{"as_of":"2026-08-11T08:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3b61439b4e1b7aab804e445018d2b2b4d55245f2a3b7051eef5442e45fae2661","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T19:03:32.569204Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2508.13565/citation-record","integrity":"/paper/2508.13565/integrity","json":"/paper/2508.13565/citation-record.json","paper":"/paper/2508.13565"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T19:03:41.222982Z","title":"Medical image analysis using convolu- tional neural networks: a review.Journal of medical systems, 42:1–13, 2018","venue":null,"work_id":"39ba3118-87ba-4f57-9c28-91d9194ed79e","year":2018},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:26.692302Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:a828d32a22819680ab92f1a0c86cc19aa5679f8af65ad6e02d7ef849e9e3f04a","observation_id":"e0f8bb7d-554d-430b-a0c6-50d4b3f89459","resolution":{"observed_at":"2026-08-05T19:03:41.314767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:41.017751Z","title":"Fewsome: One-class few shot anomaly detection with siamese networks","venue":null,"work_id":"f3ee8d67-25c5-4844-b943-0efb7993eaac","year":2023},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:26.829513Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:c61844a7d1861c756aad7f2c04e80e4177a860e1d0f06274aff1a703f7cfffc6","observation_id":"031ae5cd-7576-43a8-b1ac-fae96d9f6f93","resolution":{"observed_at":"2026-08-05T19:03:41.123661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:40.805690Z","title":"Mvtec ad–a comprehensive real-world dataset for unsupervised anomaly detection","venue":null,"work_id":"8701d3b2-ac90-4ee5-a2de-1f15ca8c0a4f","year":2019},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:26.970408Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:98ea2366235208b38c9857cb7cbd92799ef29dc0035bbc8204c25e8c6c4a84f1","observation_id":"ede0c70d-b8ba-4e84-8b2f-431cd777f845","resolution":{"observed_at":"2026-08-05T19:03:40.922487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.09045","last_updated":"2021-12-16T17:35:51Z","snapshot_observed_at":"2026-08-03T15:42:25.895204Z","submitted_at":"2021-12-16T17:35:51Z","title":"The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.09045","snapshot_observed_at":"2026-08-05T19:03:27.099316Z","title":"The mvtec 3d-ad dataset for unsupervised 3d anomaly detection and localization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:27.099316Z"},"links":{"cited_paper":"/paper/2112.09045","citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:6348776c5075aa58937102a7f7352698c16b49fc7577c8884fde48125443e826","observation_id":"057b082f-5c8f-4dfc-af06-0497ce761f34","resolution":{"observed_at":"2026-08-05T19:03:27.099316Z","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":"2026-08-05T19:03:40.611655Z","title":"Adaclip: Adapting clip with hybrid learnable prompts for zero-shot anomaly de- tection","venue":null,"work_id":"d929896b-f500-4ea5-a5e7-f0c7ffe0e512","year":2024},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:27.220584Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:8fa6d19845dea796510a9e5744f039ff14435bbf378959ba7ddd7b9f61dd55c9","observation_id":"3717cded-97af-41c6-a6f3-f60ac079dd3f","resolution":{"observed_at":"2026-08-05T19:03:40.725580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:40.472900Z","title":"Center-aware residual anomaly synthesis for multiclass industrial anomaly detec- tion","venue":null,"work_id":"637eaab4-ea4e-4577-88d4-5ae72fc0aa02","year":2025},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:27.344721Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:b7e3a6ebea17f01b14ff9b1393e4ff53ac7fa4d188fee608358b830a199e04c5","observation_id":"4080185f-9600-4619-ae26-515e2758bccb","resolution":{"observed_at":"2026-08-05T19:03:40.545898Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.17382","last_updated":"2023-10-11T07:02:45Z","snapshot_observed_at":"2026-08-10T13:06:02.519410Z","submitted_at":"2023-05-27T06:24:43Z","title":"APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.17382","snapshot_observed_at":"2026-08-05T19:03:27.539289Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:27.539289Z"},"links":{"cited_paper":"/paper/2305.17382","citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:bbcfeff019ff8f47fe3b1897cc0d12eab94764db6648d52d3b1153b953538f6a","observation_id":"943bdf82-48d2-45c2-b7cb-52496241ed87","resolution":{"observed_at":"2026-08-05T19:03:27.539289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.02357","last_updated":"2021-02-03T16:28:51Z","snapshot_observed_at":"2026-08-09T14:17:32.431497Z","submitted_at":"2020-05-05T17:43:35Z","title":"Sub-Image Anomaly Detection with Deep Pyramid Correspondences","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.02357","snapshot_observed_at":"2026-08-05T19:03:27.699167Z","title":"Sub-image anomaly detection with deep pyramid correspondences","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:27.699167Z"},"links":{"cited_paper":"/paper/2005.02357","citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:2651842fa7b7249e069a35180fcd276428f3148374434188497edfa2f058332e","observation_id":"5fe230a9-48b9-4fe0-b46c-082b2c6cebd5","resolution":{"observed_at":"2026-08-05T19:03:27.699167Z","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":"2026-08-05T19:03:40.306208Z","title":"Padim: a patch distribution modeling framework for anomaly detection and localization","venue":null,"work_id":"ba8ffe38-125b-4be3-83f4-75df38c6c277","year":2021},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:27.884489Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:5d61ae0db78f871a3b7c30c48882174efd92a1089f874b29efe76d104a3f2c64","observation_id":"d2c3fd0d-28b9-4d09-b66a-a86c1348e165","resolution":{"observed_at":"2026-08-05T19:03:40.399595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:40.169932Z","title":"The pascal visual object classes (voc) challenge","venue":null,"work_id":"8e7640b6-c1ac-4bd7-b789-811c3b1a723f","year":2010},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:28.022512Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:452ca3657fe393e6e5b87bca433a2664129747d11d0eb8cf847da736f259cb55","observation_id":"d4844ca3-a02c-466e-bbee-41c96940c54d","resolution":{"observed_at":"2026-08-05T19:03:40.274459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:40.008035Z","title":"Fastrecon: Few-shot indus- trial anomaly detection via fast feature reconstruction","venue":null,"work_id":"8774fdc7-3da1-4b28-8b1d-cc9573b4bd0d","year":2023},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:28.155844Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:bf752838c6105e9298a3115fe600922975df253d5111a78ba7ec7a551f5815f9","observation_id":"83e9d306-87b2-404f-9904-3ed6d0096953","resolution":{"observed_at":"2026-08-05T19:03:40.120865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:39.813343Z","title":"Metauas: Universal anomaly segmentation with one-prompt meta-learning","venue":null,"work_id":"15b035f0-a3e2-430b-9c53-eecd9639a00e","year":2025},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:28.298601Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:2c048228e2a4f28dbc3af14afeb583d537c4e7b80da4680717282bc0902ee8ca","observation_id":"2727b713-9f84-4195-97bb-3c2ee9b34437","resolution":{"observed_at":"2026-08-05T19:03:39.888905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:39.639286Z","title":"Anomalygpt: Detecting in- dustrial anomalies using large vision-language models","venue":null,"work_id":"bdac1b0e-651a-4b47-a04e-e5a32a96c689","year":1932},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:28.393493Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:fa24dee919eda03c823452a97e329e1aef3fac4f8239dc9b027ecf3a7d37acef","observation_id":"fd884883-942d-4414-9823-e241f721dc8e","resolution":{"observed_at":"2026-08-05T19:03:39.735481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:39.521463Z","title":"Automated seg- mentation of macular edema in oct using deep neural net- works","venue":null,"work_id":"dcc1ed67-ff8b-4909-b73d-35a31b0a1f0a","year":2019},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:28.526289Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:85618a518bffeea09337dc052e82115b8e01ff0834b8b1150d3b72d841343954","observation_id":"245db5e2-9988-4f20-85e4-3e3c2cb34b26","resolution":{"observed_at":"2026-08-05T19:03:39.557765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:39.353276Z","title":"Registration based few-shot anomaly detection","venue":null,"work_id":"b04ccc78-bbfc-4a39-8685-1919cb27ef16","year":2022},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:28.613568Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:3e67ce16d617c235880ef2c2c89d2e11f0952a7f1c7fc77c8685b8efc71251a4","observation_id":"962966cf-f0dc-4e99-9cc3-b5e040d81796","resolution":{"observed_at":"2026-08-05T19:03:39.437794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:39.217799Z","title":"Winclip: Zero- /few-shot anomaly classification and segmentation","venue":null,"work_id":"fb7e0196-95e5-4f46-8507-dc1e3ed175d2","year":2023},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:28.758191Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:06e1c680389da50380fb293f7e4ae91a4135e30dc2b5ce00f31b97123f7e703c","observation_id":"4abc3ca6-c5e6-47be-81f9-25e8d422e5d9","resolution":{"observed_at":"2026-08-05T19:03:39.275451Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:39.086672Z","title":"Deep learning-based defect detection of metal parts: evaluating current methods in complex condi- tions","venue":null,"work_id":"83f7d683-fbeb-480b-ab1d-be9904e79c7d","year":2021},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:28.910177Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:76c2f148229e1ccb62ab3047ec7335d57be98f1304c8d8386b73cdc3f2e71b6c","observation_id":"7d8b2ee9-a4a7-4dfc-8b21-a779d2fa53a7","resolution":{"observed_at":"2026-08-05T19:03:39.158693Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","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":"2026-08-05T19:03:29.049427Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:29.049427Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:41045d9fcc5d9dec80476da5b2ecce365b614a520ac785c9109ed87c2b760349","observation_id":"df4334b8-bc54-4898-be11-c88db17ea438","resolution":{"observed_at":"2026-08-05T19:03:29.049427Z","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":"2026-08-05T19:03:38.961720Z","title":"Deep learning","venue":null,"work_id":"6d6a9c83-577b-4da1-8ab0-cc2f0e5e72e3","year":2015},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:29.178911Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:e728bb9b796e11f43c2e0a66e855e9e40083c073b85bb7706127df1619c523a4","observation_id":"929b69e6-9deb-4ee5-a864-47c907e12bae","resolution":{"observed_at":"2026-08-05T19:03:39.013938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:38.782213Z","title":"Promptad: Learn- ing prompts with only normal samples for few-shot anomaly detection","venue":null,"work_id":"252a737c-67f7-4491-8e19-6bd275eca99a","year":2024},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:29.307514Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:fdd6c9a8ddd3b3e73d3481a671ae8982877c774a90375aff2b7ec2790fc70197","observation_id":"0325a91e-c89e-4783-8ac9-2645c9ff2e7f","resolution":{"observed_at":"2026-08-05T19:03:38.895794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.18998","last_updated":"2024-02-29T09:48:19Z","snapshot_observed_at":"2026-08-04T12:58:05.102076Z","submitted_at":"2024-02-29T09:48:19Z","title":"COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.18998","snapshot_observed_at":"2026-08-05T19:03:29.476048Z","title":"Coft-ad: Contrastive fine- tuning for few-shot anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:29.476048Z"},"links":{"cited_paper":"/paper/2402.18998","citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:6f7fa6dc46b5c7090e3a4475652a0f54b883d316defbf657880b189f633ba66f","observation_id":"7511df04-42a8-46ba-b4f3-55365d741126","resolution":{"observed_at":"2026-08-05T19:03:29.476048Z","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":"2026-08-05T19:03:38.465538Z","title":"Medical image classification using gen- eralized zero shot learning","venue":null,"work_id":"a1ac55c1-a1e1-4125-8dbe-74d2a1a7da0e","year":2021},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:29.658904Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:81ab57403deb5774bc3bf79f2600843a54370684fad9f14d9959d8cc55c1d991","observation_id":"6acd9b36-c4d0-4c05-8aba-63d69025634d","resolution":{"observed_at":"2026-08-05T19:03:38.623832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:38.192465Z","title":"From softmax to sparsemax: A sparse model of attention and multi-label clas- sification","venue":null,"work_id":"eff19ab1-38d7-49c3-9c95-f38dae51ec4f","year":2016},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:29.804182Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:20026c2d608fd7ece1ebf931de413c97b4c16f58255028e7b63c0760c743d133","observation_id":"ec906711-1e9a-48d8-9085-5e8a34c284d9","resolution":{"observed_at":"2026-08-05T19:03:38.336048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:37.881251Z","title":"The multimodal brain tumor image segmentation benchmark (brats)","venue":null,"work_id":"cd3bb12f-c51c-4067-b0f6-419729a84a4e","year":1993},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:29.958128Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:01f4788e112fe7bf8b006dfcad1c27602c90eabe89b162cf29ee2258c2a45dbd","observation_id":"fa115870-d329-4afe-a6fc-2e943ec12085","resolution":{"observed_at":"2026-08-05T19:03:38.031339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:37.580183Z","title":"Vt-adl: A vision trans- former network for image anomaly detection and localiza- tion","venue":null,"work_id":"70260db5-05ec-4dcb-b288-b0bf6312ba54","year":2021},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:30.107820Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:0e28847442fe8ca05bf42f8d63dc348dc1939aa7ecb3f7a71d18c1688d18cdf5","observation_id":"2ca012ff-6db7-4280-beea-2cc316a6e821","resolution":{"observed_at":"2026-08-05T19:03:37.774093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:37.227212Z","title":"Lscad: A large-small model collaboration framework for un- supervised industrial anomaly detection","venue":null,"work_id":"a1c97469-2216-4c15-b6b8-952e8fb331cb","year":2025},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:30.251581Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:340025b17b3ac7aded90d6969fef44d536dcb1c8a5c0f28099e8217b0e26788b","observation_id":"53825b62-693a-4356-9bc9-2f3186f142c4","resolution":{"observed_at":"2026-08-05T19:03:37.412043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:36.978920Z","title":"Investigating shift equivalence of convolutional neural net- works in industrial defect segmentation","venue":null,"work_id":"fcbc0657-439c-4edc-abae-bdeb7987ac9e","year":2023},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:30.378413Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:c0588068b616d00c5cfbf18f3f043a047031282e2e28b4e5b85f65a38f3c29ad","observation_id":"3a0bca10-72f7-499f-9ba2-58ccfaf370aa","resolution":{"observed_at":"2026-08-05T19:03:37.112863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:36.686249Z","title":"Vcp-clip: A visual context prompting model for zero-shot anomaly segmenta- tion","venue":null,"work_id":"5f7581d0-72eb-456f-8cf3-31c691fed30d","year":2024},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:30.518062Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:16f16341f4049a1dd0f1a5ce76011aa6687b1471609257a9a21126f0c20be248","observation_id":"0cd708c6-5a43-4f21-b2bb-76740aefff28","resolution":{"observed_at":"2026-08-05T19:03:36.873665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:36.378146Z","title":"Bayesian prompt flow learning for zero-shot anomaly detec- tion","venue":null,"work_id":"65973a82-e6b0-42b4-9061-ebc67178b953","year":2025},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:30.678996Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:a2168bd5141036de9a522a3cfdcaf1ebb90be95a39154cfcc130e719db4c52f1","observation_id":"60ba8a89-100f-495b-a959-ac9d00749f68","resolution":{"observed_at":"2026-08-05T19:03:36.485417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:36.149825Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":"0e8136fe-500d-4a31-91a0-615b84c860ee","year":2021},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:30.792990Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:139d9a3e7b47e79e092511febe30ee8fa71a5f86b55ab4b5a672d698fefcc391","observation_id":"a4c10f83-4ef1-480b-b635-5841b33d66cc","resolution":{"observed_at":"2026-08-05T19:03:36.293641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:35.855138Z","title":"Towards to- tal recall in industrial anomaly detection","venue":null,"work_id":"157f6ec2-d303-418c-89b6-3f15542a7f95","year":2022},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:30.970945Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:dbed3fc4aa5608644c13db4e2c855b812c255a8b06fb9d27a39b89ede081b27d","observation_id":"85a9e10f-6c50-447e-9eff-294dc1660e1d","resolution":{"observed_at":"2026-08-05T19:03:36.014416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:35.593770Z","title":"Same same but differnet: Semi-supervised defect detection with normalizing flows","venue":null,"work_id":"85e9cdc2-8659-4bc7-981a-8955b1a3500d","year":1907},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:31.078134Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:64d0c148f0746ea0fbde9097c57dd4240aa695f8c5ca6bdc34289eaad845a97e","observation_id":"47af037b-b642-480c-8620-8ec05d03dbf9","resolution":{"observed_at":"2026-08-05T19:03:35.725971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:35.313212Z","title":"Maeday: Mae for few-and zero-shot anomaly-detection","venue":null,"work_id":"bd93984e-7ea2-49c4-9413-ebbc1d50ea3a","year":null},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:31.195766Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:09a71643c304785686610978f63a5118899b71b3f46f918aa65fba5abbbcf635","observation_id":"633d38c0-41e5-4dc8-b156-4a563ecf84fb","resolution":{"observed_at":"2026-08-05T19:03:35.423042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:35.065786Z","title":"A hierarchical transformation-discriminating generative model for few shot anomaly detection","venue":null,"work_id":"8bd1ab58-2b22-40d1-8dcd-f09258010e6c","year":null},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:31.344227Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:2ee3f15f4f4688e1bd3fafb0a15e6655fa003f1b3d8103498850ae10a273b38e","observation_id":"456c7152-656f-425d-8c37-a16b13bcf8db","resolution":{"observed_at":"2026-08-05T19:03:35.214727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:34.864863Z","title":"Learning unsupervised metaformer for anomaly de- tection","venue":null,"work_id":"6774c81d-81e4-40b5-80b1-20241b37a22d","year":2021},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:31.479120Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:f0cd9ed6514643c7ffacf4230be971dc8d92f68ea3e3f9d4a9dd41d021a3ebca","observation_id":"3a57e2e8-e4be-426a-9577-62f5e5f37ff6","resolution":{"observed_at":"2026-08-05T19:03:34.963910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:34.499167Z","title":"Learning unsupervised metaformer for anomaly detection","venue":null,"work_id":"59adae44-798e-42b5-b158-aaa01b28840e","year":2021},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:31.634128Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:676a861734c0915c217aad5973d0dc1337fdba5551546f84ac53aa26d1678ae0","observation_id":"967a6f61-fe3a-4fe2-bc35-3866498e31bc","resolution":{"observed_at":"2026-08-05T19:03:34.702194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.12082","last_updated":"2023-10-12T09:01:04Z","snapshot_observed_at":"2026-08-10T09:21:10.563954Z","submitted_at":"2023-01-28T03:58:32Z","title":"Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.12082","snapshot_observed_at":"2026-08-05T19:03:31.756784Z","title":"Pushing the limits of fewshot anomaly de- tection in industry vision: Graphcore","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:31.756784Z"},"links":{"cited_paper":"/paper/2301.12082","citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:76c824784a4e8cda00178f25e472865de46d9b8551500b7c9696899ac9ed6625","observation_id":"81010138-53d2-4c2c-85f3-65005d3c6847","resolution":{"observed_at":"2026-08-05T19:03:31.756784Z","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":"2026-08-05T19:03:34.201800Z","title":"Resad: A simple framework for class generalizable anomaly detection","venue":null,"work_id":"ed88aac0-c10d-41c7-9db9-ab7234cad55e","year":2025},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:31.893091Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:d9e1b480b8089abf8c54304944eccb7fe09b7ea99848d9f719543d7675b75816","observation_id":"93f2d09e-4200-4b65-b3a4-c750a3623556","resolution":{"observed_at":"2026-08-05T19:03:34.291044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:33.909115Z","title":"Draem- a discriminatively trained reconstruction embedding for sur- face anomaly detection","venue":null,"work_id":"a75f7a4a-b96e-4c52-863f-18e6c7bfb497","year":2021},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:32.049520Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:fee3ce1653ef9c184957f81c0fc2f5024890ea56220f9ff984b1eb0e73be64c6","observation_id":"f4642dc1-9f41-4948-aa4b-3f6e125d006d","resolution":{"observed_at":"2026-08-05T19:03:34.059231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:33.593110Z","title":"Scene parsing through ade20k dataset","venue":null,"work_id":"5960b77b-6179-4063-9451-2752598247fe","year":null},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:32.227092Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:549853d6fbd73f4ed327a2d751a4e279ae1ed49f3a63c88446f87cd7ffa9d488","observation_id":"fbbd9073-09b7-4f83-b33f-cc8883289d8d","resolution":{"observed_at":"2026-08-05T19:03:33.759119Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:33.359410Z","title":"AnomalyCLIP: Object-agnostic prompt learning for zero-shot anomaly detection","venue":null,"work_id":"1d1f17c3-03e8-428a-ab38-c07f6db088fd","year":2024},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:32.345149Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:a2221256fbb8c1fc52fdb454181db273ae023b81688c808c717986a6a1a9ef49","observation_id":"da26d2f6-889d-4b44-a1ab-ab442c9fc988","resolution":{"observed_at":"2026-08-05T19:03:33.451792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:33.099530Z","title":"Toward generalist anomaly detection via in-context residual learning with few-shot sam- ple prompts","venue":null,"work_id":"94f3c251-1a91-4ea2-9bd9-62daa6807c6f","year":2024},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:32.473578Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:e8d8ac1474d381434f4a8020a971826971abf227918799017f5d6dd271aa127f","observation_id":"4d0cfb48-c79f-4383-a624-b77d0ec80030","resolution":{"observed_at":"2026-08-05T19:03:33.242705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-05T19:03:32.851963Z","title":"raw_img_path","venue":null,"work_id":"af52344b-6e8b-46e9-b601-4ea4e7e57241","year":2022},"citing_paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T19:03:32.569204Z"},"links":{"citing_paper":"/paper/2508.13565"},"observation_digest":"sha256:2eb36416e3108c3bc0a00dc1ef26c6acd2a22c65837ff19d527312533415c476","observation_id":"7e98b6e3-8920-40bf-a074-09732335899d","resolution":{"observed_at":"2026-08-05T19:03:32.950335Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.13565","last_updated":"2025-08-19T06:56:02Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T20:50:20.201518Z","submitted_at":"2025-08-19T06:56:02Z","title":"Generative Model-Based Feature Attention Module for Video Action Analysis"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":36},"total_outbound_references":43},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2508.13565."}