{"as_of":"2026-08-15T18:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e9f52e9a9eb682fa43576fbf93b7c39d44b270a9c479914c9f4268652f62932d","coverage":[{"denominator":64,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":64,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T22:07:34.787934Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2412.03829/citation-record","integrity":"/paper/2412.03829/integrity","json":"/paper/2412.03829/citation-record.json","paper":"/paper/2412.03829"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:07:35.657781Z","title":"A reconstruction-based feature adaptation for anomaly detection with self-supervised multi-scale aggregation,","venue":null,"work_id":"4c15fca5-d6a6-4afb-b69a-1d8ba2dd97cf","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.532840Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:f649148a09ab689877a148c28f29ab850e75bce5bdca2d36cdb9f34fccbe2047","observation_id":"a27001f3-92fa-4680-851b-1120cdc0ce94","resolution":{"observed_at":"2026-08-11T22:07:35.661700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.647101Z","title":"Simplenet: A simple network for image anomaly detection and localization,","venue":null,"work_id":"37fab42e-d700-4c68-bfad-8cf7847edbe8","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.537346Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:f8fd49f8f3e292422827fe59defe779a9825be4d0dadca0f3f6cf20a04d93f1c","observation_id":"acad7fd4-9499-4444-ac8e-5a974e17e3cd","resolution":{"observed_at":"2026-08-11T22:07:35.651089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.635775Z","title":"Omni-frequency channel-selection representations for unsupervised anomaly detection,","venue":null,"work_id":"7cceae88-a75b-4630-9a98-bd0e9c3ee476","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.541470Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:dd463a92ee4222e05074afb76b046d8126a44fc4cd947c1019c46378d635c724","observation_id":"54df62d4-6d26-4de7-b6c5-221a2e19268f","resolution":{"observed_at":"2026-08-11T22:07:35.639623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.625268Z","title":"Target be- fore shooting: Accurate anomaly detection and localization under one millisecond via cascade patch retrieval,","venue":null,"work_id":"08abeb09-7729-481d-9cd1-0c6aa0fc1106","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.545842Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:9e6f3dc92cd177f17458bfdec89a0c7a2fc903b241d4be7ef96f2d1077cdff5e","observation_id":"4a1c222f-8ed5-4453-aa5e-24ee72149901","resolution":{"observed_at":"2026-08-11T22:07:35.629182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.614185Z","title":"Deep one-class classification,","venue":null,"work_id":"0027bb82-bc30-4c42-bbd5-1e21c7237b82","year":2018},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.549834Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:59646705e5cf5c2bcdbd12a518fbee5eff417c3980fab79cc6646fc00a0f8d6b","observation_id":"79aaeaa5-ac31-4816-bd7b-5bcdbea220eb","resolution":{"observed_at":"2026-08-11T22:07:35.618211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.602867Z","title":"Learning deep features for one-class classification,","venue":null,"work_id":"5cef8d66-be73-4cf7-816b-6be97b1981c2","year":2019},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.553803Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:a354dff02b40d0750323f37e69e913b97e936c6a23730f192528a179040a208e","observation_id":"8944d4b1-59ef-42c0-8985-dec0e8c6186f","resolution":{"observed_at":"2026-08-11T22:07:35.607005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.591516Z","title":"Coft-ad: Contrastive fine-tuning for few-shot anomaly detection,","venue":null,"work_id":"f308ade8-62d2-46e5-a162-1d11c198e0c3","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.558134Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:aaac8d53023f516c6cb9c3202a9ac6fe16855098a84a50bf4b28e26d153bb3dc","observation_id":"27af588a-5dc0-4db1-a332-f9ab65e455c3","resolution":{"observed_at":"2026-08-11T22:07:35.595591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.580064Z","title":"Few-shot anomaly detection with adversarial loss for robust feature representations,","venue":null,"work_id":"af7b6af4-a58e-4489-95d6-93838ca678d9","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.561728Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:7ce3cdd2aae8f2ccae162e5ae10f6e70efc3b661e5aef5e666178ab636c5c721","observation_id":"1ba7adae-18f1-4426-a882-67a18011c256","resolution":{"observed_at":"2026-08-11T22:07:35.584027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.569116Z","title":"Zero-shot versus many-shot: Unsupervised texture anomaly detection,","venue":null,"work_id":"2278c377-36a1-42b3-86b9-1cbc8cd39d76","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.565635Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:7f50ead1d18b5a835715c75e3fb3d41eef165c0fca405c13f3f921d894af029d","observation_id":"40072f3c-2d60-4c4c-926f-89e2319fc9bc","resolution":{"observed_at":"2026-08-11T22:07:35.573015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.558168Z","title":"Pushing the limits of fewshot anomaly detection in industry vision: Graphcore,","venue":null,"work_id":"cb1c3533-acc0-4ac0-b3d1-2c518a4078a6","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.569333Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:fa6a8a3408e58fd9d7afcd1bd2ac7a0143fe4929d23e008270d61e0a38af8223","observation_id":"f86c455d-8940-4d98-8da7-9657696b3a15","resolution":{"observed_at":"2026-08-11T22:07:35.561978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.10592","last_updated":"2023-10-02T16:38:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-04-20T18:25:35Z","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.10592","snapshot_observed_at":"2026-08-11T22:07:34.573225Z","title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.573225Z"},"links":{"cited_paper":"/paper/2304.10592","citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:e26ac2af1d5efc24417d24fafae743767ecb63fc5d638a00acbc5bc42fdae26e","observation_id":"94c316fe-21bf-436a-abec-7ffc31158e2a","resolution":{"observed_at":"2026-08-11T22:07:34.573225Z","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":"2026-08-11T22:07:35.546128Z","title":"Flamingo: a visual language model for few-shot learning,","venue":null,"work_id":"76a14462-05ce-4169-bd52-d3bfdd162eb2","year":2022},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.578329Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:1c7aab460cc2409b37f903d4a8978b4fc38e7796322f5dded38e421d029c4574","observation_id":"a5fa07da-c53b-486e-941f-6cc26d90e1d7","resolution":{"observed_at":"2026-08-11T22:07:35.550308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.534856Z","title":"AnomalyCLIP: Object-agnostic prompt learning for zero-shot anomaly detection,","venue":null,"work_id":"d9e1b4cd-1434-47b0-b329-98a2e70da5f2","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.582029Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:f629ed5f8b8da9a5a21f3e395e8922012529339cf7cac66ac70511268020613c","observation_id":"c5580fee-00f2-4aa9-a8d4-5aef7c5f29a4","resolution":{"observed_at":"2026-08-11T22:07:35.539155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.523676Z","title":"Learning transferable visual models from natural language supervi- sion,","venue":null,"work_id":"31898acf-731f-43bb-aa12-a05c4806e184","year":2021},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.585756Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:5d096c3d31eb3415ba49246aa8b6a94b69e2b6b648035ad8c7dc25a2ece42d82","observation_id":"ee6f690a-d48e-48c9-8d00-def79c5b421f","resolution":{"observed_at":"2026-08-11T22:07:35.527832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.511746Z","title":"Clip-fsac: Boosting clip for few-shot anomaly classification with synthetic anomalies,","venue":null,"work_id":"7f0a11b5-6425-4b53-8fa9-0c6f1a5049be","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.589657Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:a2b1e6a9ffbe512d72b80ef9f6ba95913be12c12822c670911a62c633d37c928","observation_id":"a962dbca-f15d-47bc-81fc-97536ebf034b","resolution":{"observed_at":"2026-08-11T22:07:35.516280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04544","last_updated":"2025-03-25T14:34:04Z","snapshot_observed_at":"2026-08-13T17:56:46.435125Z","submitted_at":"2021-10-09T11:39:30Z","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.04544","snapshot_observed_at":"2026-08-11T22:07:34.593415Z","title":"Clip-adapter: Better vision-language models with feature adapters,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.593415Z"},"links":{"cited_paper":"/paper/2110.04544","citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:6b4617af55695a8dc8b4ac5fe2625616e62d5c1f8a0f8219184e760e3db454fc","observation_id":"40806851-1bf3-4169-bc6c-36e5a8a8431a","resolution":{"observed_at":"2026-08-11T22:07:34.593415Z","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":"2026-08-11T22:07:35.499993Z","title":"Pni: Industrial anomaly detection using position and neighborhood information,","venue":null,"work_id":"6f3b3821-c3be-4a67-bca3-9d2168279711","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.597684Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:280a15af37e3da8539800af885b350ba290d6bcb73ee5325f05de606774a1ca6","observation_id":"a70e232e-cef7-474f-846a-4a9fdffbfb76","resolution":{"observed_at":"2026-08-11T22:07:35.504205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.488219Z","title":"Multiresolution knowledge distillation for anomaly detection,","venue":null,"work_id":"b9e9236e-fdb5-46b1-a151-5c7caa551567","year":2021},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.601391Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:b59b580ab3fe621c0edd0a184bf67e459ef168d4995799833a2a94eabb34c5ce","observation_id":"9e9af9c5-029a-4fef-b309-d41cfc23cd5e","resolution":{"observed_at":"2026-08-11T22:07:35.492065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.477256Z","title":"Filo: Zero-shot anomaly detection by fine-grained description and high-quality localization,","venue":null,"work_id":"fbe5f90c-83dd-41fa-8f10-e0e22d735dc7","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.605375Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:700332bc8a4eb367e3ad648b614710931212299dd0a9796114475e0698bddf90","observation_id":"46383726-a7c1-4698-ab6c-b715bbc85c25","resolution":{"observed_at":"2026-08-11T22:07:35.481406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.465811Z","title":"Ganomaly: Semi- supervised anomaly detection via adversarial training,","venue":null,"work_id":"8478c23d-0034-4360-847d-dbdd185668e2","year":2019},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.609213Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:03bb0fee37ea6047079e6761dd991a28e4a2ce281eb3ac7802dfc1e6417b605f","observation_id":"f6f4abec-8070-47d4-a4c3-875f1beeeb19","resolution":{"observed_at":"2026-08-11T22:07:35.469934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.453825Z","title":"Focus the discrepancy: Intra- and inter-correlation learning for image anomaly detection,","venue":null,"work_id":"8aa22a42-042c-4b27-aa94-0e700e6504b0","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.613011Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:019c0f747a566894ac40ce873c240e900593b75f42711510b0b6950f51ed096c","observation_id":"5a79b133-dbc9-46db-acbe-4ad261c93a24","resolution":{"observed_at":"2026-08-11T22:07:35.457993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.442791Z","title":"Unsupervised anomaly detection for surface defects with dual-siamese network,","venue":null,"work_id":"34ef1355-d4c3-4e35-9c37-1d480f98b4a2","year":2022},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.616763Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:2ff4943658cd5ada036f3f95d7dc46c2cbf78cd2e2d19612c2e2b52e24cc5489","observation_id":"3a46d2de-76a5-42ef-aed8-5d8152914c5d","resolution":{"observed_at":"2026-08-11T22:07:35.446632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.431523Z","title":"Cutpaste: Self-supervised learning for anomaly detection and localization,","venue":null,"work_id":"b1552cb7-5983-43b5-9990-82c4375a6251","year":2021},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.620415Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:8187f7253f59178ac23467e523630046c473560b43cc1abafd3f0e478d1ecc85","observation_id":"0fe6fbaa-e6f2-4bf0-8b51-a679019c3d41","resolution":{"observed_at":"2026-08-11T22:07:35.435730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.419786Z","title":"Generative adversarial nets,","venue":null,"work_id":"656fb956-dd22-4aeb-a8be-93225b46504b","year":2014},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.624322Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:aa1763dcbaff42e4bcc02fe24eff3acced54792788784c3705de9189d46a7470","observation_id":"8bc3a575-65f1-4eb7-8535-5ea4058027bb","resolution":{"observed_at":"2026-08-11T22:07:35.423933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.408065Z","title":"Diad: A diffusion-based frame- work for multi-class anomaly detection,","venue":null,"work_id":"274a0b29-f10c-4f83-9d14-8d278fdbfba2","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.628128Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:03d8806447961d1550c24f3d718dd421ec24fcf25ffab441733d36ab4d08ad68","observation_id":"92ebefa7-92e2-4539-a4d1-97a0f66b7102","resolution":{"observed_at":"2026-08-11T22:07:35.412217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08730","last_updated":"2025-05-17T03:30:17Z","snapshot_observed_at":"2026-08-13T18:23:05.779034Z","submitted_at":"2023-03-15T16:14:06Z","title":"DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08730","snapshot_observed_at":"2026-08-11T22:07:34.631876Z","title":"Diffusionad: Norm-guided one-step denoising diffusion for anomaly detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.631876Z"},"links":{"cited_paper":"/paper/2303.08730","citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:e43c3e2ca7b3f10c2e8930c5ec0601aed845974b15cc141e8b598d4a6ed9e7fb","observation_id":"6e816e44-4fa7-47b8-8168-51145311dacc","resolution":{"observed_at":"2026-08-11T22:07:34.631876Z","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":"2026-08-11T22:07:35.395611Z","title":"12-in-1: Multi- task vision and language representation learning,","venue":null,"work_id":"5daa003b-7e45-429a-a025-d1299230127b","year":2020},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.636098Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:7189eeb9507622044f8d7d5da7c72d002c98243ea87bafc4cccdb17368cbe1c8","observation_id":"b994dc12-818e-4ba4-aaef-3faaf815c49b","resolution":{"observed_at":"2026-08-11T22:07:35.399627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.384275Z","title":"Alpha-clip: A clip model focusing on wherever you want,","venue":null,"work_id":"c0d40397-3a41-4bea-9c8b-e0113a5562af","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.640815Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:81c5dff871c0b383b6d1c7aa67fc2cae4743c869856a58d0b11b0afb818fe5f7","observation_id":"acdbe881-0b25-4eb3-acd4-df21a5eb7484","resolution":{"observed_at":"2026-08-11T22:07:35.388381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.373353Z","title":"Interpreting CLIP’s image representation via text-based decomposition,","venue":null,"work_id":"4249fb98-4e4a-4ad1-bf11-d0e8cb187eb4","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.644658Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:72e787df20fac7cb18b23e28c1c624b7ed88fa293ef127b6677343003e477399","observation_id":"74f76195-b50a-4001-8679-8de279a6c20c","resolution":{"observed_at":"2026-08-11T22:07:35.377481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.361553Z","title":"Pointclip: Point cloud understanding by clip,","venue":null,"work_id":"b4180fad-e937-4b91-bf02-1f3e2d976ae6","year":2022},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.648784Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:f3d40f76ad49ba204789a7493cb442f387883564e34bbf3794166b51ef53969f","observation_id":"38cc4454-6cc4-418e-841d-9ba302699cc8","resolution":{"observed_at":"2026-08-11T22:07:35.365853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.349467Z","title":"Actionclip: Adapting language-image pretrained models for video action recognition,","venue":null,"work_id":"9b208081-5519-4127-9a02-ecfbbafd989d","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.652528Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:e2b2f2be3d10216814ffabe86505338b36bfa317e93b239eaaaad094be3fb83f","observation_id":"4d812f91-e19f-4064-bcf2-a188526606f9","resolution":{"observed_at":"2026-08-11T22:07:35.353612Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.338281Z","title":"Grounded language-image pre-training,","venue":null,"work_id":"ef2db4a1-32dc-40f9-ac79-c56745c76def","year":2022},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.656230Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:228f332328d140e66f66640119bd000aa6ba838031aeb0f697f5d6f23ffe2429","observation_id":"a982f189-5240-4187-80db-194971adc53b","resolution":{"observed_at":"2026-08-11T22:07:35.342379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.327069Z","title":"Denseclip: Language-guided dense prediction with context-aware prompting,","venue":null,"work_id":"79587190-9ab4-4493-9991-a672ce4e81c1","year":2022},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.660223Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:070463f994a8c2e8e822ffa3504d11e86a627ca0fb9b659f0383e230d7cf921c","observation_id":"99ee8c33-36a3-4614-8072-ec2ce201b6c9","resolution":{"observed_at":"2026-08-11T22:07:35.331182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.315401Z","title":"In defense of clip-based video relation detection,","venue":null,"work_id":"2069a036-8870-4c4d-8f84-bb31f790db0e","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.664214Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:88d5b4232bd75fea1ec64cf1a616fbd21061ff680a0d723229ed6a4ad8218bbe","observation_id":"2bfe86db-c017-48c3-bce0-9f86b56b479b","resolution":{"observed_at":"2026-08-11T22:07:35.319725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.302904Z","title":"Clip-driven fine-grained text- image person re-identification,","venue":null,"work_id":"fb51cbf2-6ce5-486f-ad57-779add174807","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.668310Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:535155b7fb039ffe96e30311f5efe9a9b281c0b1ec626922eb5b595473fee0fe","observation_id":"c2953a91-b3ee-4bee-bf69-3eb959481e08","resolution":{"observed_at":"2026-08-11T22:07:35.307397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.291819Z","title":"Turning a clip model into a scene text spotter,","venue":null,"work_id":"9b0ccc62-4444-429f-896b-4ae14b5ba196","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.672552Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:73933a5e32e635971b3aeacc37c7c5ff0fac152005ea7c7dff70135f0a6c3b18","observation_id":"4d9405a2-2f49-4532-b549-15ec6196459f","resolution":{"observed_at":"2026-08-11T22:07:35.295665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.279909Z","title":"Winclip: Zero-/few-shot anomaly classification and segmentation,","venue":null,"work_id":"f5147338-4454-4442-b230-b1eb00613574","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.676334Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:5b53eebe46b58e040c9c3497ea2b5b8d64374b0cc36b26a0e1ad45dab0aa376f","observation_id":"9dd3bdb0-96be-4ca3-b451-afd008e88137","resolution":{"observed_at":"2026-08-11T22:07:35.284114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.267959Z","title":"Fastrecon: Few- shot industrial anomaly detection via fast feature reconstruction,","venue":null,"work_id":"9d7b6481-6fa6-4228-9b49-649aed4c53a2","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.680314Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:23bcc8bd2418cfe27c56f227557065542b6dfa0bf4ce162b11f2f174b754fcfe","observation_id":"37ebd55a-01a9-44da-bb66-de7df66eb3dc","resolution":{"observed_at":"2026-08-11T22:07:35.272031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.256608Z","title":"Few- shot fast-adaptive anomaly detection,","venue":null,"work_id":"2690e900-99b5-49e7-93a3-3c7e5f30ae4e","year":2022},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.684089Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:278404fedf862af11abf97f41818f5c1ba1f346acd654e41dad5cba4e7bb477a","observation_id":"2f857b9b-8596-4935-be2e-d47c7598b4b3","resolution":{"observed_at":"2026-08-11T22:07:35.260631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.244647Z","title":"Toward generalist anomaly detection via in-context residual learning with few-shot sample prompts,","venue":null,"work_id":"63afbfb1-c08a-46a4-bb30-9ce55262291f","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.688029Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:e5155f8cfb7a58fda77830198494aa8edcc9eff2ab4bafdffc372f0b20d18cb5","observation_id":"345a0080-3720-4615-899d-69b53c1737a4","resolution":{"observed_at":"2026-08-11T22:07:35.249073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.233185Z","title":"Fewsome: One- class few shot anomaly detection with siamese networks,","venue":null,"work_id":"541c0686-15ea-437e-b68e-d6359823118b","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.692053Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:1aa2988c6d8de79ef09f12332863789198d90d79b84bfbb93ba3ef95fc2476e2","observation_id":"1ddbb263-9dac-4297-bc00-558bc98f47e3","resolution":{"observed_at":"2026-08-11T22:07:35.237231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.219566Z","title":"Registration based few-shot anomaly detection,","venue":null,"work_id":"f99bd73b-d495-41d6-ab75-b11676375db2","year":2022},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.695818Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:1595f67c85eea6afe2746923f3b278f64e21333a909f2fb69b8122d968e3c313","observation_id":"6d287d6b-fc05-43fd-8f4b-f17ef56704f0","resolution":{"observed_at":"2026-08-11T22:07:35.224689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.12665","last_updated":"2024-01-29T10:57:38Z","snapshot_observed_at":"2026-08-14T19:21:37.217085Z","submitted_at":"2024-01-23T11:20:03Z","title":"ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.12665","snapshot_observed_at":"2026-08-11T22:07:34.699824Z","title":"Clipsam: Clip and sam collaboration for zero-shot anomaly segmentation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.699824Z"},"links":{"cited_paper":"/paper/2401.12665","citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:f3382bcbe37047d4f7e10fba12c1db0394194c6fc987a53cb2427547ecab0968","observation_id":"3851f3e4-ec8f-4f13-b466-3fd16a273282","resolution":{"observed_at":"2026-08-11T22:07:34.699824Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.00453","last_updated":"2024-03-02T13:54:31Z","snapshot_observed_at":"2026-08-13T05:35:02.501086Z","submitted_at":"2023-11-01T11:39:22Z","title":"CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.00453","snapshot_observed_at":"2026-08-11T22:07:34.704463Z","title":"Clip-ad: A language-guided staged dual-path model for zero- shot anomaly detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.704463Z"},"links":{"cited_paper":"/paper/2311.00453","citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:846fd8b2c3025b491d78d31396b6a899dc379c24c3b71eef1bd8ca314ad2478f","observation_id":"628c1d1c-9b8d-43cc-bc1c-563439a634e8","resolution":{"observed_at":"2026-08-11T22:07:34.704463Z","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":"2026-08-11T22:07:35.207472Z","title":"Anomalygpt: Detecting industrial anomalies using large vision- language models,","venue":null,"work_id":"e937f31e-b856-4ef6-9958-521c5aa44ed3","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.708922Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:aea7161c52d0014c40a586aa41205f3f3838638e11a34e3121756540134d170c","observation_id":"53a00488-3356-4050-99ce-9c97a9874308","resolution":{"observed_at":"2026-08-11T22:07:35.211496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.195367Z","title":"Promptad: Learning prompts with only normal samples for few-shot anomaly detection,","venue":null,"work_id":"4efa631f-5807-4264-819d-50691d34a06c","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.712816Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:1711fd3704d67e96909de01719f00c98080270f55b9b9573374091edbf43a81a","observation_id":"7e4047c7-3004-47f6-895f-4d7985c83eaf","resolution":{"observed_at":"2026-08-11T22:07:35.199610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.182875Z","title":"Collaborative discrepancy optimization for reliable image anomaly localization,","venue":null,"work_id":"43260d67-3d29-443c-8fe4-85140787e199","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.716560Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:06a72ea8b36b3c31ea4dad10b08873ea071eed66439825b23fb915c186b07dff","observation_id":"35db4451-b7c7-4cd7-8ba9-918e12b215ee","resolution":{"observed_at":"2026-08-11T22:07:35.187382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.170971Z","title":"Natural synthetic anomalies for self-supervised anomaly detection and localization,","venue":null,"work_id":"c01e7aa5-d7aa-4e67-84cd-fbba03b3583b","year":2022},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.720571Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:cba8130853bbdcbc01873236ca498f95984b824a9d73802978ddd673e22963d6","observation_id":"04bc81c6-69de-48c6-a018-08250301891e","resolution":{"observed_at":"2026-08-11T22:07:35.174973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.159686Z","title":"Momentum contrast for unsupervised visual representation learning,","venue":null,"work_id":"583c62ea-b5d5-460c-98f6-de6fd05b1d5a","year":2020},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.724840Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:810b44b0bb172143da6e262c7d93584a9590fa97adf6692c62a21fe2c4b61943","observation_id":"9d77c78b-5d9b-49b6-a85b-ab40b6a58f9f","resolution":{"observed_at":"2026-08-11T22:07:35.163767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.146499Z","title":"Padim: A patch distribution modeling framework for anomaly detection and localiza- tion,","venue":null,"work_id":"229f5a32-3d2d-4c1c-b7b1-6d785909e765","year":2021},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.729008Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:6441cedfe223fd709f501683e1eeafe5a8e79d02690f0bc8beb27526d8136aa0","observation_id":"f5212c28-9415-4a00-aedd-75130fd0bafa","resolution":{"observed_at":"2026-08-11T22:07:35.151276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.133880Z","title":"Towards total recall in industrial anomaly detection,","venue":null,"work_id":"cd5bbf0b-3a19-47a4-97ed-74e6f2a03728","year":2022},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.733080Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:47c8af50d2e5f57c52b413c1a00c836274194b40e0782de8121a7909cddb8e91","observation_id":"f6d6917d-b513-4c8f-930e-847ae11cfc6e","resolution":{"observed_at":"2026-08-11T22:07:35.138185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.120809Z","title":"Sub-image anomaly detection with deep pyramid correspondences,","venue":null,"work_id":"c0a6c511-799d-4d83-9e97-0b754b3a3933","year":2021},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.737501Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:d28883a60a71871401d167e1f5dbe52012d74c7099170d7430abafadda0191db","observation_id":"8854f8e0-31ee-4d97-82c1-143a247eca6a","resolution":{"observed_at":"2026-08-11T22:07:35.124965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.108718Z","title":"Mvtec ad — a comprehensive real-world dataset for unsupervised anomaly detection,","venue":null,"work_id":"271be376-ce68-43dd-8537-eaf45434ac65","year":2019},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.741409Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:0796e587788bc3f4e2947aa1bc8e0770184c39f249574177042d075074f87b45","observation_id":"5fe9b4e6-0641-45af-bd51-b750502085eb","resolution":{"observed_at":"2026-08-11T22:07:35.112869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.097255Z","title":"Spot-the- difference self-supervised pre-training for anomaly detection and seg- mentation,","venue":null,"work_id":"14cbf0ca-e2be-4ca8-90ab-bbb5bf3dedf9","year":2022},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.745321Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:e66bebf32f1b6109727898c032c94ab4b94d1ce4324e6a889b9e82bf73a5dd38","observation_id":"7bf89a99-66a5-4345-b31e-af401be60de1","resolution":{"observed_at":"2026-08-11T22:07:35.101426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.086151Z","title":null,"venue":null,"work_id":"3bc13c34-79a5-4c1c-97d0-c82164bc40cd","year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.749418Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:32cf547097f5e382f11b922a4d7fe3ed8abda49fa3af10ab178d94e98ff770cb","observation_id":"346f7ee2-22d9-4be5-80e2-9662d2c8b5d6","resolution":{"observed_at":"2026-08-11T22:07:35.089859Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2408.13516","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:07:34.955200Z","title":"Anople: Few-shot anomaly detection via bi-directional prompt learning with only normal samples,","venue":null,"work_id":"664b6fea-48ab-4907-ab00-60b6e9951af5","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.753578Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:e682062f1edf3d5bc6e92d2b9c41d5ce40a8c7c4df28619c18d0c4efb2986889","observation_id":"c0ef731f-eac5-4c18-8847-15542adb8476","resolution":{"observed_at":"2026-08-11T22:07:34.961472Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:34.757985Z","title":"Openclip,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.757985Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:8d1fd7675b809f3a2b058bc7ef960fddb3f5f689bf50eaf2fe3ee8be70e53651","observation_id":"314a5873-4dd6-41a4-bae0-045e63fd27de","resolution":{"observed_at":"2026-08-11T22:07:34.757985Z","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":"2026-08-11T22:07:34.762762Z","title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.762762Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:6410ea03d5821a18043aa5ba7a16b973a6ce5566b7f6c1450d2cb74340d86ba3","observation_id":"dd8cd18e-f060-465a-aae4-68666a561bee","resolution":{"observed_at":"2026-08-11T22:07:34.762762Z","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":"2026-08-11T22:07:35.067113Z","title":"Efficientad: Accurate visual anomaly detection at millisecond-level latencies,","venue":null,"work_id":"27613b4d-fde4-4dbc-b8f9-bf82ebadb49d","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.767013Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:162282297b5dbc46faae318489c1ce22d7fa12b6df95ec804524ad3763c72a96","observation_id":"158b76b9-7691-4e50-9f80-d903fe84954f","resolution":{"observed_at":"2026-08-11T22:07:35.071068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.07068","last_updated":"2023-09-13T16:28:43Z","snapshot_observed_at":"2026-08-13T21:26:10.381965Z","submitted_at":"2023-09-13T16:28:43Z","title":"FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.07068","snapshot_observed_at":"2026-08-11T22:07:34.771217Z","title":"Fair: Frequency-aware image restoration for industrial visual anomaly detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.771217Z"},"links":{"cited_paper":"/paper/2309.07068","citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:158248b8bd6fd052e886de772639a03425d706d4de306db5d5c4ec65cc45c0df","observation_id":"aeff1e8b-6a2f-43fd-9e55-fb401c941f88","resolution":{"observed_at":"2026-08-11T22:07:34.771217Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.14485","last_updated":"2022-10-26T05:21:43Z","snapshot_observed_at":"2026-08-14T08:15:36.311864Z","submitted_at":"2022-10-26T05:21:43Z","title":"Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection","version":1},"cited_work":{"arxiv_id":"2210.14485","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.14485","snapshot_observed_at":"2026-08-11T22:07:34.831154Z","title":"Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection","venue":"cs.CV","work_id":"b3607c5d-3b09-4852-8946-d95f3412f603","year":2022},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.775962Z"},"links":{"cited_paper":"/paper/2210.14485","citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:0155c5ec44bd48ab64624339cb3b6f197f878fef67d652c23c888eefb833db4f","observation_id":"482518ba-093f-433c-a06e-9b35837ead56","resolution":{"observed_at":"2026-08-11T22:07:34.837882Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.054427Z","title":"A unified anomaly synthesis strategy with gradient ascent for industrial anomaly detection and localization,","venue":null,"work_id":"cd3c7c60-a7a4-4a8a-8df8-60e6f3e2a552","year":2024},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.780397Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:ecfc808bf18dc5ab6ea3abcd5dcf3ba1a6eb93aebf1f00637ac8e88fa0ed2df7","observation_id":"87a9afcc-bdc5-4913-b998-a8dae7e757a3","resolution":{"observed_at":"2026-08-11T22:07:35.059058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.042513Z","title":"Visualizing data using t-sne,","venue":null,"work_id":"d93de859-ac78-441c-b319-9388e95cbf1f","year":2008},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.784132Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:6b85bd93b0400b401b92ebbcaaccf685858ecdac8201aa73493ecace755bfc5a","observation_id":"3d412d58-d923-44eb-9bb8-4d3af00aa95c","resolution":{"observed_at":"2026-08-11T22:07:35.046764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T22:07:35.030901Z","title":"Learning to prompt for vision- language models,","venue":null,"work_id":"12b94b66-c407-400e-8e55-dc15ed628075","year":2022},"citing_paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T22:07:34.787934Z"},"links":{"citing_paper":"/paper/2412.03829"},"observation_digest":"sha256:6ee30cac6ccfc11efff81a7233f91d0f12d449282b849db8d3d0b2bbf691b509","observation_id":"020a4a85-e657-4ffa-9ea9-9d448d9e864d","resolution":{"observed_at":"2026-08-11T22:07:35.034993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.03829","last_updated":"2024-12-05T02:44:45Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T13:25:12.714749Z","submitted_at":"2024-12-05T02:44:45Z","title":"CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP"},"reference_resolution":{"displayed":64,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":2,"verified_fuzzy":53},"total_outbound_references":64},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2412.03829."}