{"as_of":"2026-08-11T01:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:456dcb94d6c5cfb1d80083fecb85408221d56abce145c2728864c3246692e107","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T14:30:29.473393Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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":"2026-08-10T14:30:29.270425Z","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":"2026-08-10T14:30:29.772103Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"cited_work":{"arxiv_id":"2501.15271","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.15271","snapshot_observed_at":"2026-08-10T14:30:29.772103Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","venue":"cs.LG","work_id":"448b4f27-7793-4c33-83a1-361407335078","year":2025},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.270425Z"},"links":{"cited_paper":"/paper/2501.15271","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:b17bd3180ee6cde9f4e93910a38cb7e1e475f45219a700138924b6be0c117f90","observation_id":"abdd564d-bbad-441a-8179-11e8bc7eb296","resolution":{"observed_at":"2026-08-10T14:30:29.779054Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.15271/citation-record","integrity":"/paper/2501.15271/integrity","json":"/paper/2501.15271/citation-record.json","paper":"/paper/2501.15271"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"cited_work":{"arxiv_id":"2501.15271","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.15271","snapshot_observed_at":"2026-08-10T14:30:29.772103Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","venue":"cs.LG","work_id":"448b4f27-7793-4c33-83a1-361407335078","year":2025},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.270425Z"},"links":{"cited_paper":"/paper/2501.15271","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:b17bd3180ee6cde9f4e93910a38cb7e1e475f45219a700138924b6be0c117f90","observation_id":"abdd564d-bbad-441a-8179-11e8bc7eb296","resolution":{"observed_at":"2026-08-10T14:30:29.779054Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:30.155768Z","title":"Various self-supervised approaches have been introduced in ND to learn the normal sample distribution","venue":null,"work_id":"4f9e915c-2f3b-455f-adaa-12f5425af54b","year":null},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.275638Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:b6377708af0376a00e0027abc9fb53f7602bc1f14acd2191a02748d1239d9d2d","observation_id":"981667e0-f26b-43b4-b6df-b1663fe11ca1","resolution":{"observed_at":"2026-08-10T14:30:30.160578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:30.125291Z","title":"In ND, our focus is on a specialized training set that comprises solely normal, unlabeled samples","venue":null,"work_id":"75ff4f03-3475-45d2-8884-8501d6cb31c0","year":null},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.285067Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:040db40de05fea1a981a5f1d821d429b6e81e1188971921da2c36da07b09cdc1","observation_id":"1c84a1d2-3a35-4bf7-ad83-2b663d396bcd","resolution":{"observed_at":"2026-08-10T14:30:30.130024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:30.110482Z","title":"Initialization: Feature Extraction Our methodology begins with the critical step of feature ex- traction, setting the stage for all downstream operations","venue":null,"work_id":"8962f1ae-d5e8-470a-a078-1e51478ec8ae","year":null},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.290064Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:f3107e4dfc4436ae6e8911bc53c9c173246011d60690be9d67b2cf4ccd9d7fac","observation_id":"362f25d1-a685-4713-a9c8-974976654898","resolution":{"observed_at":"2026-08-10T14:30:30.115533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:30.095013Z","title":null,"venue":null,"work_id":"adc63db1-0eaa-4b0b-892d-86f3bd0b34c2","year":null},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.295053Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:e17e17092ffa4555d974ef5500369d02484b4e467ce5024083fbd9d52e73b54d","observation_id":"7490cd58-3c05-4c99-973a-284caf2f296a","resolution":{"observed_at":"2026-08-10T14:30:30.100482Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:30.080046Z","title":"Our method performs well in AUROC metrics and strongly resists adversarial attacks","venue":null,"work_id":"325db9bb-7cf7-4034-b62a-149588ed37cd","year":null},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.299954Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:481d3fa0c962a397bcc2fef7462c982159b4c9b7601e70ceeeaa3d119d02c465","observation_id":"3c7b4e96-dcef-4c05-b91a-e54844b7c3df","resolution":{"observed_at":"2026-08-10T14:30:30.084955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:30.034974Z","title":"Deep neural networks are easily fooled: High confidence pre- dictions for unrecognizable images,","venue":null,"work_id":"8de57e6c-d6d8-4f7b-b9cb-89f89760a1a1","year":2015},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.334168Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:32b9b9fb207ed69d280cecfe2cfb6c9fd6874d1be0bbacbe6727785d1f892fbc","observation_id":"365a6758-068f-45dd-a219-ea5907f7598e","resolution":{"observed_at":"2026-08-10T14:30:30.039762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03844","last_updated":"2022-11-28T15:19:19Z","snapshot_observed_at":"2026-08-05T19:20:51.046468Z","submitted_at":"2021-06-07T17:58:03Z","title":"Mean-Shifted Contrastive Loss for Anomaly Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03844","snapshot_observed_at":"2026-08-10T14:30:29.305072Z","title":"Mean-shifted con- trastive loss for anomaly detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.305072Z"},"links":{"cited_paper":"/paper/2106.03844","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:38e7d93bf9c800237fff4f4a58186d4f73fa362095934fbcdd2c6967405c4258","observation_id":"eee2b0f3-b788-4569-bd68-8112eb02df9d","resolution":{"observed_at":"2026-08-10T14:30:29.305072Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.04185","last_updated":"2022-07-17T18:35:38Z","snapshot_observed_at":"2026-07-06T12:16:30.385490Z","submitted_at":"2021-12-08T09:21:31Z","title":"Transformaly -- Two (Feature Spaces) Are Better Than One","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.04185","snapshot_observed_at":"2026-08-10T14:30:29.310029Z","title":"Transformaly– two (feature spaces) are better than one,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.310029Z"},"links":{"cited_paper":"/paper/2112.04185","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:d47e18f8d1361d5077b1dfc961442f7ff085deb22935522e82e5703fd6eae256","observation_id":"4b753a99-95a7-4a3f-8539-923ea53f8c85","resolution":{"observed_at":"2026-08-10T14:30:29.310029Z","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":"2026-08-10T14:30:30.065187Z","title":"Ad- versarially robust one-class novelty detection,","venue":null,"work_id":"8b73d74b-a418-417b-b69c-cdbcf74f92dd","year":2022},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.315061Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:ecfc5f663ca76e40819081640b94fbca7d4e7d90e601ebcb646ccb948b8ca2e9","observation_id":"8605b80e-77e2-4cc3-8489-d039baed0f12","resolution":{"observed_at":"2026-08-10T14:30:30.069993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.01978","last_updated":"2024-04-01T20:01:10Z","snapshot_observed_at":"2026-07-06T14:58:21.855086Z","submitted_at":"2023-01-26T15:40:10Z","title":"Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.01978","snapshot_observed_at":"2026-08-10T14:30:29.319424Z","title":"Robust one-class classifica- tion with signed distance function using 1-lipschitz neu- ral networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.319424Z"},"links":{"cited_paper":"/paper/2303.01978","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:5e313e5557b0bd208451f10045d477019663867118495c5eb76c8330d8c5d317","observation_id":"72cb72ea-2d88-4cf8-947a-ac54973daa1f","resolution":{"observed_at":"2026-08-10T14:30:29.319424Z","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":"2026-08-10T14:30:30.049779Z","title":"Robustness of autoencoders for anomaly detection under adversarial impact,","venue":null,"work_id":"95013d91-8323-4542-962a-b0bab2f717fc","year":2021},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.324130Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:8967cdcc305afe3b5d073d2d0c154149629c44f0596e4a0a2ad60b756717712f","observation_id":"3f442d91-8b04-42a9-9c23-78eb2db7dc74","resolution":{"observed_at":"2026-08-10T14:30:30.054283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.03064","last_updated":"2021-01-08T15:30:29Z","snapshot_observed_at":"2026-08-06T20:01:49.861435Z","submitted_at":"2021-01-08T15:30:29Z","title":"One-Class Classification: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.03064","snapshot_observed_at":"2026-08-10T14:30:29.329333Z","title":"One-class classification: A survey,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.329333Z"},"links":{"cited_paper":"/paper/2101.03064","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:549c9a852a9cc4f4bb102b5f642d0eb288997e8fe93893ab04185f0e23a18061","observation_id":"2ca85b56-e7ec-4862-80aa-2550193da593","resolution":{"observed_at":"2026-08-10T14:30:29.329333Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.10445","last_updated":"2020-02-24T18:51:33Z","snapshot_observed_at":"2026-08-09T15:59:42.376249Z","submitted_at":"2020-02-24T18:51:33Z","title":"Deep Nearest Neighbor Anomaly Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.10445","snapshot_observed_at":"2026-08-10T14:30:29.368186Z","title":"Deep nearest neighbor anomaly detection,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.368186Z"},"links":{"cited_paper":"/paper/2002.10445","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:e0651df75b8215d2885af7f6068b26562b3abac213eee87a0bcb1353267b6d40","observation_id":"5b6b22fe-d5b6-41bc-bb69-17d191f9a3db","resolution":{"observed_at":"2026-08-10T14:30:29.368186Z","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":"2026-08-10T14:30:30.019866Z","title":"Mvtec ad–a comprehensive real-world dataset for unsupervised anomaly detection,","venue":null,"work_id":"369888eb-a699-44ec-9ff9-49c63d62891e","year":2019},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.338877Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:210dfb5ae4a400a73b3fb24e2afb35fec65d45b20bbec44398e1554bfb33324d","observation_id":"0d665660-5e41-4b29-8069-fe4c665eea0f","resolution":{"observed_at":"2026-08-10T14:30:30.024734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.14535","last_updated":"2024-02-08T18:38:30Z","snapshot_observed_at":"2026-07-06T15:08:00.868057Z","submitted_at":"2023-03-25T18:48:33Z","title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.14535","snapshot_observed_at":"2026-08-10T14:30:29.343552Z","title":"Efficientad: Accurate visual anomaly detection at millisecond-level latencies,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.343552Z"},"links":{"cited_paper":"/paper/2303.14535","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:4747d507bb74c65499b275cbe2149392ac1ac903f020cabb20755f07a8f73a79","observation_id":"7d342865-ec42-46e0-8ad7-ea6a2c9eeced","resolution":{"observed_at":"2026-08-10T14:30:29.343552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14051","last_updated":"2022-12-03T15:10:18Z","snapshot_observed_at":"2026-07-06T12:02:19.650098Z","submitted_at":"2021-10-26T22:05:31Z","title":"A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14051","snapshot_observed_at":"2026-08-10T14:30:29.348421Z","title":"A unified survey on anomaly, novelty, open-set, and out-of-distribution detection: Solutions and future challenges,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.348421Z"},"links":{"cited_paper":"/paper/2110.14051","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:b63527323a31730bb9815002e97fc633add9729b40fabfdc5e8214c2a73d3350","observation_id":"21a54cac-189e-4d82-911c-b55fb5736950","resolution":{"observed_at":"2026-08-10T14:30:29.348421Z","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":"2026-08-10T14:30:30.005102Z","title":"Papajorgji, and Panos M","venue":null,"work_id":"21d03727-df53-40cb-91ff-ff09aeb0e48c","year":2009},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.353824Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:050d5c93eb8448381b4b5eb7486d2096e702d5377a587f9de897347c829c607c","observation_id":"8ccdb676-5b29-49ab-8484-1b96d078817d","resolution":{"observed_at":"2026-08-10T14:30:30.009580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:29.989704Z","title":"Csi: Novelty detection via contrastive learning on distributionally shifted instances,","venue":null,"work_id":"869ed5a8-c0cf-4e7a-b6c9-63223af2eb0a","year":2020},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.358729Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:80c7c23122dac5c5754973c938d3fca3178f73669924f5738444ac3858684048","observation_id":"c4eab3a0-2c79-4506-aabf-d7d825836509","resolution":{"observed_at":"2026-08-10T14:30:29.994552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.14297","last_updated":"2022-11-28T20:58:52Z","snapshot_observed_at":"2026-07-31T21:45:01.723738Z","submitted_at":"2022-05-28T02:02:53Z","title":"Fake It Till You Make It: Towards Accurate Near-Distribution Novelty Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.14297","snapshot_observed_at":"2026-08-10T14:30:29.363163Z","title":"Fake it till you make it: Near-distribution novelty detec- tion by score-based generative models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.363163Z"},"links":{"cited_paper":"/paper/2205.14297","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:2c5580faf7c1fc8fed20ee12cdfa641b24d6fff8a4b388e709fd242e50f99489","observation_id":"348b51e7-edc2-484a-8cc4-13d7d9b8ff43","resolution":{"observed_at":"2026-08-10T14:30:29.363163Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.09952","last_updated":"2023-10-15T21:07:09Z","snapshot_observed_at":"2026-07-06T16:33:26.145691Z","submitted_at":"2023-10-15T21:07:09Z","title":"Seeking Next Layer Neurons' Attention for Error-Backpropagation-Like Training in a Multi-Agent Network Framework","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.09952","snapshot_observed_at":"2026-08-10T14:30:29.402441Z","title":"Seeking next layer neu- rons’ attention for error-backpropagation-like training in a multi-agent network framework,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.402441Z"},"links":{"cited_paper":"/paper/2310.09952","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:47e27ae65dd57720fa9347c381cf82704b240606384893adc0d7e84ae11af63f","observation_id":"e1523143-12f0-4aa0-aa20-7024ec46dfda","resolution":{"observed_at":"2026-08-10T14:30:29.402441Z","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":"2026-08-10T14:30:29.974689Z","title":"Panda: Adapting pretrained features for anomaly detection and segmentation,","venue":null,"work_id":"8975fa94-7dc8-41f3-9429-c0b14646cf45","year":2021},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.373801Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:031785061d5e1db44ae535ef71f6817350a38ed831f699abe3f0365065c5e942","observation_id":"4e5bb389-be00-401b-bcfe-3fc864133b3b","resolution":{"observed_at":"2026-08-10T14:30:29.979829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:29.960212Z","title":"Open-set adversarial defense with clean-adversarial mutual learning,","venue":null,"work_id":"665d180f-c9e8-47de-ab5f-52654b731030","year":null},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.378127Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:cbbd8bc99e96ac1465f6dff0328a5a00333bf6bfcbbe6440e675e8360f25b3bc","observation_id":"91c6cec6-88d7-43a9-97bb-8abc4baa75c9","resolution":{"observed_at":"2026-08-10T14:30:29.964954Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:29.945661Z","title":"Rodeo: Robust outlier detection via ex- posing adaptive out-of-distribution samples,","venue":null,"work_id":"3d815720-c584-4570-9fd2-1ca3ce459d9e","year":null},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.382486Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:b46f9afa100978110f01123119be89ffb96f3cd54be51246422bba192674dea0","observation_id":"d0a73ce8-e0e9-49dd-bcd9-8f243af79c99","resolution":{"observed_at":"2026-08-10T14:30:29.950674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10744","last_updated":"2025-01-26T17:35:40Z","snapshot_observed_at":"2026-07-06T19:33:12.610676Z","submitted_at":"2024-10-14T17:22:12Z","title":"Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10744","snapshot_observed_at":"2026-08-10T14:30:29.387333Z","title":"Ad- versarially robust out-of-distribution detection using lyapunov-stabilized embeddings,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.387333Z"},"links":{"cited_paper":"/paper/2410.10744","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:33a366ffe84f676af3e3d0b0050aee4e1c3c488a3f99d1b1a5a698a589739677","observation_id":"a809b81b-f8ba-4417-a93f-f32c870f406d","resolution":{"observed_at":"2026-08-10T14:30:29.387333Z","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":"2026-08-10T14:30:29.929433Z","title":"Universal novelty detection through adaptive contrastive learning,","venue":null,"work_id":"bdeee2e4-ed58-477d-89a4-20788149db14","year":2024},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.393056Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:d36b14452f65d301193ba99312a8bcc703987910de87738bef5c6773280dd7bd","observation_id":"cb0ab26f-ba95-4a2e-b5c6-aa5e7bbff0f5","resolution":{"observed_at":"2026-08-10T14:30:29.934183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:29.914016Z","title":"Scanning trojaned models using out- of-distribution samples,","venue":null,"work_id":"0dc555c0-3809-4fab-88c9-92db4de8647c","year":null},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.397691Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:33e4b26edb5ac223632d80cce20583beb57c973b838f8dee08994f94927175db","observation_id":"d6bfb1e7-0dd4-4379-8dcd-ac9554dc432f","resolution":{"observed_at":"2026-08-10T14:30:29.919064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.11774","last_updated":"2024-07-16T14:33:01Z","snapshot_observed_at":"2026-07-06T18:47:13.029539Z","submitted_at":"2024-07-16T14:33:01Z","title":"Sharif-MGTD at SemEval-2024 Task 8: A Transformer-Based Approach to Detect Machine Generated Text","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.11774","snapshot_observed_at":"2026-08-10T14:30:29.435947Z","title":"Sharif- mgtd at semeval-2024 task 8: A transformer-based ap- proach to detect machine generated text,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.435947Z"},"links":{"cited_paper":"/paper/2407.11774","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:4f7837b8efb53c752a50a00674b61232518fad8a4a63e2e044738041be5d0091","observation_id":"9e4e3008-1f68-4f90-92b1-95dee6b790d5","resolution":{"observed_at":"2026-08-10T14:30:29.435947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.11584","last_updated":"2023-07-21T13:48:11Z","snapshot_observed_at":"2026-07-06T15:56:57.247160Z","submitted_at":"2023-07-21T13:48:11Z","title":"A Change of Heart: Improving Speech Emotion Recognition through Speech-to-Text Modality Conversion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.11584","snapshot_observed_at":"2026-08-10T14:30:29.407338Z","title":"A change of heart: Improving speech emotion recogni- tion through speech-to-text modality conversion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.407338Z"},"links":{"cited_paper":"/paper/2307.11584","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:f3d8e3ea4de890dce41be506cd43b9022b6b32eb2a0da7d6e6fee64b4fcad46c","observation_id":"12d0b69a-165f-48f3-b84a-95a21d692f87","resolution":{"observed_at":"2026-08-10T14:30:29.407338Z","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":"2026-08-10T14:30:30.140779Z","title":"During each itera- tion, the adversarial noise is constrained within an ℓ∞-ball of radius ϵ: x∗ 0 = x, x∗ t+1 = x∗ t + α","venue":null,"work_id":"ad5f6e66-469b-4e77-b294-4f7ce51eae0b","year":null},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.280398Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:64f98c5d21d0a51ae2795d94a99bc33bf548867452e0796827daf4e113449e70","observation_id":"f3074691-9785-468d-8550-d1fe7ced2a88","resolution":{"observed_at":"2026-08-10T14:30:30.145787Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:29.898802Z","title":"HalluSafe at SemEval-2024 task 6: An NLI-based approach to make LLMs safer by better detecting hallucinations and over- generation mistakes,","venue":null,"work_id":"929d46f3-2750-43f2-b234-8302f159d9e5","year":2024},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.412224Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:7cee4f1a5209060867ffdcd78a1cfd9b031dbf50a642257e5ce93a4f1766a577","observation_id":"ec9401d0-daa7-4450-a1c3-b03e0941e384","resolution":{"observed_at":"2026-08-10T14:30:29.903899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.10354","last_updated":"2023-08-20T20:10:55Z","snapshot_observed_at":"2026-07-06T16:08:17.076884Z","submitted_at":"2023-08-20T20:10:55Z","title":"Imaginations of WALL-E : Reconstructing Experiences with an Imagination-Inspired Module for Advanced AI Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.10354","snapshot_observed_at":"2026-08-10T14:30:29.417005Z","title":"Imaginations of wall- e: Reconstructing experiences with an imagination- inspired module for advanced ai systems,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.417005Z"},"links":{"cited_paper":"/paper/2308.10354","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:7b9c1e869f4c55c5e55a5a5dad6218e485b4c93ff5870b02d441d5ee3fceea82","observation_id":"c4202e55-9382-4f6c-b3f5-528ffd7f90be","resolution":{"observed_at":"2026-08-10T14:30:29.417005Z","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":"2026-08-10T14:30:29.883161Z","title":"Ebhaam at SemEval-2023 task 1: A CLIP-based approach for com- paring cross-modality and unimodality in visual word sense disambiguation,","venue":null,"work_id":"10012c22-a9a1-4a18-8d3b-7eb38fd4925e","year":2023},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.421893Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:6088af80b0f8a49c3b13b1ab6827c74a65f890cc8549a03b05baf70caa19c0d8","observation_id":"52151135-db61-4cb8-9b9f-35c4b3fb907c","resolution":{"observed_at":"2026-08-10T14:30:29.888162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.05010","last_updated":"2024-12-06T13:03:22Z","snapshot_observed_at":"2026-08-04T04:00:51.163736Z","submitted_at":"2024-12-06T13:03:22Z","title":"Backdooring Outlier Detection Methods: A Novel Attack Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.05010","snapshot_observed_at":"2026-08-10T14:30:29.426409Z","title":"Backdoor- ing outlier detection methods: A novel attack approach,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.426409Z"},"links":{"cited_paper":"/paper/2412.05010","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:de4ee00f76b34e51f2c2af1c4af9572486652561a1d389430410a82641d961a0","observation_id":"9ae65b69-bb3c-4ef2-bdee-529ea571e934","resolution":{"observed_at":"2026-08-10T14:30:29.426409Z","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":"2026-08-10T14:30:29.868093Z","title":"NIMZ at SemEval-2024 task 9: Evaluating methods in solving brainteasers de- fying commonsense,","venue":null,"work_id":"4b44e4d2-1f47-467a-b2a3-ff0b4c7ca8db","year":2024},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.431299Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:cb4429a195eb376ff0bcc5e5d7319b953b0f3ff2f4f9860540de135cc2adf8a6","observation_id":"3265cf2d-01eb-48e5-af05-41b1cda8dcef","resolution":{"observed_at":"2026-08-10T14:30:29.873356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.12426","last_updated":"2024-07-17T09:25:18Z","snapshot_observed_at":"2026-07-06T18:47:42.757727Z","submitted_at":"2024-07-17T09:25:18Z","title":"Sharif-STR at SemEval-2024 Task 1: Transformer as a Regression Model for Fine-Grained Scoring of Textual Semantic Relations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.12426","snapshot_observed_at":"2026-08-10T14:30:29.440759Z","title":"Sharif-str at semeval- 2024 task 1: Transformer as a regression model for fine- grained scoring of textual semantic relations,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.440759Z"},"links":{"cited_paper":"/paper/2407.12426","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:c62bfa9da6f69c3813c4b6ff3fa5bdc364d1d2b5e0aecc837b97a9e32647cb6e","observation_id":"e06e9334-58b6-4663-891b-3b640c3fbf88","resolution":{"observed_at":"2026-08-10T14:30:29.440759Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-10T14:30:29.446038Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.446038Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:d93d045753dddfafa8da7109717cb1a2a7633de6ab9d32ab57fdc41c154b61bc","observation_id":"d6bad4ba-3943-4929-a180-c8e0c86a8515","resolution":{"observed_at":"2026-08-10T14:30:29.446038Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.08489","last_updated":"2020-12-08T01:56:10Z","snapshot_observed_at":"2026-08-08T14:51:59.750738Z","submitted_at":"2020-07-16T17:42:40Z","title":"Do Adversarially Robust ImageNet Models Transfer Better?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.08489","snapshot_observed_at":"2026-08-10T14:30:29.450912Z","title":"Do adversarially ro- bust imagenet models transfer better?,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.450912Z"},"links":{"cited_paper":"/paper/2007.08489","citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:a0ade9259a0d35cf17672b89b7988aac6985fc2082c6c10bde2ec102068ff91c","observation_id":"221fd680-a00d-44c8-832c-604c11fbe910","resolution":{"observed_at":"2026-08-10T14:30:29.450912Z","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":"2026-08-10T14:30:29.852030Z","title":"Reliable eval- uation of adversarial robustness with an ensemble of diverse parameter-free attacks,","venue":null,"work_id":"58b5f099-f194-4c56-aaa1-a29eee9f9acf","year":2020},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.455350Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:de324360b6fd33d3190749fd3cca609affcebd1a64e26ebdc0932e846679c422","observation_id":"4833102f-2b55-47c6-9579-e50872059f75","resolution":{"observed_at":"2026-08-10T14:30:29.857137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:29.837270Z","title":"Head ct - hemorrhage,","venue":null,"work_id":"afbb3006-3e8e-43a9-9a8d-7194651d1813","year":null},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.459881Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:4bf695059d565740d1ff3b359fd70e7513b60734c0499a851f1362bbef387b1c","observation_id":"e6f7bed6-b326-49b0-837e-9573870a7b09","resolution":{"observed_at":"2026-08-10T14:30:29.841922Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:29.821807Z","title":"Brain tumor clas- sification (mri),","venue":null,"work_id":"36ee07ef-c79c-458b-be5a-9f7e6f9a949f","year":2020},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.464428Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:160b1865bb143dbf3cb6d8c1580cb6c6e6c9f361edd9be37f4bd445a51838128","observation_id":"8d1599a8-6a94-4f9e-b00e-4647032ef809","resolution":{"observed_at":"2026-08-10T14:30:29.826762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:29.805934Z","title":"Covid-19 image data collection,","venue":null,"work_id":"6585f810-572e-41c8-94ec-a9e2e8894271","year":2020},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.468835Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:f84888e2069d9c719726b910c852fb750f6bf0fb2c59c712deb48ef994d7f756","observation_id":"671afdb8-93bc-44d6-a969-8751b3aafe1f","resolution":{"observed_at":"2026-08-10T14:30:29.810611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T14:30:29.790507Z","title":"Brain tumor mri dataset,","venue":null,"work_id":"3aa58827-3243-4629-868a-b60505bbed73","year":2021},"citing_paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T14:30:29.473393Z"},"links":{"citing_paper":"/paper/2501.15271"},"observation_digest":"sha256:e8e43743dc3ebad7bbf7eb73b44164ef2ba127eb7e1074e76f3fb4d5bf7fb523","observation_id":"4d6e2143-a9ea-4d4c-9c06-893888607d6e","resolution":{"observed_at":"2026-08-10T14:30:29.795375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.15271","last_updated":"2025-01-25T16:44:47Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T14:24:28.193256Z","submitted_at":"2025-01-25T16:44:47Z","title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":17,"verified_exact":0,"verified_fuzzy":24},"total_outbound_references":43},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 1 inbound Pith citation observation for arXiv:2501.15271."}