{"as_of":"2026-08-16T19:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dedaa1d4b44fa079fd483c11c99cac09db5e20c7ac41960bf59ebc30ad8c6f47","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T17:06:12.832949Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2508.17726/citation-record","integrity":"/paper/2508.17726/integrity","json":"/paper/2508.17726/citation-record.json","paper":"/paper/2508.17726"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.364399Z","title":"Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings","venue":null,"work_id":"449bea5e-4736-4223-af99-930c1428a66b","year":2020},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.651031Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:0ba6e963be317cf426c563868a1265f787ecdb05c9de3227fcdaaf145e59c85b","observation_id":"93d4d899-86f1-4dff-a4ae-37fc6ef2bc00","resolution":{"observed_at":"2026-08-15T17:06:13.368144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.353842Z","title":"Mvtec ad – a comprehensive real-world dataset for unsupervised anomaly detection","venue":null,"work_id":"29f7d3b8-59ac-4c3c-87d2-fbd0e05f63bc","year":2019},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.656001Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:0076a09756f46d79947cb6518df3223540ed62851eb2d7e037b5c7dd43476a74","observation_id":"1eadf4ab-6233-4fd3-9629-0f256aa2b073","resolution":{"observed_at":"2026-08-15T17:06:13.357775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:12.659794Z","title":"Padim: a patch distribution modeling framework for anomaly detection and localization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.659794Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:ca3cef8f10c5ebc15053bc14a9e80a2360a918db389fccdeec892c0b5fbc733b","observation_id":"fbedaee0-7a0d-414d-b6e9-9b9e248afa85","resolution":{"observed_at":"2026-08-15T17:06:12.659794Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.337720Z","title":"Anomaly detection for industrial surface inspection: applica- tion in maintenance of aircraft components","venue":null,"work_id":"616f8a85-18be-48e2-a9a1-ab2303589e81","year":2022},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.663586Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:cdadfb6c652385081f15d7f1fbbce0775b0f29e392cee8219914d34e1f407de7","observation_id":"00d88b4b-0654-44ae-bd61-bc18df57a5ca","resolution":{"observed_at":"2026-08-15T17:06:13.341376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:12.667128Z","title":"Supervised anomaly detection for complex indus- trial images","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.667128Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:c6f6f86f75211460cb96e04f3481f8eb658e7189638227532d4839c34fb70c4f","observation_id":"1ce0d92a-4ad2-4636-b1b8-7bd42e4ed3ae","resolution":{"observed_at":"2026-08-15T17:06:12.667128Z","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":"2026-08-15T17:06:12.670677Z","title":"f-anogan: Fast unsupervised anomaly detection with generative adversarial networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.670677Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:27856725791ff8ad72fc7b47ebdb40c118bba16c27b78588544bbcd2590ae7ef","observation_id":"75aba50e-63d1-46fe-86d1-02a96ff3fb0b","resolution":{"observed_at":"2026-08-15T17:06:12.670677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.315127Z","title":"Madgan: Unsupervised medical anomaly detection gan us- ing multiple adjacent brain mri slice reconstruction","venue":null,"work_id":"08f6c919-de01-4e87-a8cf-c319d726a8ce","year":2021},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.674514Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:2e339f678f0e0f5d43e1d76040e10f670a7ffb95e56b56792a53a878efb8af83","observation_id":"1ca7543b-fdd0-456d-b05d-4c60f23b399b","resolution":{"observed_at":"2026-08-15T17:06:13.318867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.304344Z","title":"Unsupervised deep anomaly detection for medical images using an improved adversarial autoen- coder","venue":null,"work_id":"6944fbec-146a-44a2-8b51-f4229d69af6b","year":2022},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.677707Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:c77955c9ac01fc5538fb05ca79301b1c7587e28b7f9088c2109b5f5284f8eb4f","observation_id":"62b6f9ad-e1db-4faf-9f30-92f978aea08f","resolution":{"observed_at":"2026-08-15T17:06:13.307901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.294490Z","title":"Unsu- pervised anomaly detection for posteroanterior chest x-rays using multiresolution patch-based self-supervised learning","venue":null,"work_id":"1a907967-f7be-40d0-849d-1ed54c84610b","year":2023},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.681017Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:1ebcfcba0c117aade8a5302f07bc45d379d48bb47b0c4d4147bb4c50bd84dc8f","observation_id":"980e6f5e-b2d2-4c19-8af9-f7fa27f74038","resolution":{"observed_at":"2026-08-15T17:06:13.298225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.17457","last_updated":"2025-06-20T19:58:38Z","snapshot_observed_at":"2026-08-15T19:06:14.838328Z","submitted_at":"2025-06-20T19:58:38Z","title":"When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network","version":1},"cited_work":{"arxiv_id":"2506.17457","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.17457","snapshot_observed_at":"2026-08-15T17:06:12.918342Z","title":"When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network","venue":"cs.CV","work_id":"ee3a5076-e2ef-4b5a-aaab-802b27141966","year":2025},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.683957Z"},"links":{"cited_paper":"/paper/2506.17457","citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:b4274a709db2c02bf235b35ea26cac4fc40c4bf63cce65228be49ec182d1f76a","observation_id":"2d98808f-e61b-447f-aca4-3e11789f113e","resolution":{"observed_at":"2026-08-15T17:06:12.922774Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.284699Z","title":"Scaling out-of- distribution detection for real-world settings","venue":null,"work_id":"72fa0e57-7202-44a8-9844-359481356458","year":2022},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.687621Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:4ba9b67ae44e0449d0114e7c678dd5e30ee9d5090a8197c24edada052d76ab61","observation_id":"b865dfb3-7e62-4ff5-8204-0e1a45444718","resolution":{"observed_at":"2026-08-15T17:06:13.288185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.274351Z","title":"Spotting the unexpected (stu): A 3d lidar dataset for anomaly segmenta- tion in autonomous driving","venue":null,"work_id":"9b3d2e43-d9c2-464b-97fa-59e6564de98e","year":2025},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.691493Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:58f05364b8f92b60133d8daa7b17aa81521406386635447905f40815842e4990","observation_id":"2287c2c7-2932-4c91-99b2-59cb26b9840f","resolution":{"observed_at":"2026-08-15T17:06:13.278119Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.17381","last_updated":"2024-04-26T12:56:16Z","snapshot_observed_at":"2026-08-16T13:57:33.650758Z","submitted_at":"2024-04-26T12:56:16Z","title":"Frequency-Guided Multi-Level Human Action Anomaly Detection with Normalizing Flows","version":1},"cited_work":{"arxiv_id":"2404.17381","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.17381","snapshot_observed_at":"2026-08-15T17:06:12.901662Z","title":"Frequency-Guided Multi-Level Human Action Anomaly Detection with Normalizing Flows","venue":"cs.CV","work_id":"976d3d70-6d68-48d0-901a-55da1c4a0145","year":2024},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.694997Z"},"links":{"cited_paper":"/paper/2404.17381","citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:db0f9d4f54ad756b73e9c1644756f13bc7e21e65bc99c4819decdb732ad1a324","observation_id":"d032ece4-9cc4-46e7-80ca-0bf16ab103bd","resolution":{"observed_at":"2026-08-15T17:06:12.907432Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.264007Z","title":"Multimodal motion con- ditioned diffusion model for skeleton-based video anomaly detection","venue":null,"work_id":"dce4fa70-b975-4922-836a-5480521bc8f8","year":2023},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.698670Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:3fc4a634333df0daaeccc01670aa43584f29588402c62b4f48ad6742672db46c","observation_id":"ec49c918-1366-4ec6-84e5-9d570a0329c7","resolution":{"observed_at":"2026-08-15T17:06:13.267665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.252540Z","title":"Normalizing flows for human pose anomaly detection","venue":null,"work_id":"9b7d786f-0b24-4a7b-bdd1-bc33b67b9c93","year":2023},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.702292Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:7bdab449d672fd6804804288f5796ad438dc2989e771f2813e6fc53f7610cbd3","observation_id":"26daaf13-8948-472f-a0bd-dc184e1127cf","resolution":{"observed_at":"2026-08-15T17:06:13.256446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.242067Z","title":"A unified model for multi-class anomaly detection","venue":null,"work_id":"c5829c0a-823a-48f2-8ebf-55f9387ce348","year":2022},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.705808Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:d0656a5e9d6c1031f316bce2725018260626826cc17cf4e03b31f0de44c9f309","observation_id":"37705a6b-2d9c-4de5-8589-ac72df3b2cf8","resolution":{"observed_at":"2026-08-15T17:06:13.245454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.231813Z","title":"Registration based few-shot anomaly detection","venue":null,"work_id":"7f873085-08a8-4c67-bea6-fcde41e0b3f9","year":2022},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.709277Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:ec60db141a9bda9ab4ec074fb80ba47750d5387c4c681adb6c2e71e42a97a5b6","observation_id":"215f719a-6559-4333-b00d-b2b02762ff0a","resolution":{"observed_at":"2026-08-15T17:06:13.235418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.221272Z","title":"Omnial: A unified cnn framework for unsuper- vised anomaly localization","venue":null,"work_id":"f51acf0e-ee35-4320-a777-1677412cb95a","year":2023},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.712817Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:27939e5202db3aa9dbc4d344fc27b37204304df2dc218174b8994e4a243833bb","observation_id":"d7b21d97-dbe6-4d61-b25e-a8c8d9aa6f11","resolution":{"observed_at":"2026-08-15T17:06:13.224879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.210209Z","title":"Hierarchical vector quantized transformer for multi-class unsupervised anomaly detection, 2023","venue":null,"work_id":"2440cf8a-e21b-4c2a-a9aa-23b5e54ca9f7","year":2023},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.716151Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:b2b94ae9d1719076d2873e949748df567c15acfd06fdb175de3a053da1fb3edf","observation_id":"de5f2a68-0976-4e14-a98d-e53ab7474f62","resolution":{"observed_at":"2026-08-15T17:06:13.214329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.198922Z","title":"Karls- son, Biqing Huang, and Chin Yew Lin","venue":null,"work_id":"0b2aa315-80fb-4d64-94e3-50864edb7e58","year":2023},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.719815Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:65a819155b10e9c479b8cd3116deacc6289140e4cdafe005e9b60b10a5c51fcc","observation_id":"3a889f3b-1d4a-4a47-863e-fc9a9a5a686f","resolution":{"observed_at":"2026-08-15T17:06:13.202729Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.187846Z","title":"Mambaad: Exploring state space models for multi-class unsupervised anomaly detec- tion","venue":null,"work_id":"5aff2ce7-c1c3-444b-9e09-70e3d56c0c22","year":2024},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.723481Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:7c8f318e6b7ef8113870e24570a15816b1c95b6c154009a6743b827d4fb6a44a","observation_id":"dbb23674-5423-4541-9774-0e9dd780082f","resolution":{"observed_at":"2026-08-15T17:06:13.191536Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.176815Z","title":"Learning to detect multi-class anomalies with just one normal image prompt","venue":null,"work_id":"5a5ff3b9-82fe-4b96-9907-6814eceaa6a3","year":2024},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.726789Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:9e22d5addf70690634e35014c42b09a0f302e2c3e78ac1df148dcf6d31dd3cb8","observation_id":"727bbf43-56bc-4041-a136-e47c87effa11","resolution":{"observed_at":"2026-08-15T17:06:13.180927Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.164876Z","title":"Dinomaly: The less is more philosophy in multi-class unsupervised anomaly detection","venue":null,"work_id":"219ba17f-fde6-4150-af06-963c11e04f92","year":2025},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.730300Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:376a07a119a1f6c7eec8a94eb47dcece8c1d0bf56a1ad671a8f4cf5f2b4d822e","observation_id":"5ebad5e7-015c-493f-8b2b-6dfbdded243f","resolution":{"observed_at":"2026-08-15T17:06:13.169020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.153900Z","title":"Correcting deviations from normality: A reformulated diffusion model for multi-class unsupervised anomaly detection","venue":null,"work_id":"c03385c4-fe64-4e94-a664-f79e235adc08","year":2025},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.733675Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:806e7332f0eed3471a2de2c360bc5c213f8c45731f5b8ce96a39e8fe5a679dd1","observation_id":"f5578d6d-11bd-47cb-82db-c1661a6a62d6","resolution":{"observed_at":"2026-08-15T17:06:13.157992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:12.736996Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.736996Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:b5f5a25132c4d35dc45d0ac74d2a56f50174fcdfcddfed8ae4701a2b2dfea8a3","observation_id":"52c6bcc2-9f2b-4c10-b1aa-7525b009af14","resolution":{"observed_at":"2026-08-15T17:06:12.736996Z","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":"2026-08-15T17:06:12.740063Z","title":"Exploring simple siamese rep- resentation learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.740063Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:143ddbd04b256c120a84c7e02cb961bec97d75d83dc656425af6ad6a0806e934","observation_id":"0b422442-399f-40a1-bff3-20c88471d003","resolution":{"observed_at":"2026-08-15T17:06:12.740063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.131100Z","title":"Boosting contrastive self- supervised learning with false negative cancellation","venue":null,"work_id":"424d1a97-0ced-4641-89fd-31a1ffe67f47","year":2022},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.743871Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:205898aa9364f651d0e9df542db9e7657165dccd3471023bc6362741111a4178","observation_id":"ae9801cf-175e-4e4e-b16d-d7c1528754cd","resolution":{"observed_at":"2026-08-15T17:06:13.134582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.120480Z","title":"Humanmac: Masked motion completion for human motion prediction","venue":null,"work_id":"19318b67-ae14-4e9d-8307-a4b3d141c29d","year":2023},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.747730Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:2f4050b03b34b4cf8d5fe5981996fc106e14b75d89681014978e66e6a18676af","observation_id":"0f31cf31-57c6-46cf-bc1a-ed5d3d49fb7c","resolution":{"observed_at":"2026-08-15T17:06:13.124327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.110323Z","title":"Ac- tion2motion: Conditioned generation of 3d human motions","venue":null,"work_id":"d6605865-640b-456d-8d8f-7e8732c0d9b4","year":2021},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.751172Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:d998ac4e8a882819598dedb0a56e4c2418122b364427d10f9a62a0147394339e","observation_id":"7ad1b4b0-5459-4d0a-af71-ee6ba6147d8f","resolution":{"observed_at":"2026-08-15T17:06:13.113880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:12.754653Z","title":"Anomaly detection and localization in crowded scenes.IEEE transactions on pattern analysis and machine intelligence , 36(1):18–32, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.754653Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:b6a8d9db40ce59021c0c18210c9d6daa0a4c109f611d47de594ae6560234269b","observation_id":"eff2e890-7b7e-4ce2-99ad-9f78486359d6","resolution":{"observed_at":"2026-08-15T17:06:12.754653Z","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":"2026-08-15T17:06:12.757913Z","title":"Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenes","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.757913Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:d0dfea7d5a19e735728b51133e7af301c47f91d97c492522926eb331a6f432ef","observation_id":"a39efe11-acbe-433e-8800-23882e4eed7f","resolution":{"observed_at":"2026-08-15T17:06:12.757913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.087144Z","title":"Video anomaly detection and localization by local motion based joint video representation and ocelm","venue":null,"work_id":"38c4fb5e-0851-4bcf-809f-ec46e5de9ced","year":2018},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.761611Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:1171efaff6ce1ab6d84df7f1b3b7b23f940c1fae71046a8d0661890aff8f0355","observation_id":"11abdcce-59dc-43ca-942e-88c5bce23ca3","resolution":{"observed_at":"2026-08-15T17:06:13.091311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.076595Z","title":"Learning regular- ity in skeleton trajectories for anomaly detection in videos","venue":null,"work_id":"cf2f1f5d-a149-40fc-9346-be7beaa23e48","year":2019},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.764747Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:bd9287f1994322cfc8f69c392f65f36e02aba1a41556701ea21686baadf4117f","observation_id":"c50dea84-b8cc-45c4-a349-1bc306ef03e1","resolution":{"observed_at":"2026-08-15T17:06:13.080648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.065663Z","title":"A survey of single-scene video anomaly detection","venue":null,"work_id":"041a7902-ef29-4d11-8b33-0b78d552e764","year":2020},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.768363Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:4875b04c273b5273b45c768424c7e50c99f5d88cacfdb07a4bdc74a5484a6657","observation_id":"3dfd7c3c-9eaa-435a-8b4d-0b5538cfb21f","resolution":{"observed_at":"2026-08-15T17:06:13.069302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.053015Z","title":"Anomaly detection in video via self- supervised and multi-task learning","venue":null,"work_id":"51bcc6e9-8693-4b69-94df-16373d8b6785","year":2021},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.771779Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:9a4c12ff03a7eedf9b297e7017ca0655b1a962d626344c3373ea61f97e1034c6","observation_id":"3db237f3-94d8-4b10-b575-44879c2737ae","resolution":{"observed_at":"2026-08-15T17:06:13.057968Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:12.775755Z","title":"A background-agnostic framework with adversarial training for abnormal event detection in video","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.775755Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:7b16a24f91caee86f0b05484918d0659b2ab4131ef32aee745ff92cbce3eb671","observation_id":"e5dea515-3eba-4f77-bcfe-f4d2569a3146","resolution":{"observed_at":"2026-08-15T17:06:12.775755Z","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":"2026-08-15T17:06:12.779562Z","title":"Hierarchical recur- rent neural network for skeleton based action recognition","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.779562Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:4b324cb9cd5680fe83624974d66d910bc6291fa33934721e34be6477b9953143","observation_id":"03948e12-fca5-40ea-9d64-1c842ecad803","resolution":{"observed_at":"2026-08-15T17:06:12.779562Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.028902Z","title":"Spatial tempo- ral graph convolutional networks for skeleton-based action recognition","venue":null,"work_id":"96228435-e5f2-48fd-9e57-6a1cb6a30ca6","year":2018},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.783219Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:5e5f5e2abb936c60c6e994f7e1aedca703a107dbd1175413a9611157c2e3eaa7","observation_id":"dbc6b70d-45bb-40ef-be27-6f0ea68db312","resolution":{"observed_at":"2026-08-15T17:06:13.032737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.017206Z","title":"Skeleton-based action recognition with directed graph neu- ral networks","venue":null,"work_id":"a4347475-a852-4a77-b8e2-380f7f742fbd","year":2019},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.786899Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:614c70ec3a3c8cc3f58cf1a378b1d9dbd492867e502a2121d191be5d825f9a16","observation_id":"528d6e6c-3eb2-4171-933d-b77dd8bd6cab","resolution":{"observed_at":"2026-08-15T17:06:13.021616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:13.005807Z","title":"Revisiting skeleton-based action recognition","venue":null,"work_id":"44f4edeb-5012-4349-9c2c-8a59637078a2","year":2022},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.790453Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:4352134a33f4e11a189a512fee8255c51d6a4f933ef183760127514bfa67146f","observation_id":"08c4b890-d46e-4066-88bd-eb9ecf0f74d3","resolution":{"observed_at":"2026-08-15T17:06:13.009454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:12.793909Z","title":"A survey on 3d skeleton-based action recognition using learn- ing method","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.793909Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:9795c7a6b2bd1a4a5ef67a5deb3e7c42fda4a536881187cf703d7fe1580f856f","observation_id":"fe2a57fe-df46-477a-ac20-ad5836900cba","resolution":{"observed_at":"2026-08-15T17:06:12.793909Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.01760","last_updated":"2021-03-18T10:35:33Z","snapshot_observed_at":"2026-08-06T00:05:32.412150Z","submitted_at":"2020-07-03T15:29:06Z","title":"Explainable Deep One-Class Classification","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.01760","snapshot_observed_at":"2026-08-15T17:06:12.797375Z","title":"Explainable deep one-class classification","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.797375Z"},"links":{"cited_paper":"/paper/2007.01760","citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:c914fa7985c7e87096d85208171337fd435d4b741839851948c3bf9500792158","observation_id":"78b0232f-4531-46ed-a533-e2cc1bec8ab5","resolution":{"observed_at":"2026-08-15T17:06:12.797375Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:12.986818Z","title":"Adtr: Anomaly detection transformer with feature reconstruction","venue":null,"work_id":"85c37eb0-4075-443e-9495-fec9026e27cf","year":null},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.800975Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:f1ffa7ea09ded27ed2b831cd77fa0f4f0369fb0d3cd6080b6aa502f565ee68e5","observation_id":"d17f75a0-7036-4f69-aff1-7257e384abde","resolution":{"observed_at":"2026-08-15T17:06:12.991197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:12.974739Z","title":"Draem- a discriminatively trained reconstruction embedding for sur- face anomaly detection","venue":null,"work_id":"50a0f6f7-d6e0-4c2a-b864-966027cb6fbf","year":2021},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.804552Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:520862fe0e19c54943e57d8613dd18f0fcd3246079dae270a6bac902ed2418bc","observation_id":"b2f4a2f0-9b75-4dd9-9252-e5647a7eaaf6","resolution":{"observed_at":"2026-08-15T17:06:12.978946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:12.963717Z","title":"Learning trajectory dependencies for human motion pre- diction","venue":null,"work_id":"a4eda443-2af5-4072-80f1-071aecd6318d","year":2019},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.807906Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:0573f8b545209e69b5eee69fa3ca4f147f5b3cb00d41f6cb9db6a5dac29a0475","observation_id":"cfe126d9-86ca-4b56-8c55-d2fe7ff05afb","resolution":{"observed_at":"2026-08-15T17:06:12.967583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:12.952550Z","title":"Nonrigid structure from motion in trajectory space","venue":null,"work_id":"7f703b21-fda9-4c26-8fcd-aaa1314104fc","year":2008},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.811390Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:18826bc21c5ac28e19f99d7c6543badc0748b04b8f920008d227f6c77d42874a","observation_id":"14929d61-6270-4a44-b02a-9e888c9d3e38","resolution":{"observed_at":"2026-08-15T17:06:12.956740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-13T11:38:10.906031Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-15T17:06:12.814875Z","title":"Semi-supervised classi- fication with graph convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.814875Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:628c97335052bee516b5b644ba8b7be7d7d5fb9213961f0720c951a9a9ff70d4","observation_id":"b79c114c-3f13-4f58-8bcf-7b980a822623","resolution":{"observed_at":"2026-08-15T17:06:12.814875Z","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":"2026-08-15T17:06:12.818803Z","title":"Denoising dif- fusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.818803Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:72b06d9d5ff392ae1ee2027db3e803b0cba2c3baf9407dec7816251eb5d3688e","observation_id":"b9418301-73ba-47cc-aadb-dedc5378ac6f","resolution":{"observed_at":"2026-08-15T17:06:12.818803Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-14T18:51:16.666127Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-15T17:06:12.822129Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.822129Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:cf6200ebe5e5b956f5f987c315d20d4edadf46ea9826560e4b31f0d6584b578f","observation_id":"8b7eaaab-4f10-4166-ac1e-0e738ce79adf","resolution":{"observed_at":"2026-08-15T17:06:12.822129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-08-11T15:38:14.931716Z","submitted_at":"2020-10-06T06:15:51Z","title":"Denoising Diffusion Implicit Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02502","snapshot_observed_at":"2026-08-15T17:06:12.825880Z","title":"Denoising diffusion implicit models","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.825880Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:e374188ba3d2172c7db918c6f766af460ab6e99546721b7344528d8b52efee9b","observation_id":"d614ccd2-7c5e-4630-a86d-863297a32569","resolution":{"observed_at":"2026-08-15T17:06:12.825880Z","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":"2026-08-15T17:06:12.829373Z","title":"Improved denoising diffusion probabilistic models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.829373Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:8543e3b759b9d2f481123d8689d7bb862168514978714530166f90c45233157f","observation_id":"dca373a7-83cf-428f-b636-a5868075483c","resolution":{"observed_at":"2026-08-15T17:06:12.829373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:06:12.929888Z","title":"Visualiz- ing data using t-sne","venue":null,"work_id":"4d5470ca-4d29-4acd-849a-fc9f036b172c","year":2008},"citing_paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T17:06:12.832949Z"},"links":{"citing_paper":"/paper/2508.17726"},"observation_digest":"sha256:69fb1a90c4967212ae325db1b277208bc9d531a4d69bb990784e059f37e6f272","observation_id":"fc6f2fe0-b71c-4dc5-b0c6-179eae6a0bda","resolution":{"observed_at":"2026-08-15T17:06:12.933211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.17726","last_updated":"2025-08-25T07:07:35Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T16:58:39.481276Z","submitted_at":"2025-08-25T07:07:35Z","title":"Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":2,"verified_fuzzy":34},"total_outbound_references":52},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2508.17726."}