5f3dd6a90082155e078e099ccd20b50bd0167ff001531272b511287","observation_id":"38d05eb1-269a-4901-adf6-12eef4dc94bf","resolution":{"observed_at":"2026-08-01T15:56:41.255754Z","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":"2026-08-01T15:56:41.307365Z","title":"In: International conference on pattern recognition","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.307365Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:3bd19654a6071aaa64088631d7f31d56cbbf7718578278f61c09c87d729e4bf3","observation_id":"51b2f00c-fe43-4c03-a955-c9b328fbf16b","resolution":{"observed_at":"2026-08-01T15:56:41.307365Z","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":"2026-08-01T15:56:41.382340Z","title":"In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers)","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.382340Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:f7c0e0870a6f9392fe8468068af929542218fcbe3d35632eb989130eb443aee4","observation_id":"2c72f2c7-3b13-4efa-8897-32a16f83e8c7","resolution":{"observed_at":"2026-08-01T15:56:41.382340Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04769","last_updated":"2025-07-17T15:16:09Z","snapshot_observed_at":"2026-08-05T13:51:02.330984Z","submitted_at":"2024-12-06T04:31:09Z","title":"Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.04769","snapshot_observed_at":"2026-08-01T15:56:41.441789Z","title":"arXiv preprint arXiv:2412.04769 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.441789Z"},"links":{"cited_paper":"/paper/2412.04769","citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:09150c20d4bbdc4e61ae9c8e5ea69990570a1fa7422e6de612b7a5f2ee5a9b35","observation_id":"04989302-31d5-45e9-b08b-b98964c79042","resolution":{"observed_at":"2026-08-01T15:56:41.441789Z","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":"2026-08-01T15:56:41.496309Z","title":"In: Proceedings of the IEEE/CVF International Conference on Computer Vision","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.496309Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:07da27213359ab9fc8b99e7a3df606787e4188d9b7ca16dc17987a7c5f12c92e","observation_id":"c6d85c57-3e9c-498b-b8eb-a425f8747e8d","resolution":{"observed_at":"2026-08-01T15:56:41.496309Z","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":"2026-08-01T15:56:41.553855Z","title":"In: Proceedings of the AAAI conference on artificial intelligence","venue":null,"work_id":null,"year":1932},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.553855Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:4314bdc00d8798f63f29f914bfe40669cd630616e0cb7aed96ff1382c89a83cd","observation_id":"56a40696-9a52-4633-a758-b95d76d61d1b","resolution":{"observed_at":"2026-08-01T15:56:41.553855Z","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":"2026-08-01T15:56:41.625346Z","title":"In: Proceedings of the Computer Vision and Pattern Recognition Conference","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.625346Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:e5c4c6fa17e394af05820d1b6eed47e3fbb7276345842bbfc3f395be65205fca","observation_id":"31e1deae-a342-4ed4-bd17-c669129d9539","resolution":{"observed_at":"2026-08-01T15:56:41.625346Z","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":"2026-08-01T15:56:41.661845Z","title":"Advances in Neural Information Processing Systems37, 71162– 71187 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.661845Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:e06220246aec173f2b6815f146d9f0357f7b9b329cffcb8674981fd634bf2a51","observation_id":"ab0d62e8-a914-4b89-9822-e8583f8a77d3","resolution":{"observed_at":"2026-08-01T15:56:41.661845Z","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":"2026-08-01T15:56:41.720365Z","title":"In: Proceedings of the 30th ACM international con- ference on multimedia","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.720365Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:fdbfc1cf4033f243cbd572639173560651ab529bbfea1b396ef853aaf6d37832","observation_id":"a26ae69e-cf53-4787-ae64-f6cfaea81c9c","resolution":{"observed_at":"2026-08-01T15:56:41.720365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.19877","last_updated":"2025-05-26T12:05:16Z","snapshot_observed_at":"2026-08-07T14:02:26.750386Z","submitted_at":"2025-05-26T12:05:16Z","title":"Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.19877","snapshot_observed_at":"2026-08-01T15:56:41.756320Z","title":"arXiv preprint arXiv:2505.19877 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.756320Z"},"links":{"cited_paper":"/paper/2505.19877","citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:b4cd67d29abd4d24ba41fe60c51f5635497b09b4249e8896f25d8af894b67493","observation_id":"615540cb-879f-45fc-b9cc-2eaa3b41bae6","resolution":{"observed_at":"2026-08-01T15:56:41.756320Z","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":"2026-08-01T15:56:41.807660Z","title":"In: Pro- O-VAD 17 ceedings of the IEEE/CVF winter conference on applications of computer vision","venue":null,"work_id":null,"year":2052},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.807660Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:ee119d1087118dbebcf3baf6094d4dd4b0d21f7c78451b37533c26d3493bb99a","observation_id":"aaca1df4-a573-4217-9b5a-366e8ba17599","resolution":{"observed_at":"2026-08-01T15:56:41.807660Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.09453","last_updated":"2025-02-21T04:50:45Z","snapshot_observed_at":"2026-08-06T23:07:59.630081Z","submitted_at":"2024-10-12T09:16:09Z","title":"MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.09453","snapshot_observed_at":"2026-08-01T15:56:41.874961Z","title":"arXiv preprint arXiv:2410.09453 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.874961Z"},"links":{"cited_paper":"/paper/2410.09453","citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:9c78e03fa3ff571545e02e611f1e420cafd90e57765cf46dd5f131fcb60c190e","observation_id":"65bede4b-d7a3-4a98-8cfb-0c5229e0b49c","resolution":{"observed_at":"2026-08-01T15:56:41.874961Z","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":"2026-08-01T15:56:41.938733Z","title":"Advances in Neural In- formation Processing Systems35, 15433–15445 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.938733Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:378f784351244794ee346cb152d4b0a0e49a616d57d9d3e9f67b260043e50882","observation_id":"da51f965-c5a5-42e3-ae7e-e590c43680ef","resolution":{"observed_at":"2026-08-01T15:56:41.938733Z","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":"2026-08-01T15:56:41.989760Z","title":"In: The Fourteenth International Con- ference on Learning Representations (2026)","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:41.989760Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:7e1bb648fda80844900775a9ab17fdacaa4262c33751eb7e27949fd5d6c23d5f","observation_id":"dab65c64-7345-4539-9bbc-c5972b0af57c","resolution":{"observed_at":"2026-08-01T15:56:41.989760Z","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":"2026-08-01T15:56:42.053113Z","title":"In: Proceedings of the IEEE/CVF international conference on computer vision","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:42.053113Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:d4559d320cedc8f79967aa158d980e0387b00368bd7a2593349cb1ffc62e7ce3","observation_id":"c9357cd8-5f6f-4e8d-a50d-be5373f90c4b","resolution":{"observed_at":"2026-08-01T15:56:42.053113Z","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":"2026-08-01T15:56:42.108555Z","title":"In: European Conference on Computer Vision","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:42.108555Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:d6d600a351bea81256b484929a8cc645c516ec242464ba7025d8148bce86d7a3","observation_id":"1a3b2da2-31a4-4c2a-b309-af0c0b9bf5c5","resolution":{"observed_at":"2026-08-01T15:56:42.108555Z","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":"2026-08-01T15:56:42.167791Z","title":"arXiv preprint arXiv:2506.02535 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:42.167791Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:5607387717f2d30a36389a3610cdcaa247dd0efbf119b53b0e8c0051146a88ee","observation_id":"7c7b713b-f802-4529-9e1c-035fe1ff1830","resolution":{"observed_at":"2026-08-01T15:56:42.167791Z","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":"2026-08-01T15:56:42.251879Z","title":"Advances in Neu- ral Information Processing Systems38, 148372–148404 (2026)","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:42.251879Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:c44206eb0e1d9c5827113de05228a6b6ca1f38296029b4fbea2cb67c4f3f62a7","observation_id":"03c98924-851d-4264-9845-a5fd6c9f39d0","resolution":{"observed_at":"2026-08-01T15:56:42.251879Z","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":"2026-08-01T15:56:42.320944Z","title":"In: Proceedings of the Computer Vision and Pattern Recogni- tion Conference","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:42.320944Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:3e7034f7be76fe9760773f684351b4c1e5a3a805947678b940ca94376c557faf","observation_id":"cc726aaa-f0eb-4528-aeb6-ed5073184860","resolution":{"observed_at":"2026-08-01T15:56:42.320944Z","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":"2026-08-01T15:56:42.500742Z","title":"arXiv preprint arXiv:2511.00962 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:42.500742Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:f2446f7613fbb3bf88775657a3c3901971ad9417db757d7a73480ebac65dcc7e","observation_id":"6cdd9599-ff2b-416b-9112-47e80b79ce73","resolution":{"observed_at":"2026-08-01T15:56:42.500742Z","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":"2026-08-01T15:56:42.625687Z","title":"In: 2025 International Conference on Advanced Robotics and Mechatronics (ICARM)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:42.625687Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:5144f06360a09b076023439cb734e7e495f302b8dc4321deb468d63f548ee122","observation_id":"e3997e51-7f6e-424c-88ae-d3eb6e8dbf9c","resolution":{"observed_at":"2026-08-01T15:56:42.625687Z","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":"2026-08-01T15:56:42.776085Z","title":"IEEE Transactions on Circuits and Systems for Video Technology35(1), 380–393 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:42.776085Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:a59de074d250de579e1213a04ecfe7ee81149d7ed0480386c1fcd1c65ef21894","observation_id":"45bc17c0-fcad-4081-99f6-c4364cf72dab","resolution":{"observed_at":"2026-08-01T15:56:42.776085Z","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":"2026-08-01T15:56:42.918778Z","title":"In: Proceedings of the 27th ACM International Conference on Multimedia","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:42.918778Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:52cf9cee6745b7145974e51613619bcea39eed9a198acbbcf87d088cc9526ce2","observation_id":"f742e7cf-7b54-4b09-abc9-1bfc3ada43ee","resolution":{"observed_at":"2026-08-01T15:56:42.918778Z","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":"2026-08-01T15:56:43.070749Z","title":"In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:43.070749Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:3c87c505ed7318c8d6a53a63c897bbbbd4b5b14f993b6b6cef930367ab9a1dd6","observation_id":"b0cbca19-d172-4a38-82e2-0d8b34b5dc36","resolution":{"observed_at":"2026-08-01T15:56:43.070749Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.05776","last_updated":"2023-04-02T22:01:17Z","snapshot_observed_at":"2026-07-31T08:06:57.921225Z","submitted_at":"2022-11-10T18:58:22Z","title":"High-Quality Entity Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.05776","snapshot_observed_at":"2026-08-01T15:56:43.183792Z","title":"arXiv preprint arXiv:2211.05776 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:43.183792Z"},"links":{"cited_paper":"/paper/2211.05776","citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:8542ad40731593c1e82fd7753c5ef80107aeeff6bea109a63f54717566a2d1b5","observation_id":"bec6a009-1277-433d-9074-85de31c27370","resolution":{"observed_at":"2026-08-01T15:56:43.183792Z","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":"2026-08-01T15:56:43.313059Z","title":"In: International conference on machine learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:43.313059Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:3b1b0adba1e087f6e1cacc92f1de6fa124da886f7ae2bd3e41b77c996397a5cc","observation_id":"5380ae6c-6e36-4ef1-bbb2-12c2a8570143","resolution":{"observed_at":"2026-08-01T15:56:43.313059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00714","last_updated":"2024-10-28T16:37:57Z","snapshot_observed_at":"2026-07-06T18:55:41.459417Z","submitted_at":"2024-08-01T17:00:08Z","title":"SAM 2: Segment Anything in Images and Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.00714","snapshot_observed_at":"2026-08-01T15:56:43.442994Z","title":"arXiv preprint arXiv:2408.00714 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:43.442994Z"},"links":{"cited_paper":"/paper/2408.00714","citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:e4716d8e42c514ae9233537e221d92e2b434b1772c091eb4a1d09b5a93d70dba","observation_id":"e2587daa-012b-4300-9e1c-c8052741a00e","resolution":{"observed_at":"2026-08-01T15:56:43.442994Z","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":"2026-08-01T15:56:43.571800Z","title":"In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:43.571800Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:db70259c948311908ea9f4330c05c1d9c123aa63ba9e4549c463d23a2efd9ccf","observation_id":"e5587c46-095f-48b0-8915-7931c162b4cc","resolution":{"observed_at":"2026-08-01T15:56:43.571800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.03267","last_updated":"2026-05-01T23:55:43Z","snapshot_observed_at":"2026-08-02T10:52:10.211700Z","submitted_at":"2025-12-19T07:05:38Z","title":"OpenAI GPT-5 System Card","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.03267","snapshot_observed_at":"2026-08-01T15:56:43.755806Z","title":"arXiv preprint arXiv:2601.03267 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:43.755806Z"},"links":{"cited_paper":"/paper/2601.03267","citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:f09d74c121f6ee66a34a743990225be2a1f221a5cc6fd2775cac4d56d2a21681","observation_id":"bd5c9652-18f9-4b15-ab2a-2135b083e28e","resolution":{"observed_at":"2026-08-01T15:56:43.755806Z","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":"2026-08-01T15:56:43.870784Z","title":"In: 2023 IEEE International Conference on Multimedia and Expo (ICME)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:43.870784Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:8751598c8d2379c9125e835610fbd1a96b083136209443dc2183161e09d35523","observation_id":"ad3e3ef7-e9c8-4318-8855-5a5c7c99d540","resolution":{"observed_at":"2026-08-01T15:56:43.870784Z","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":"2026-08-01T15:56:43.978593Z","title":"arXiv preprint arXiv:2511.04678 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:43.978593Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:bb96639d7627458dc79397eafbe2e5421d3e90d37e83d9b2bab5c54f0dfca6a1","observation_id":"c5c6131f-d845-46a9-908a-c162338f4222","resolution":{"observed_at":"2026-08-01T15:56:43.978593Z","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":"2026-08-01T15:56:44.070458Z","title":"In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.070458Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:51d7aee6b2e0ece16e15c76369bcf10b65c50366b66bd7a3942bb6f11d2847a1","observation_id":"075d4961-8256-402f-bee1-6e675954805c","resolution":{"observed_at":"2026-08-01T15:56:44.070458Z","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":"2026-08-01T15:56:44.126926Z","title":"In: European Conference on Computer Vision","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.126926Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:2b6b03534a80c7ac013923850157a51f158b1cb80547b7638c6bad98bfd18e08","observation_id":"60300efa-4d05-458e-9a06-e672613b9359","resolution":{"observed_at":"2026-08-01T15:56:44.126926Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.03825","last_updated":"2021-08-09T06:11:14Z","snapshot_observed_at":"2026-08-07T11:27:42.495037Z","submitted_at":"2021-08-09T06:11:14Z","title":"Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.03825","snapshot_observed_at":"2026-08-01T15:56:44.208994Z","title":"arXiv preprint arXiv:2108.03825 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.208994Z"},"links":{"cited_paper":"/paper/2108.03825","citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:784687ed6529cc06b52679c7e9e7b9fe4a2be9eefe78471f2cdbd681a95d0f81","observation_id":"73907005-9c15-4073-b494-e637c84dd70e","resolution":{"observed_at":"2026-08-01T15:56:44.208994Z","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":"2026-08-01T15:56:44.300053Z","title":"In: Proceedings of the 32nd ACM International Conference on Multimedia","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.300053Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:9fe97036cab0d9305a50193b3eb1c0a15c33302f4c5d01abaeb070a04ac0c431","observation_id":"d4550672-5134-4efb-b8db-862e98ad4907","resolution":{"observed_at":"2026-08-01T15:56:44.300053Z","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":"2026-08-01T15:56:44.360403Z","title":"In: Proceedings of the Computer Vision and Pattern Recognition Conference","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.360403Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:3ddd47007b86f22b1cbaf7e081a5cc4d18fe3360dc8dcb94768e02a60032a776","observation_id":"b0069403-b19c-4208-b144-daf135324590","resolution":{"observed_at":"2026-08-01T15:56:44.360403Z","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":"2026-08-01T15:56:44.412648Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.412648Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:45fbf3c983cf160edf613b8f303053c63376c151e5bfac8c43a3c5282d6ed494","observation_id":"3c4430a1-9753-4c1e-962e-bdb710cc8fda","resolution":{"observed_at":"2026-08-01T15:56:44.412648Z","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":"2026-08-01T15:56:44.460066Z","title":"In: Proceedings of the IEEE/CVF international conference on computer vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.460066Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:e8c1bd1c69f533d6ab3ab3e7c9584c952417a00edc00fb0870827d42f76bff1c","observation_id":"f1067331-7b57-4c1b-a96d-d485c8e6f623","resolution":{"observed_at":"2026-08-01T15:56:44.460066Z","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":"2026-08-01T15:56:44.529612Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.529612Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:9543ade1807757f2e55088dce1ff1e5d8febd15776015633fe77ae0e61941317","observation_id":"22ed0fd1-9eda-4ad2-bbff-7ffcd4198b4a","resolution":{"observed_at":"2026-08-01T15:56:44.529612Z","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":"2026-08-01T15:56:44.595532Z","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":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.595532Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:02341167f193f0afd0bc84bd1e62e3a1727bcd5e807fc28378d716fa7a8edbcd","observation_id":"a9d14b84-36b2-4986-9471-7690db7ca0bc","resolution":{"observed_at":"2026-08-01T15:56:44.595532Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22039","last_updated":"2026-07-29T09:31:57Z","snapshot_observed_at":"2026-08-07T21:55:46.500544Z","submitted_at":"2025-05-28T07:02:15Z","title":"OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.22039","snapshot_observed_at":"2026-08-01T15:56:44.645657Z","title":"arXiv preprint arXiv:2505.22039 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.645657Z"},"links":{"cited_paper":"/paper/2505.22039","citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:c8fb470273983d01c2765204c8dc670465b6e52297cc56a1421ff86511b5b2ee","observation_id":"db536c50-f8a5-4cc9-bb04-df4b5617fcb5","resolution":{"observed_at":"2026-08-01T15:56:44.645657Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.12440","last_updated":"2026-04-14T08:29:31Z","snapshot_observed_at":"2026-08-08T02:03:51.549597Z","submitted_at":"2026-04-14T08:29:31Z","title":"IAD-Unify: A Region-Grounded Unified Model for Industrial Anomaly Segmentation, Understanding, and Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.12440","snapshot_observed_at":"2026-08-01T15:56:44.700501Z","title":"arXiv preprint arXiv:2604.12440 (2026)","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.700501Z"},"links":{"cited_paper":"/paper/2604.12440","citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:72b1b1db15725415935996d63859bd4bab7c42a269dc74c5ea24056f7685f7bd","observation_id":"d9b3a7af-22ac-4b7b-86b0-3caf5a298089","resolution":{"observed_at":"2026-08-01T15:56:44.700501Z","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":"2026-08-01T15:56:44.752136Z","title":"Advances in neural information processing systems36, 46595–46623 (2023) O-VAD 19","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.752136Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:9f607339ae944bfb6b8a8e3f7dfd9f20580ba2b97ee7029a663148b1124ee110","observation_id":"c5808f27-be6f-4bdd-8906-f69d2cae004b","resolution":{"observed_at":"2026-08-01T15:56:44.752136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.23504","last_updated":"2025-05-29T14:48:10Z","snapshot_observed_at":"2026-08-09T01:12:29.594269Z","submitted_at":"2025-05-29T14:48:10Z","title":"VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.23504","snapshot_observed_at":"2026-08-01T15:56:44.829023Z","title":"arXiv preprint arXiv:2505.23504 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.829023Z"},"links":{"cited_paper":"/paper/2505.23504","citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:0992f1ad6a4278d20946dcc9c99ca6febf638f6d6d9f8e506d5b8ab018e52a17","observation_id":"e38028c4-39f9-41e9-a8c5-8f3ad0eb4dfa","resolution":{"observed_at":"2026-08-01T15:56:44.829023Z","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":"2026-08-01T15:56:44.876785Z","title":"In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.876785Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:855be26cbbe15c68799adef17013700a3640d47ed1ea75da3405735a7be6241e","observation_id":"d9188239-87b2-4089-9323-63d96b872ae3","resolution":{"observed_at":"2026-08-01T15:56:44.876785Z","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":"2026-08-01T15:56:44.952392Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:44.952392Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:baa5179857271fed297c843ed88252743f99b3d5a10333e5e57e81351f49d3ec","observation_id":"38b33f7d-f81f-4774-a5b9-a05f306fe492","resolution":{"observed_at":"2026-08-01T15:56:44.952392Z","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":"2026-08-01T15:56:45.005335Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:45.005335Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:1facb317035d0c9116d3a17c00f0fab6fa8f66920ab422a2940a0f345d7ff028","observation_id":"cad663dc-6b87-44d3-9c06-3c0e158b50f7","resolution":{"observed_at":"2026-08-01T15:56:45.005335Z","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":"2026-08-01T15:56:45.058017Z","title":"screw” and “screw thread","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:45.058017Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:5bd835bfe3dc17d4a8901126d8849ded775a8b807c69e095213faf503e157288","observation_id":"924e3b55-fcd4-4f53-bd13-9c12daa84856","resolution":{"observed_at":"2026-08-01T15:56:45.058017Z","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":"2026-08-01T15:56:45.131631Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:45.131631Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:06d8348ad08bc83a66d39f7c5b47484d11a5f0ca2c22b9708adafb124b7047c3","observation_id":"90ccb93e-5747-4d80-9593-655aaf116b77","resolution":{"observed_at":"2026-08-01T15:56:45.131631Z","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":"2026-08-01T15:56:45.216366Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:45.216366Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:a4069281f267d48298659efce28225129ec60a37a1019e8f9ed63f2a1da10952","observation_id":"69a0ece4-ad4b-47cf-886a-7e0baccf232c","resolution":{"observed_at":"2026-08-01T15:56:45.216366Z","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":"2026-08-01T15:56:45.318431Z","title":"\"role\":","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-01T15:56:45.318431Z"},"links":{"citing_paper":"/paper/2607.18142"},"observation_digest":"sha256:9aee94ffd16dbeab6e9fe972dd3cdba7011ee62ef1abe9a8442b63f0453deaf8","observation_id":"9e968a37-e5b5-496f-98c7-cb9609f20343","resolution":{"observed_at":"2026-08-01T15:56:45.318431Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.18142","last_updated":"2026-07-20T16:36:00Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T21:56:26.957775Z","submitted_at":"2026-07-20T16:36:00Z","title":"O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning"},"reference_resolution":{"displayed":55,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":54,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":55},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2607.18142."}