{"as_of":"2026-08-15T21:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b0a4659e62c91983bddaf1afad5432c235979177f2e9d1c20b1811678d36720a","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T18:59:10.064175Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T23:20:41.133891Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-04T23:20:42.851582Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"cited_work":{"arxiv_id":"2508.13560","doi":null,"metadata_source":"pith","pith_arxiv_id":"2508.13560","snapshot_observed_at":"2026-08-04T23:20:42.851582Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","venue":"cs.CV","work_id":"5951fc68-4ce5-4961-87d9-4ac9ec5f758a","year":2025},"citing_paper":{"arxiv_id":"2509.06693","last_updated":"2025-09-08T13:47:01Z","snapshot_observed_at":"2026-08-10T20:36:34.737160Z","submitted_at":"2025-09-08T13:47:01Z","title":"STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T23:20:41.133891Z"},"links":{"cited_paper":"/paper/2508.13560","citing_paper":"/paper/2509.06693"},"observation_digest":"sha256:114618328d98f36f5fd1362ece6a30fc1b2429ff45c9c4dac44b1d43ea7afdd9","observation_id":"ea951715-8674-4dad-aac8-39b3889113a4","resolution":{"observed_at":"2026-08-04T23:20:42.957200Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2508.13560/citation-record","integrity":"/paper/2508.13560/integrity","json":"/paper/2508.13560/citation-record.json","paper":"/paper/2508.13560"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:59:07.082035Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.082035Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:d8f9599f4d623d2fa7d7d7e2986f846811ed0d092b707034cf0fbd6a2b291c61","observation_id":"100c29bc-65ac-4514-a22f-9ec9ecc75e4e","resolution":{"observed_at":"2026-08-05T18:59:07.082035Z","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":"2026-08-05T18:59:18.903039Z","title":"Medical image analysis using convolutional neural networks: a review","venue":null,"work_id":"a0bd7c76-5e8c-460f-b201-98c076a7e60b","year":2018},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.143477Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:6cccc7d3d2321e4fde7b1b6a88119842af62db8549338e93b6b7268b19b45aaf","observation_id":"7080a032-4d7e-469d-b3d7-5be7c5793225","resolution":{"observed_at":"2026-08-05T18:59:19.043941Z","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":"2026-08-05T18:59:18.683595Z","title":"Fewsome: One-class few shot anomaly detection with siamese networks","venue":null,"work_id":"cfc903cf-e135-433d-a6c2-21f88f7c0937","year":2023},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.233615Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:217897f0baa00c9f7b4c03b434cd7f79fc5ba0b7f2eb297b62fa095f203a00e2","observation_id":"78faa7b2-4d07-487c-9eb9-fe4074839513","resolution":{"observed_at":"2026-08-05T18:59:18.783347Z","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":"2026-08-05T18:59:18.387726Z","title":"Mvtec ad--a comprehensive real-world dataset for unsupervised anomaly detection","venue":null,"work_id":"ce2b7c10-ee5f-426c-8466-d731a48cb672","year":2019},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.337590Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:cc5b873c7a692b68b52a8c18f9353143b0c1394393dc670289a9ecda1426a3b0","observation_id":"7d91c7a2-e83a-402a-87e2-50f4f646f2bc","resolution":{"observed_at":"2026-08-05T18:59:18.526037Z","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":"2112.09045","last_updated":"2021-12-16T17:35:51Z","snapshot_observed_at":"2026-08-13T17:13:50.518308Z","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":"2026-08-05T18:59:07.400067Z","title":"The mvtec 3d-ad dataset for unsupervised 3d anomaly detection and localization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.400067Z"},"links":{"cited_paper":"/paper/2112.09045","citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:2e23566f387f4ff0c86978d3c25d36f977cc3ad71932646729285f4b5dfce887","observation_id":"88b3d618-9c8f-4be4-86d9-19a6302793f7","resolution":{"observed_at":"2026-08-05T18:59:07.400067Z","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":"2026-08-05T18:59:18.156261Z","title":"Adaclip: Adapting clip with hybrid learnable prompts for zero-shot anomaly detection","venue":null,"work_id":"e66d17f0-60be-4531-8606-d893b1867c49","year":2024},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.474165Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:6a3c76101185b7328a45e34cb75c216c23661dabbc0b7a5bc7fb7fd05392dbda","observation_id":"8c6a614e-840a-423f-b798-6e39db9bb7bc","resolution":{"observed_at":"2026-08-05T18:59:18.273321Z","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":"2026-08-05T18:59:17.935586Z","title":"Center-aware residual anomaly synthesis for multiclass industrial anomaly detection","venue":null,"work_id":"0ffe231b-78f8-40da-bb5f-a8c98d243630","year":2025},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.532504Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:c07dbef54fdcca269e3601b0a050149d1f61f920482348933f929270c093a2ba","observation_id":"f982a6a1-44d4-403f-bd21-67778df62fca","resolution":{"observed_at":"2026-08-05T18:59:18.038054Z","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":"2305.17382","last_updated":"2023-10-11T07:02:45Z","snapshot_observed_at":"2026-08-14T16:27:45.217025Z","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":"2026-08-05T18:59:07.580832Z","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","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.580832Z"},"links":{"cited_paper":"/paper/2305.17382","citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:c5ea7b1567d0d76cb3ffa4240749ad6d1c3a2a66b01016fe8e15db6fb1e192e6","observation_id":"e2ce198e-f9d7-4d71-bde9-707db797270c","resolution":{"observed_at":"2026-08-05T18:59:07.580832Z","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":"2026-08-13T23:57:38.237254Z","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":"2026-08-05T18:59:07.630867Z","title":"Sub-image anomaly detection with deep pyramid correspondences","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.630867Z"},"links":{"cited_paper":"/paper/2005.02357","citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:182af6eb121f0b50e6b0d8ff74186de0fb2fae420ed79cc0314ae047aef030f0","observation_id":"b2fb6e2c-16d1-4bb2-8b67-85af30506bca","resolution":{"observed_at":"2026-08-05T18:59:07.630867Z","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":"2026-08-05T18:59:17.678315Z","title":"Padim: a patch distribution modeling framework for anomaly detection and localization","venue":null,"work_id":"e054a589-78f4-4da5-ae4a-faca45a4af10","year":2021},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.681049Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:5e2b0c393c70a6a2f196a72800ab636623d4d7e3cdf43c231c4545563f55670b","observation_id":"6eb41b03-36c4-4879-b46e-f9fef3084d03","resolution":{"observed_at":"2026-08-05T18:59:17.791899Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:59:07.723092Z","title":"The pascal visual object classes (voc) challenge","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.723092Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:e760c668af668726e56c2875190d5ddf1a2f7f2ff9adfdea95e5ea616550b332","observation_id":"6bad250d-979c-4efb-b48e-ec82f7226df4","resolution":{"observed_at":"2026-08-05T18:59:07.723092Z","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":"2026-08-05T18:59:17.411048Z","title":"Fastrecon: Few-shot industrial anomaly detection via fast feature reconstruction","venue":null,"work_id":"b69c0fab-2e51-4449-9658-0ad6966af0d8","year":2023},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.784764Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:a2b2f5ce0739555f0a21e3128f84b348b2c7be20981580ffb01edaa0c83d0733","observation_id":"c6938484-bfc3-47ec-b7aa-8b1d2adee633","resolution":{"observed_at":"2026-08-05T18:59:17.546425Z","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":"2026-08-05T18:59:17.152720Z","title":"Metauas: Universal anomaly segmentation with one-prompt meta-learning","venue":null,"work_id":"7c50d1b7-ec29-4def-817f-a66f91b675d7","year":2025},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.830889Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:4503f2ac39e8cae127c8a68c976073e2a76dc6410bcd5db9da9b0c87983ae3e0","observation_id":"bbbecc70-c176-4cff-b898-c28694fab4f4","resolution":{"observed_at":"2026-08-05T18:59:17.236054Z","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":"2026-08-05T18:59:16.911776Z","title":"Anomalygpt: Detecting industrial anomalies using large vision-language models","venue":null,"work_id":"1dca2f6b-c44b-435d-a3e5-d16c7aba4c74","year":1932},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.874205Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:9b7d94388bf329a2d75b67e6b491f43bfed13f7c01c9e4ba6d40c3dac397b50a","observation_id":"8b8ee526-ef15-4420-bc95-68c0e0386d3f","resolution":{"observed_at":"2026-08-05T18:59:17.017586Z","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":"2026-08-05T18:59:16.613590Z","title":"Automated segmentation of macular edema in oct using deep neural networks","venue":null,"work_id":"c5f8bedd-b97c-48fb-84bf-79a4bed1b55c","year":2019},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:07.949697Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:b4cae99d10508197db002063b3794a7c9cc7a692a74d45ce9c5065873b35cfe2","observation_id":"449b1b85-8254-4bd9-a96b-48c1691882b2","resolution":{"observed_at":"2026-08-05T18:59:16.768298Z","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":"2026-08-05T18:59:16.266955Z","title":"Registration based few-shot anomaly detection","venue":null,"work_id":"0bbe2ba6-293d-4a6c-bf4f-1b44ad5ca1b8","year":2022},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.008657Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:ab8a08589159faf0bf1603fc2337ad5a932aeeaa5b3819548d88a6019bdc9e44","observation_id":"adc261a3-1dad-491b-a459-f1bec371eff4","resolution":{"observed_at":"2026-08-05T18:59:16.456372Z","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":"2026-08-05T18:59:15.968558Z","title":"Winclip: Zero-/few-shot anomaly classification and segmentation","venue":null,"work_id":"7a1d1caa-9d23-422d-8822-f630f4d6f6f7","year":2023},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.084670Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:62fb1b51a92f2f8c4e52d98578b3591ee279553ff36bdbd4c58d641621f9d642","observation_id":"91e9256a-e1a3-4df0-a2d7-a7c6535b6c87","resolution":{"observed_at":"2026-08-05T18:59:16.123121Z","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":"2026-08-05T18:59:15.721781Z","title":"Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions","venue":null,"work_id":"b05957c6-1777-4622-a64e-8588bfd10d87","year":2021},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.170244Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:d2b533b637e137a7690b61184df5302679a93641e0416a9cf144ccfa979c4657","observation_id":"990b2a91-9a36-4ae8-931b-6f07a7a0c0ee","resolution":{"observed_at":"2026-08-05T18:59:15.837919Z","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":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-14T18:51:16.666127Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-05T18:59:08.224096Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.224096Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:edcc46153c261bd03b7d9f99ef1c80768ada9af1e6eed7cb9177637b8661210f","observation_id":"a61db4ab-ca6f-4da6-9b13-d8b6d5dea54b","resolution":{"observed_at":"2026-08-05T18:59:08.224096Z","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":"2026-08-05T18:59:08.297271Z","title":"Deep learning","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.297271Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:fcf49c23302533d279206e7a719be250eed800ff38396f5994f863cf73e6280b","observation_id":"293cff77-699b-450e-84d3-1a9fc4f2ec88","resolution":{"observed_at":"2026-08-05T18:59:08.297271Z","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":"2026-08-05T18:59:15.503344Z","title":"Promptad: Learning prompts with only normal samples for few-shot anomaly detection","venue":null,"work_id":"5edd3b17-385a-465f-949e-2ef0c3c923f0","year":2024},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.374399Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:14759cc3c36cf237a0840546ddf9b67d846aa83d1a7f091baeb806b248c84c36","observation_id":"3abea52b-0a4e-4edd-955a-d2fde4e40e9c","resolution":{"observed_at":"2026-08-05T18:59:15.627768Z","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":"2402.18998","last_updated":"2024-02-29T09:48:19Z","snapshot_observed_at":"2026-08-13T04:07:31.064432Z","submitted_at":"2024-02-29T09:48:19Z","title":"COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection","version":1},"cited_work":{"arxiv_id":"2402.18998","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.18998","snapshot_observed_at":"2026-08-05T18:59:10.164592Z","title":"COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection","venue":"cs.CV","work_id":"5884831d-849f-4ae2-bb13-3967511fef2d","year":2024},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.451570Z"},"links":{"cited_paper":"/paper/2402.18998","citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:616f592302313320dc54258b4c39cb5966cf1cd2f7aa9dab8049543b97dcd966","observation_id":"aacabae7-a46f-4a0e-9444-032444009acc","resolution":{"observed_at":"2026-08-05T18:59:10.303460Z","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":"2026-08-05T18:59:15.235768Z","title":"Medical image classification using generalized zero shot learning","venue":null,"work_id":"ae7827da-0d1d-4871-ae8a-0bd9698f8a0d","year":2021},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.539208Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:5f48695545ab014809ac280e0f3c17cc35aab2f391e1d1b4e4d6f04f50b21ef6","observation_id":"91e9f8fe-05da-4faf-8e66-96c8d624c155","resolution":{"observed_at":"2026-08-05T18:59:15.381222Z","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":"2026-08-05T18:59:15.007362Z","title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","venue":null,"work_id":"3bc47e5c-71bb-4e23-ad5f-00978e6b4d06","year":2016},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.636527Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:bb3db5b790a6e6a63f3391d6871c51ff7b4367e7d80d2d5b511ad6cce9f9fb0a","observation_id":"6e76bfec-195c-4efe-8d1d-5dc74d371e75","resolution":{"observed_at":"2026-08-05T18:59:15.112120Z","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":"2026-08-05T18:59:14.796785Z","title":"The multimodal brain tumor image segmentation benchmark (brats)","venue":null,"work_id":"541bb2a6-3de8-4934-9a3f-b9bffa66ab94","year":1993},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.690043Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:9898d3bf1d5346cede22cbe7466a718c3b7b6174190c53b7e464f712174090a3","observation_id":"b4354657-cee6-475d-8dba-806b593d9fa2","resolution":{"observed_at":"2026-08-05T18:59:14.894216Z","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":"2026-08-05T18:59:14.535834Z","title":"Vt-adl: A vision transformer network for image anomaly detection and localization","venue":null,"work_id":"680beac6-2b79-4937-a09f-712fa4af4a87","year":2021},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.744872Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:79f66ee869c9d00815c4496d06c29566a50bd6f8e090ae0b6bf26ce73c3590ef","observation_id":"0295532f-ec23-402f-a310-21df325710c5","resolution":{"observed_at":"2026-08-05T18:59:14.654603Z","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":"2026-08-05T18:59:14.275234Z","title":"Lscad: A large-small model collaboration framework for unsupervised industrial anomaly detection","venue":null,"work_id":"0a2a2e6e-5581-4a03-bac9-e37f33074a75","year":2025},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.797856Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:299c204d9ce40cf562f85dd0898f4f85c4c1ce69b617e834e70703ffca6e1903","observation_id":"e1534bb3-9b2f-4fb0-bfd6-840639e1c0cf","resolution":{"observed_at":"2026-08-05T18:59:14.383140Z","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":"2026-08-05T18:59:14.056514Z","title":"Investigating shift equivalence of convolutional neural networks in industrial defect segmentation","venue":null,"work_id":"d122c036-cd6e-47c9-bb8f-7fbc30f09860","year":2023},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.851421Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:87c1255eb1c98e65eeff5e64c9c128a2ffc929b509081dced03b58cafabfdf9c","observation_id":"0294bb8d-5b1a-4542-91f0-a6bc92d7ac25","resolution":{"observed_at":"2026-08-05T18:59:14.157033Z","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":"2026-08-05T18:59:13.753876Z","title":"Vcp-clip: A visual context prompting model for zero-shot anomaly segmentation","venue":null,"work_id":"d52dca6b-9bee-49df-8667-02219d851612","year":2024},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.890565Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:399beb7f536c5ad8db35c703b7572afe70e40b5634a22f7ea46e72582dd152f1","observation_id":"fca53566-2a02-4d8c-925d-a986afc30f60","resolution":{"observed_at":"2026-08-05T18:59:13.902424Z","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":"2026-08-05T18:59:13.535741Z","title":"Bayesian prompt flow learning for zero-shot anomaly detection","venue":null,"work_id":"18a10912-7cb3-4d7a-a4c7-38ec670bf445","year":2025},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:08.949439Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:907d1e553966073cbd86a4a5cb4ec25fc39cabaf798c8f4c78ef3bb2dbf517fd","observation_id":"584a7644-09e6-4a05-8608-6655e8fef205","resolution":{"observed_at":"2026-08-05T18:59:13.669065Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:59:09.037393Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.037393Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:1b40256a4def9c7512ee70966d31563a54a80a9d7979c3115ff8f07a47f03afe","observation_id":"7459fcd7-ab6a-473b-845b-259b2296ab31","resolution":{"observed_at":"2026-08-05T18:59:09.037393Z","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":"2026-08-05T18:59:13.272850Z","title":"Towards total recall in industrial anomaly detection","venue":null,"work_id":"2bf5fe56-2a86-4f8f-bbb4-cd5edfbb2955","year":2022},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.096868Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:f117887c9f52655ac748cb439fb6aed02c7582fd69a3b57b9fffae4d956997ac","observation_id":"f40d3f5c-823a-49ac-a1e8-4cc908b009d1","resolution":{"observed_at":"2026-08-05T18:59:13.411064Z","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":"2026-08-05T18:59:13.023306Z","title":"Same same but differnet: Semi-supervised defect detection with normalizing flows","venue":null,"work_id":"d50e2d08-4fe2-494d-86a6-9ef9f11d2157","year":1907},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.161600Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:5317d7f55cfd36160e239b7e48fb0318f813508500ba0e1542f8e10299bc8c11","observation_id":"9939af31-fad2-494f-b89f-e219e4eae541","resolution":{"observed_at":"2026-08-05T18:59:13.124059Z","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":"2026-08-05T18:59:12.745788Z","title":"Maeday: Mae for few-and zero-shot anomaly-detection","venue":null,"work_id":"5d44310e-d0e9-496f-999f-78819545589a","year":2024},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.259258Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:3a3f96bd000e0151380808410d7443b2ec8faf33a257c271712d5200f3ca3956","observation_id":"dc94d27e-33e3-47f6-b3f3-7c493c989e8e","resolution":{"observed_at":"2026-08-05T18:59:12.884981Z","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":"2026-08-05T18:59:12.461058Z","title":"A hierarchical transformation-discriminating generative model for few shot anomaly detection","venue":null,"work_id":"794394e8-517c-43b9-ba6c-450c8401a6dd","year":2021},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.317312Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:be7a2af8646a7d988084f3046e0c34908375ee83e9efb02351ac3dc758a1c470","observation_id":"73a10ba9-ab4d-47b5-8df5-60bb6615a307","resolution":{"observed_at":"2026-08-05T18:59:12.571768Z","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":"2026-08-05T18:59:12.210031Z","title":"Learning unsupervised metaformer for anomaly detection","venue":null,"work_id":"5f90ec97-0f66-4ed4-9695-64a323f35748","year":2021},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.415799Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:d61a1157154a8db0bce626ce817e0c98dba6b1692a8cdb6a00bdef2915e8028a","observation_id":"56538cc0-c65b-4bce-9bac-a5d9002eb6a4","resolution":{"observed_at":"2026-08-05T18:59:12.319704Z","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":"2026-08-05T18:59:11.968069Z","title":"Learning unsupervised metaformer for anomaly detection","venue":null,"work_id":"ea600806-fcb9-441f-bb40-a1cb224a5ea1","year":2021},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.511485Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:a280733bb8bc448c475d49bf9dcdb2e6d7ea085c7d2a94c965a81eaebb055074","observation_id":"d84bca5a-7b80-44e3-a99c-a180969bce30","resolution":{"observed_at":"2026-08-05T18:59:12.060729Z","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":"2301.12082","last_updated":"2023-10-12T09:01:04Z","snapshot_observed_at":"2026-08-14T01:01:54.752901Z","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":"2026-08-05T18:59:09.587820Z","title":"Pushing the limits of fewshot anomaly detection in industry vision: Graphcore","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.587820Z"},"links":{"cited_paper":"/paper/2301.12082","citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:7e9c8291216011673d564202528187bbca63fa3d86b6d7669b7b8ef485ae6b3c","observation_id":"07083c70-f381-433a-9e41-75e0eb3855a7","resolution":{"observed_at":"2026-08-05T18:59:09.587820Z","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":"2026-08-05T18:59:11.718883Z","title":"Resad: A simple framework for class generalizable anomaly detection","venue":null,"work_id":"80fbcae7-0ccb-4b07-9cab-4a46d2d65a5b","year":2025},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.652048Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:2909360f05e0769b8cbc1b6d927caa3f23024c8de55519492b19a456681c5799","observation_id":"447af4ff-b596-4f24-ac9f-20bf7ee69007","resolution":{"observed_at":"2026-08-05T18:59:11.838874Z","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":"2026-08-05T18:59:11.465870Z","title":"Draem-a discriminatively trained reconstruction embedding for surface anomaly detection","venue":null,"work_id":"55971cfe-88ba-49c3-bf92-bf95ab1ae8a5","year":2021},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.698985Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:99f332c8c5eb171043d39394640214f29869ba3b0a7b190ba0345a5cbfe326b6","observation_id":"c6b87188-a999-4314-9617-76f9dba5cb62","resolution":{"observed_at":"2026-08-05T18:59:11.620613Z","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":"2026-08-05T18:59:11.186326Z","title":"Scene parsing through ade20k dataset","venue":null,"work_id":"61132abe-a6ca-4f43-be33-03f7c6fd8604","year":2017},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.811850Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:5dfcf8ed2e8f17509eb4b2819ea1ba5fbf86e6ba419a0f3581b455e5f9685e5f","observation_id":"e66932c8-5389-4bf0-81da-8d92654aabd7","resolution":{"observed_at":"2026-08-05T18:59:11.356429Z","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":"2026-08-05T18:59:10.933667Z","title":"Anomaly CLIP : Object-agnostic prompt learning for zero-shot anomaly detection","venue":null,"work_id":"d0de65e5-164d-4990-9a7d-d6d899e919ec","year":2024},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.852219Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:86a347664dc4ad70068114bd669421332ffd701d18a5e7197919569f3a8cef5b","observation_id":"fa56e008-9d96-47f1-8bcd-d2c78fece8c3","resolution":{"observed_at":"2026-08-05T18:59:11.086422Z","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":"2026-08-05T18:59:10.695686Z","title":"Toward generalist anomaly detection via in-context residual learning with few-shot sample prompts","venue":null,"work_id":"92b06996-0ba9-4df9-a577-902f1d7b6e3d","year":2024},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:09.980477Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:9f402dbf57cee94f114d9e8c7ab3820ae1ed49f68e58aec2d4c232ec37214588","observation_id":"cdd29a99-1dad-4ceb-a350-7bf51817f88c","resolution":{"observed_at":"2026-08-05T18:59:10.818852Z","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":"2026-08-05T18:59:10.420251Z","title":"Spot-the-difference self-supervised pre-training for anomaly detection and segmentation","venue":null,"work_id":"aca7e19d-bcd9-4dc0-8b6d-75ee1636ae37","year":2022},"citing_paper":{"arxiv_id":"2508.13560","last_updated":"2025-08-21T02:08:06Z","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-05T18:59:10.064175Z"},"links":{"citing_paper":"/paper/2508.13560"},"observation_digest":"sha256:b47f4ea0539789ae2797369791b5d96b3f5b44ed29347bc7f59b54cdb976bc39","observation_id":"cd0cf16b-4b82-480d-9878-6266f984f30d","resolution":{"observed_at":"2026-08-05T18:59:10.521673Z","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":"2508.13560","last_updated":"2025-08-21T02:08:06Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T10:51:54.193220Z","submitted_at":"2025-08-19T06:38:56Z","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":1,"verified_fuzzy":34},"total_outbound_references":44},"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 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2508.13560."}