{"as_of":"2026-08-08T23:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7cf8a99b5824d25674eea1a27c516c160bfa3983198f95c56e1dfd2ca015ac4c","coverage":[{"denominator":55,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":55,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:55:55.795518Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.09399/citation-record","integrity":"/paper/2506.09399/integrity","json":"/paper/2506.09399/citation-record.json","paper":"/paper/2506.09399"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:55:56.195615Z","title":"H., Park, G.-M., and Kim, S","venue":null,"work_id":"676d783b-f3e7-4a89-b818-baa8c280a2b2","year":2023},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.686412Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:7c4db5315c0debf19591a09d252befa9da13e724c5b5a740eb5acfd9fd83b67a","observation_id":"ca5d1e09-42f6-4656-97a0-b6c57aa6dabd","resolution":{"observed_at":"2026-08-07T04:55:56.198156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.189254Z","title":"B., Belkhir, N., Popescu, S., Manzanera, A., and Franchi, G","venue":null,"work_id":"641fe870-d91d-48ae-a27e-98c06589ed6f","year":2024},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.689301Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:0967adc08a42d18a8e30cfb8346d5e758c4aad418c948460950446be032896ef","observation_id":"224028d6-8be6-454f-b2d3-4c0c9fe2072a","resolution":{"observed_at":"2026-08-07T04:55:56.191530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.182827Z","title":"Scaling out-of-distribution detection for real-world settings","venue":null,"work_id":"636bbfef-fd3f-4213-93eb-54ab2594140d","year":2022},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.691498Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:b53f2004bbec24ae2db9bdddab6f596bb0c625a24b32e260fec52bd48d17f3bb","observation_id":"5e893325-6e3f-4a1e-a97f-2a1f3f891b61","resolution":{"observed_at":"2026-08-07T04:55:56.185088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.176385Z","title":"L., Li, X., He, W., Gou, L., and Ren, L","venue":null,"work_id":"6a5a40d6-8bce-43b3-98c6-904d9952d723","year":2023},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.693899Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:0c59b400ded91ed8e5b6629fd0129450786d6cfd5ea136404ab68bec4e8796b9","observation_id":"ff4167f3-e23b-445b-b48b-d68d80caf1c6","resolution":{"observed_at":"2026-08-07T04:55:56.178536Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:55.696182Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.696182Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:ad339b9b151c376566e0e99a52e0f04f016e8726e6367c95be6d9274504cec0b","observation_id":"1b0ce6e2-f1a9-46ef-8c62-16208ea0c6f8","resolution":{"observed_at":"2026-08-07T04:55:55.696182Z","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":"2026-08-07T04:55:56.166158Z","title":"Atom: Robustifying out-of-distribution detection using outlier mining","venue":null,"work_id":"12a54312-d6b5-408f-b852-28aab8d91534","year":2021},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.698460Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:73a4fe750fdb36ea1430f2fdaf973cb120f79d7a5abf81fa87a5f3ef7f003aac","observation_id":"51fa2765-c9b6-4d1b-911f-95fc22a10a46","resolution":{"observed_at":"2026-08-07T04:55:56.168597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.159989Z","title":null,"venue":null,"work_id":"dbd0d228-9026-40b9-aa32-636ee311fdf2","year":2023},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.700707Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:87c1918073822c25d660f988d3d842d4859debb3e10af05cd3b4964b00dcfd9c","observation_id":"5d7f6583-606a-442b-9fbd-2034d54fdab3","resolution":{"observed_at":"2026-08-07T04:55:56.162081Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.153544Z","title":"Describing textures in the wild","venue":null,"work_id":"614db4e5-3ff5-4c33-86e4-1ce099b4cb3d","year":2014},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.702774Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:7c1d10c4ecb627b0ee44b2554f1ae186a08d294bae0eeaa9e2aa6bad4fde051e","observation_id":"6d6d7f82-a2f4-4bde-950e-779d6ab13594","resolution":{"observed_at":"2026-08-07T04:55:56.155905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:55.704739Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.704739Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:691d83fd9f878b9d3b0b64e548cae17b86fecd000320a4dd7bdca7b2aee7b265","observation_id":"9ed1b652-331a-4b0a-abd8-dca2f2fcbbcd","resolution":{"observed_at":"2026-08-07T04:55:55.704739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.04865","last_updated":"2018-02-13T21:31:36Z","snapshot_observed_at":"2026-07-06T06:23:16.798440Z","submitted_at":"2018-02-13T21:31:36Z","title":"Learning Confidence for Out-of-Distribution Detection in Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.04865","snapshot_observed_at":"2026-08-07T04:55:55.706718Z","title":"and Taylor, G","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.706718Z"},"links":{"cited_paper":"/paper/1802.04865","citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:d305c7adfee126c1ca376a62cecbcf1215851ca998eebcd903f2910890dda73b","observation_id":"e56565a3-371d-4dcb-ae08-cc87e40cdb3c","resolution":{"observed_at":"2026-08-07T04:55:55.706718Z","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":"2026-08-07T04:55:55.709030Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.709030Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:d393eda0e6f6447f96b22cefc3e47a860ceb912720d47177f7b63a79c921869a","observation_id":"c76d72e7-ac6b-4f48-b3a2-12ca703c90ca","resolution":{"observed_at":"2026-08-07T04:55:55.709030Z","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":"2312.14427","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:55:55.912595Z","title":"Grood: Gradient-aware out-of-distribution detection in interpolated manifolds","venue":null,"work_id":"21fcdc7b-7c10-46e4-96b4-385c224fb310","year":2023},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.711136Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:ecc55eababa77ce4f6483ac40858594d8f4430522b61008130f2b753a45a427f","observation_id":"561b43d7-a65b-4eb6-92c2-88a8856c3180","resolution":{"observed_at":"2026-08-07T04:55:55.918020Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.139205Z","title":"Can autonomous vehicles identify, recover from, and adapt to distribution shifts? In International Conference on Machine Learning, pp.\\ 3145--3153","venue":null,"work_id":"ed5b4aba-6fb7-4823-a087-bd1efeb2134c","year":2020},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.713009Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:61dac21b1a85a23dd9ea3b740701532e412981daa27b43e50d19ab5e90d391f2","observation_id":"5bacf770-39cf-4328-a019-940d42d448a8","resolution":{"observed_at":"2026-08-07T04:55:56.141706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.132616Z","title":"Evidence reconciled neural network for out-of-distribution detection in medical images","venue":null,"work_id":"bed24c03-2660-4ff3-80c0-bd55436aed0c","year":2023},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.714870Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:87995a3c72796e77481eae7f10c592d9246e1c8baabad2253ec00bae6e911067","observation_id":"15baafca-12c2-46db-bf3b-e32795b97a5c","resolution":{"observed_at":"2026-08-07T04:55:56.134932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.126174Z","title":null,"venue":null,"work_id":"6dc5e26d-8751-47c7-ab6c-5c1b8a7b9372","year":2023},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.716775Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:ba543a5aa0b8115a7fcbccd7663d5e8c38ca79e4ce6b4aa012e5f5b637f22e7b","observation_id":"8e052846-7357-4ce4-8d5f-2d48a2d2e08e","resolution":{"observed_at":"2026-08-07T04:55:56.128480Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.119788Z","title":"A survey on vision transformer","venue":null,"work_id":"72f247cc-efad-4b37-945c-b3c947245bad","year":2022},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.718675Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:af132a96e8b115758f25a40da361c8786ed3560ddfcbdbcf6106fa969771de78","observation_id":"4ce8b998-14b6-4d0b-9937-5611a62ce81f","resolution":{"observed_at":"2026-08-07T04:55:56.122078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:55.720628Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.720628Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:8bf42ca8ff6a1528a280261441b48d92ce4333a6924b24003759b39da5853986","observation_id":"7335cb59-1243-4b14-afa5-7bc4dd650a81","resolution":{"observed_at":"2026-08-07T04:55:55.720628Z","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":"2026-08-07T04:55:56.109224Z","title":"Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem","venue":null,"work_id":"71d86324-2585-4789-b2ed-eb68319a30e8","year":2019},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.722536Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:9249fbfb868ef0ec80defa066af81c678003ee8e88a1f1b27e82e1a24cea6587","observation_id":"c3090ad2-74c6-492e-a76c-3d27093884cf","resolution":{"observed_at":"2026-08-07T04:55:56.111637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.103075Z","title":"and Gimpel, K","venue":null,"work_id":"83460b63-41ef-4fec-8d9e-75bed3e5f6c4","year":2017},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.724431Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:d0510b885238580d2198b666a1baedab7d66caa92ed75be6ee8767c8b8ef96aa","observation_id":"7ea32554-cc58-4937-af89-6a34954079da","resolution":{"observed_at":"2026-08-07T04:55:56.105305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.096527Z","title":"Natural adversarial examples","venue":null,"work_id":"d52bb75c-2072-4894-bf53-59f74c8b3a03","year":2021},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.726402Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:3d2ae1f927c55d7efd7113bf40a3b38d5a796ceec790eff9fb8e09086805a7cf","observation_id":"02b06b53-10ed-46db-b05a-60268105c572","resolution":{"observed_at":"2026-08-07T04:55:56.098934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.089965Z","title":"Pixmix: Dreamlike pictures comprehensively improve safety measures","venue":null,"work_id":"0c721bf1-e03d-4bfb-a7cf-73383aac37f9","year":2022},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.728299Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:b18598e83c5e3e89162cb5130bd56ff14b5936e961325f3f227d26dface8357b","observation_id":"37c0b2cc-c18e-4b85-8ac3-570f2f666bb4","resolution":{"observed_at":"2026-08-07T04:55:56.092289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.083681Z","title":"and Li, Y","venue":null,"work_id":"ceeae44a-7f38-4cb7-9cf4-80a14abb193e","year":2021},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.730191Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:0dec3006854470f11e51e7ae5f40e590f687fbd2f01422071bcbcd2822d864c4","observation_id":"25405d7e-7afa-44f7-a8b6-c57d4f5b321d","resolution":{"observed_at":"2026-08-07T04:55:56.085784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.077297Z","title":"On the importance of gradients for detecting distributional shifts in the wild","venue":null,"work_id":"ae3b4a3c-7b2d-4b32-99de-4f4c81c3d0f2","year":2021},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.732142Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:b00b7e35598eb46530f3623a11b678a18f4d7bfab588938d157eb112d942ce05","observation_id":"680b4994-3bf8-4faf-9f9c-bf5f33b99160","resolution":{"observed_at":"2026-08-07T04:55:56.079587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.070346Z","title":"Enhancing camera surveillance using computer vision: a research note","venue":null,"work_id":"bede83c9-9bd8-4acf-b53f-b09ac9dc4a01","year":2018},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.733988Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:1e0785aa340c53a3b917d032b62247b7b5a6bd2b5622e47d781d2968d22aef42","observation_id":"6d4747e8-937d-4a25-9a2a-46dca3872f1f","resolution":{"observed_at":"2026-08-07T04:55:56.072726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.063913Z","title":"Openimages: A public dataset for large-scale multi-label and multi-class image classification","venue":null,"work_id":"13a66ecf-20f3-4949-a6b6-a020b4c7d16a","year":2017},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.735858Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:78de9ea88095466ab151c8ace5c8b63118262ae731ea9cb756f0674541470dda","observation_id":"c4eb67e9-f653-49ab-9d8b-8e7f5ac329be","resolution":{"observed_at":"2026-08-07T04:55:56.066298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:55.737730Z","title":"Crafting papers on machine learning","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.737730Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:12c39c6a83a79f2e13536b216ac16ab237e82fc0ee650a6471d01a3d9e9083ba","observation_id":"179677a5-99d6-490a-b657-c13f83164ae3","resolution":{"observed_at":"2026-08-07T04:55:55.737730Z","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":"2026-08-07T04:55:55.739567Z","title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.739567Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:d1ebb130612901bd6f0a1c59eef3da0fd99fd6af6a457f0bdc1441f87505cb71","observation_id":"0bfdcf92-16ae-439f-8b77-573e2c103b36","resolution":{"observed_at":"2026-08-07T04:55:55.739567Z","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":"2026-08-07T04:55:56.049507Z","title":"Enhancing the reliability of out-of-distribution image detection in neural networks","venue":null,"work_id":"6eb32337-06b7-4167-8d2a-5dc895bde11f","year":2018},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.741581Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:7aef2fe5e3fae2b5ced008bfd26a91acff752567aa050c0a3be9a51bb91a0a79","observation_id":"b28045bd-e854-4712-85e0-efe6eda9b1da","resolution":{"observed_at":"2026-08-07T04:55:56.051822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11536","last_updated":"2024-06-04T16:01:27Z","snapshot_observed_at":"2026-07-06T17:04:50.608413Z","submitted_at":"2023-12-15T19:50:32Z","title":"Fast Decision Boundary based Out-of-Distribution Detector","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11536","snapshot_observed_at":"2026-08-07T04:55:55.743522Z","title":"and Qin, Y","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.743522Z"},"links":{"cited_paper":"/paper/2312.11536","citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:8014418f4151c783c25cdfd9cc814fab09be33b19b272e0b80066c589b2361f8","observation_id":"3361e836-23f4-4643-b1af-0d8128c4f1ff","resolution":{"observed_at":"2026-08-07T04:55:55.743522Z","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":"2026-08-07T04:55:56.043283Z","title":"Energy-based out-of-distribution detection","venue":null,"work_id":"5794aa9c-044b-4e58-940a-74ac2b774b5e","year":2020},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.745899Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:49fdd8d5457662aa9667edf34bdfcc4d5b8b7e9ea3e43349ccaf1ecd167f0e04","observation_id":"36f5011c-24ee-4316-8413-1ffa56cffe76","resolution":{"observed_at":"2026-08-07T04:55:56.045510Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.036835Z","title":"and Li, Y","venue":null,"work_id":"92f0a91e-7499-4c4d-8686-932d1475ca10","year":2022},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.747933Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:15e51e1881df8dfaf33c0947ebd039d20c229ea9a335c2c0f7acb322b3261923","observation_id":"45c31aef-1f7e-4e69-9795-849f068c7f02","resolution":{"observed_at":"2026-08-07T04:55:56.039059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.030435Z","title":"Y., et al","venue":null,"work_id":"f2829b9b-01d3-488b-80bc-1d60d2e0a7c5","year":2011},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.749736Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:fc465c48882758b1b861e65fe49feb53472d08d9b7b3e89da0d87fa225006197","observation_id":"d0b09e33-ac49-4d4c-aa1b-091023bee8d8","resolution":{"observed_at":"2026-08-07T04:55:56.032564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.023756Z","title":"Boundary-aware backward-compatible representation via adversarial learning in image retrieval","venue":null,"work_id":"cf61d63e-b5b2-4861-b892-1e1db9e573e1","year":2023},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.751614Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:e256e78a0e03f323de38769c4f79efc978a29ae356b9fae1de57aa103bd5737a","observation_id":"506c8392-3c75-4d15-9fe5-79b0dadca7ec","resolution":{"observed_at":"2026-08-07T04:55:56.026229Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:55.753464Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.753464Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:5974850f5e579525078d79c5f7ee1512bed679baa1930c72fbf73d2252e2d8ed","observation_id":"8851acf2-e44b-48e7-9154-bd0b9e89be96","resolution":{"observed_at":"2026-08-07T04:55:55.753464Z","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":"2026-08-07T04:55:56.013290Z","title":"Conjnorm: Tractable density estimation for out-of-distribution detection","venue":null,"work_id":"a65f1e50-ac12-4e16-bc85-4245cc44f2af","year":2024},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.755342Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:09d301c07e023fb29d6f3da9f210e55f9d516e03638cc062c81d29994744df29","observation_id":"e9b2b4c0-93be-468d-a5bd-3201a2c19ef5","resolution":{"observed_at":"2026-08-07T04:55:56.015613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:56.006351Z","title":"I., and Strapasson, J","venue":null,"work_id":"fa82966b-a24a-4441-aa14-a6ee307e838d","year":2019},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.757350Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:6b0f4240f367960ca61a25d302553147c579d5f9f0870f29bb9847b1f3673514","observation_id":"796d0600-9eb2-4651-8ffb-e5fe18298ea1","resolution":{"observed_at":"2026-08-07T04:55:56.009125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09022","last_updated":"2021-06-16T20:43:56Z","snapshot_observed_at":"2026-08-06T04:13:23.160399Z","submitted_at":"2021-06-16T20:43:56Z","title":"A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09022","snapshot_observed_at":"2026-08-07T04:55:55.759393Z","title":"G., Padhy, S., and Lakshminarayanan, B","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.759393Z"},"links":{"cited_paper":"/paper/2106.09022","citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:a41c404dd3ce47c52265f4faaaf489b5b4c3de087849bd8552af4b96b0d632ba","observation_id":"bed4b6a1-f3dc-4fa1-932a-bede5c0c88d1","resolution":{"observed_at":"2026-08-07T04:55:55.759393Z","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":"2026-08-07T04:55:55.999579Z","title":"\\ SSD \\ : A unified framework for self-supervised outlier detection","venue":null,"work_id":"301fa185-60d5-4e6a-b01e-034ea4cc11dd","year":2021},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.761505Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:4d1687dfc58f62f5ed6cc1774ae36fb204a95f29fe0a1d4f5f7465934558ade4","observation_id":"dd447961-f348-4813-8a38-6d40b7461a34","resolution":{"observed_at":"2026-08-07T04:55:56.002110Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:55.763455Z","title":"and Li, Y","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.763455Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:ee2cad54fd2ec1d7e601fc292a2cf29f946ea01f2428294ab1ddb1251ca093d4","observation_id":"da8456ad-9ff3-4b93-a1e1-83a9ec81319c","resolution":{"observed_at":"2026-08-07T04:55:55.763455Z","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":"2026-08-07T04:55:55.765233Z","title":"React: Out-of-distribution detection with rectified activations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.765233Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:b4297ce8c5e57d540c729cbd04bcfd8a16142a06933959792e4cfc09c208cd7c","observation_id":"cf63069e-711a-4425-af0a-76a494d934b1","resolution":{"observed_at":"2026-08-07T04:55:55.765233Z","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":"2026-08-07T04:55:55.767110Z","title":"Out-of-distribution detection with deep nearest neighbors","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.767110Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:5fd59935e740fd866366b7f1edb263dd21cb4240a6f9fe76365f5bf5985b6ec5","observation_id":"69ef714c-085a-45a0-866f-11dbe702dcee","resolution":{"observed_at":"2026-08-07T04:55:55.767110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05554","last_updated":"2021-09-12T16:35:00Z","snapshot_observed_at":"2026-07-06T11:46:47.166671Z","submitted_at":"2021-09-12T16:35:00Z","title":"No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.05554","snapshot_observed_at":"2026-08-07T04:55:55.769034Z","title":"M., and Liang, P","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.769034Z"},"links":{"cited_paper":"/paper/2109.05554","citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:8144983d7fd138749dce0c5ba39f81e52a33346be864ba5f3c808c4af2f2f976","observation_id":"4c0e00b9-44ec-4e0f-977a-c83ff5cef704","resolution":{"observed_at":"2026-08-07T04:55:55.769034Z","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":"2026-08-07T04:55:55.771201Z","title":"Training data-efficient image transformers & distillation through attention","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.771201Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:343d34fd05fe290bd77845dc5da3d314b553d0b34d10b92cf1102b08d58be684","observation_id":"35c5b261-783c-48ed-9bb5-3e996349b41c","resolution":{"observed_at":"2026-08-07T04:55:55.771201Z","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":"2026-08-07T04:55:55.773901Z","title":"The inaturalist species classification and detection dataset","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.773901Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:1d20bcaaf354fccb411f7732ffc2ae358417feba6ff3714f65b52a73b56694c4","observation_id":"8364cd41-7ade-4bd7-b15d-06ea92d04014","resolution":{"observed_at":"2026-08-07T04:55:55.773901Z","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":"2026-08-07T04:55:55.974012Z","title":null,"venue":null,"work_id":"4b1abe1c-2a17-481c-9371-060f51f8a1c3","year":2018},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.775790Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:4cfdb85cc739c2e50debc7d10b19d6a0dcbd6fa14e7b79a3d66eeb4485601692","observation_id":"0f431665-0e3b-4e04-b79f-397ec88388a8","resolution":{"observed_at":"2026-08-07T04:55:55.976158Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:55.967094Z","title":"Vim: Out-of-distribution with virtual-logit matching","venue":null,"work_id":"166faf78-9a5e-4ce9-9bba-c4447d33d449","year":2022},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.777734Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:7476d4a92e7425053f9956bc5f4ec71e8d846c16af3725962414caa46a3d0ab7","observation_id":"6205177a-e135-4740-ac46-904853b2e1b4","resolution":{"observed_at":"2026-08-07T04:55:55.969688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:55.960501Z","title":"Energy-based open-world uncertainty modeling for confidence calibration","venue":null,"work_id":"7770a9c6-4751-4d13-97c9-b4cbabdc205d","year":2021},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.779632Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:459835d4f8845f644df967578ca9b38420914c24a7d5df0508342b0234175c42","observation_id":"40015bef-b9ec-4d28-ba31-18ae99250e60","resolution":{"observed_at":"2026-08-07T04:55:55.962884Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:55.781511Z","title":"A., Oliva, A., and Torralba, A","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.781511Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:81012f91319326168661d2777315f3d94150839d211d38c62e591d1c5345b4e0","observation_id":"6e87a3df-a8a8-4b36-a26f-053df1b0830e","resolution":{"observed_at":"2026-08-07T04:55:55.781511Z","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":"2026-08-07T04:55:55.949872Z","title":"Scaling for training time and post-hoc out-of-distribution detection enhancement","venue":null,"work_id":"bc0a2982-5990-4619-9b76-0c0ffcda78a4","year":2024},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.783588Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:7496896044646fb7bad0e01053355910e1f030cdafdeabc8afb2639b26647983","observation_id":"6522af2d-3a58-45a0-a39a-2a252df7977a","resolution":{"observed_at":"2026-08-07T04:55:55.952246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1504.06755","last_updated":"2015-05-20T18:51:23Z","snapshot_observed_at":"2026-07-06T04:16:03.127842Z","submitted_at":"2015-04-25T19:26:47Z","title":"TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1504.06755","snapshot_observed_at":"2026-08-07T04:55:55.785382Z","title":"A., Zhang, Y., Finkelstein, A., Kulkarni, S","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.785382Z"},"links":{"cited_paper":"/paper/1504.06755","citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:2b1b56f37177556a98b23b95706b3ef15874bdac499035ee02f7edab29ebb7fb","observation_id":"6c06e161-91c8-4d0b-bdce-f6cd34575dd1","resolution":{"observed_at":"2026-08-07T04:55:55.785382Z","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":"2026-08-07T04:55:55.943272Z","title":"Openood: Benchmarking generalized out-of-distribution detection","venue":null,"work_id":"28b16074-1ce3-414f-837d-36943bddd8f6","year":2022},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.787657Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:c098ddf19aa9ed9d2381c16ac836096d2f3472409df7476d36d993839eed9295","observation_id":"6095afa6-35d6-4d91-8993-cfcae68127a3","resolution":{"observed_at":"2026-08-07T04:55:55.945636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T04:55:55.936649Z","title":"Generalized out-of-distribution detection: A survey","venue":null,"work_id":"f2fb52d8-601e-44f2-af61-0e48b0eb6516","year":2024},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.789707Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:d507e8305b7e4cbfe60a5a2b3a0227275be46bec3e9f8b781896b7e2802f3905","observation_id":"14f6449b-14fa-422c-aedc-94a139102cac","resolution":{"observed_at":"2026-08-07T04:55:55.939034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1506.03365","last_updated":"2016-06-04T09:51:30Z","snapshot_observed_at":"2026-08-08T13:26:17.517503Z","submitted_at":"2015-06-10T15:38:47Z","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.03365","snapshot_observed_at":"2026-08-07T04:55:55.791506Z","title":"Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.791506Z"},"links":{"cited_paper":"/paper/1506.03365","citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:74d43a1c34f41f81e3609dacf0099362bf6ac205642df22ae058c17cb3b52d28","observation_id":"1fc832ed-b2e5-499c-bf48-7f6e9284a22f","resolution":{"observed_at":"2026-08-07T04:55:55.791506Z","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":"2026-08-07T04:55:55.793716Z","title":"Places: A 10 million image database for scene recognition","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.793716Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:3752c15aa6ba537da72cd797de29f3cbea52a512f96cb4553cf8efbe459f6c9e","observation_id":"62b8b410-0362-453e-b57f-fc49b3676cca","resolution":{"observed_at":"2026-08-07T04:55:55.793716Z","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":"2026-08-07T04:55:55.795518Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration","version":3},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-07T04:55:55.795518Z"},"links":{"citing_paper":"/paper/2506.09399"},"observation_digest":"sha256:aca5577b7a6d401b3c50e51c16d0a410709311838396a4b6617400a71ec6a41e","observation_id":"0f21c3ee-6152-4168-84d5-8d1c61a7043a","resolution":{"observed_at":"2026-08-07T04:55:55.795518Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.09399","last_updated":"2025-06-24T12:16:38Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T16:32:07.876889Z","submitted_at":"2025-06-11T05:05:26Z","title":"Improving Out-of-Distribution Detection via Dynamic Covariance Calibration"},"reference_resolution":{"displayed":55,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":1,"verified_fuzzy":30},"total_outbound_references":55},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2506.09399."}