{"as_of":"2026-08-19T00:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2ecf9bbdbad48118a7b71354fce9d16d79b035d0f0973f25a57c4f8ea275a790","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T19:01:50.805371Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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":"2026-06-26T09:11:53.740246Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T09:59:45.912937Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"cited_work":{"arxiv_id":"2412.07219","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.07219","snapshot_observed_at":"2026-07-04T09:59:45.912937Z","title":"arXiv preprint arXiv:2412.07219 (2024)","venue":null,"work_id":"88ecf3a0-93bb-4d78-99dc-57c5d1e87842","year":2024},"citing_paper":{"arxiv_id":"2606.23373","last_updated":"2026-06-22T14:07:33Z","snapshot_observed_at":"2026-08-07T17:04:01.983015Z","submitted_at":"2026-06-22T14:07:33Z","title":"Polynomial Dice Loss for Medical Image Segmentation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-26T09:11:53.740246Z"},"links":{"cited_paper":"/paper/2412.07219","citing_paper":"/paper/2606.23373"},"observation_digest":"sha256:6e1f21f4030da96c5a504cecfa9d20426809773f23cce406466c6f86dfaeca5c","observation_id":"296bcfa3-0d77-4836-a3a4-3c0748514e33","resolution":{"observed_at":"2026-07-04T09:59:45.914680Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.07219/citation-record","integrity":"/paper/2412.07219/integrity","json":"/paper/2412.07219/citation-record.json","paper":"/paper/2412.07219"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:01:51.839666Z","title":"Atom: Robustifying out-of-distribution detection using outlier mining","venue":null,"work_id":"3964a23e-4ea5-4c23-b67f-e417d15baf3a","year":2021},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.510055Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:8c19973fd44678689ec859210a2e63d199e50f56c4d3a12ac9063a0dd4c0c474","observation_id":"326bd700-7ee4-431c-ab93-a402805c0838","resolution":{"observed_at":"2026-08-11T19:01:51.864387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:50.520964Z","title":"Describing textures in the wild","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.520964Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:f2a98c07e025add65bc0b20f76409558c6c037ee461d53186bc148110a053ef4","observation_id":"3fe1f50b-376f-488f-b76f-7e55834d8d0e","resolution":{"observed_at":"2026-08-11T19:01:50.520964Z","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":"2026-08-14T19:46:10.262380Z","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":"2026-08-11T19:01:50.529621Z","title":"Learning confi- dence for out-of-distribution detection in neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.529621Z"},"links":{"cited_paper":"/paper/1802.04865","citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:7802a31efb70e93c2f741f4794eda13027691716b27f8b6a6d618b64aae76f01","observation_id":"947e77fd-9a08-4481-a236-a4f0b32fcabc","resolution":{"observed_at":"2026-08-11T19:01:50.529621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.09858","last_updated":"2023-05-01T22:27:08Z","snapshot_observed_at":"2026-08-16T16:31:08.845997Z","submitted_at":"2022-09-20T17:09:49Z","title":"Extremely Simple Activation Shaping for Out-of-Distribution Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.09858","snapshot_observed_at":"2026-08-11T19:01:50.535287Z","title":"Extremely simple activation shaping for out- of-distribution detection","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.535287Z"},"links":{"cited_paper":"/paper/2209.09858","citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:5d83b8a5db04e1b8eb630219ef2a3235d768837ec4c5a1352f632ee9819ff530","observation_id":"04421c4e-4e74-4805-b962-bc57e7503b7c","resolution":{"observed_at":"2026-08-11T19:01:50.535287Z","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":"2026-08-11T19:01:51.797884Z","title":"V os: Learning what you don’t know by virtual outlier synthesis","venue":null,"work_id":"d25c1c94-dbca-47c2-b2ed-7544605caec7","year":2022},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.541141Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:7a0b0c1972dc382a250e99eac8e0dfc9975d1865a741d441e4ce6bcad7b86234","observation_id":"545a07c6-cb42-43ac-aa29-7529eb64ab7b","resolution":{"observed_at":"2026-08-11T19:01:51.804799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.768547Z","title":"Dream the impossible: Outlier imagination with diffusion models","venue":null,"work_id":"d4c9d3b0-ffb2-4cab-ac05-222d31216f4d","year":2023},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.549147Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:847c704841becaef5bee2dbec2419b3ec2db4b16f59be04416020563c6546bbf","observation_id":"04eb71ed-891b-4dd1-903f-f774642f2fdc","resolution":{"observed_at":"2026-08-11T19:01:51.778626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.733043Z","title":"Can cross entropy loss be robust to label noise? In IJCAI, pages 2206–2212, 2021","venue":null,"work_id":"981f1513-33c7-4b28-9804-88dbe13973fe","year":2021},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.553950Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:5e0cf74b5b8b52fb8cdf10068fddd9fca7cc2f87391ea41d55530315ffd68a7c","observation_id":"835ec69c-1a3d-4eb7-adba-c9cf50665b3b","resolution":{"observed_at":"2026-08-11T19:01:51.742062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.703487Z","title":"A baseline for detect- ing misclassified and out-of-distribution examples in neural networks","venue":null,"work_id":"ae021a9a-0af9-46a8-a139-f5408396fcbb","year":2017},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.566918Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:41c975107a2aa8517215d6885771a2d400832f951d2735d81834ec049bd7b71d","observation_id":"a92e22d3-d467-430b-ae01-08368d417623","resolution":{"observed_at":"2026-08-11T19:01:51.710046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.673910Z","title":"Deep anomaly detection with outlier exposure","venue":null,"work_id":"10b23b1c-eb3f-4d8c-b539-c1d089b9f7c9","year":null},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.571303Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:ce220162606cb22e151522d87ac124579e28ba470ce6647ee0c5cb1e72b1338c","observation_id":"9f9f1b0d-4986-44a3-b2a0-7845c522afa1","resolution":{"observed_at":"2026-08-11T19:01:51.681040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.657297Z","title":"Scaling out-of-distribution detection for real-world settings","venue":null,"work_id":"33658f69-8e88-46c6-9840-9129dd8f7b41","year":null},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.576141Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:f1b18d422e9fc6ebdfb293eab109bbd1341fda451e79e3d7759c25d576cd7eba","observation_id":"95719457-104e-4747-b0f5-56b844a8cedc","resolution":{"observed_at":"2026-08-11T19:01:51.664467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.630957Z","title":"On the impor- tance of gradients for detecting distributional shifts in the wild","venue":null,"work_id":"c966ff79-ce6c-46a8-b21b-338b78291bbd","year":null},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.587853Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:66e6bb7f074576c7af5e506c9d389225d0dbf9b6575fe5d2938a2de261c0f1eb","observation_id":"673982e8-499f-4ec5-bbed-75fc072d341d","resolution":{"observed_at":"2026-08-11T19:01:51.639700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.595675Z","title":"Robust estimation of a location parameter","venue":null,"work_id":"44f72669-478b-4e4a-a287-bd30b09a32e9","year":1992},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.593911Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:189ced87885750fbcbadb8b05ed56fae58b0a7dc31ee3ec0109ea47c56600bd4","observation_id":"198299b6-e0f5-494f-bd95-ddd9f0d84fc9","resolution":{"observed_at":"2026-08-11T19:01:51.607538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.562861Z","title":"DOS: Diverse outlier sampling for out- of-distribution detection","venue":null,"work_id":"1e9ed913-687e-4452-b50c-021c04e64890","year":2024},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.603081Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:beb4cfff13ed8798af3841f1ada7035a85faee990d0d4dc28976d2bd31c40972","observation_id":"f5bb8474-ee2c-4902-ad1d-45c316c682a4","resolution":{"observed_at":"2026-08-11T19:01:51.568297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.546225Z","title":"Training ood detectors in their natural habitats","venue":null,"work_id":"11b79231-806c-4436-aa0a-9ece2995de77","year":2022},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.609388Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:b47348a46a822c9e51a71885f87d45503d817da621977523d1dc31854515da5c","observation_id":"8cc1d35e-21c1-4ab2-b832-23effd3dd197","resolution":{"observed_at":"2026-08-11T19:01:51.552241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.512710Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"f373de6c-aca2-4a86-bcb7-ac6118c58095","year":2009},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.614920Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:5b3d38b12b1d4e92435dff94e3f2dd61ad8188446ba674eeeb9f8dfba6d083f6","observation_id":"c6a3d83e-e1bb-4cb1-beeb-34d76672712f","resolution":{"observed_at":"2026-08-11T19:01:51.522641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.487690Z","title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","venue":null,"work_id":"cbb799d2-7f7f-4379-8e06-503e26b6fcb5","year":2018},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.626950Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:63ccde7679ba7aba1ee08b461dfc5aee6550612b21fb5afd08500056bb21f8c7","observation_id":"597447e8-8c0e-4571-aea5-e71f4fdeb9eb","resolution":{"observed_at":"2026-08-11T19:01:51.492595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.470053Z","title":"Polyloss: A polynomial expansion perspective of classifica- tion loss functions","venue":null,"work_id":"b08d808d-cb60-4e6f-bf88-1a4da50aa72a","year":2022},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.635273Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:696c7e0aa64e92d11f1c1eb911c8e2c891879d14811008f2aad4f9c815720afe","observation_id":"dbf7a356-1c6d-4de3-b461-a8843ff2d47c","resolution":{"observed_at":"2026-08-11T19:01:51.476802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.441997Z","title":"Background data resampling for outlier-aware classification","venue":null,"work_id":"1d957b3c-fd2f-4549-b0b2-3dc87be209dc","year":2020},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.640237Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:9b7aaec743f934052e76ab0bb8d8ff35562f4865b56bb3544f48cf7b420ee6f3","observation_id":"2dcab317-5a8c-4946-962b-c2f2af14332e","resolution":{"observed_at":"2026-08-11T19:01:51.448958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.420239Z","title":null,"venue":null,"work_id":"8baef442-f74d-442f-b04b-0694769e6580","year":2018},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.648560Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:fd0a80747ea03a1468da505332abdbc55fe40f471ef07bf63b70f699ac007d4a","observation_id":"c59e6de8-260c-4ee3-9332-b29860b205d2","resolution":{"observed_at":"2026-08-11T19:01:51.428111Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.379338Z","title":"Mood: Multi- level out-of-distribution detection","venue":null,"work_id":"fe542b2f-1c53-483a-8af5-b311daa39c4d","year":2021},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.656478Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:ed638fa7e68e0ccf623ffd67c6b7fb6a3bfef30c5b2813c737f7e3ae4dbf1592","observation_id":"2154849e-5c8e-45d6-8302-e098a69bb712","resolution":{"observed_at":"2026-08-11T19:01:51.392313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.341111Z","title":"Energy-based out-of-distribution detection","venue":null,"work_id":"1a3e3330-b29b-4b6d-a93e-b4e65c780bb6","year":2020},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.664281Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:217080048dca53a65039f18ef4bedb1fcf92be0371bf43430aa32b9507d9d83b","observation_id":"f19132cb-50cd-4d55-8d2c-a874ff60caa9","resolution":{"observed_at":"2026-08-11T19:01:51.347055Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.313413Z","title":"Peer loss functions: Learning from noisy labels without knowing noise rates","venue":null,"work_id":"14947e1a-b2d7-4816-ad49-54465da550d9","year":2020},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.672789Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:739d6d762cc60ddee8b7515e7e806e6d5fdbce2c4b5b9fd148cf36d79d97149e","observation_id":"28476501-68be-4ec9-9868-ccc65a8c73f6","resolution":{"observed_at":"2026-08-11T19:01:51.319061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.291920Z","title":"SGDR: Stochastic gradi- ent descent with warm restarts","venue":null,"work_id":"4109d0e4-d88b-49eb-896a-6498621ded75","year":2017},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.688695Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:b046a737827db60c739576b959b5c8ca892dbee353ee2094c3c4859d5a276d34","observation_id":"250b9a52-61d2-46ba-b2bc-86b6d682ce16","resolution":{"observed_at":"2026-08-11T19:01:51.296211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.264522Z","title":"Poem: Out-of- distribution detection with posterior sampling","venue":null,"work_id":"0eaf1782-8adc-4b5c-8e34-e896d0a77a92","year":2022},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.695694Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:814ea99d5bc18b2770f90fec62159c98d381db7173f95c74f857c218df9fb22c","observation_id":"6391f663-0da2-4138-82fd-a4ac1f893dc1","resolution":{"observed_at":"2026-08-11T19:01:51.272999Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.246236Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":"2385a43e-b4f0-4e82-86c6-3d50cfb056f9","year":2011},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.702178Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:8c2475833d58e849b070216e27682217b189dcd599c69096ad981fd6dc9aa1c5","observation_id":"6dcc7818-52bb-4ef8-9541-622d8c2c0fee","resolution":{"observed_at":"2026-08-11T19:01:51.250519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.220926Z","title":"Gradient-regularized out-of- distribution detection","venue":null,"work_id":"712224b4-dd3e-41b3-9b1c-8d944492fc13","year":null},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.713492Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:f673e220af26f9c3ebf06f7201210c0dc935198c3a6b58e212f7fb314597a43b","observation_id":"efaa08b1-a1c2-4207-88d5-1aa620f8daa5","resolution":{"observed_at":"2026-08-11T19:01:51.229079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.181397Z","title":"Dice: Leveraging sparsification for out-of-distribution detection","venue":null,"work_id":"930e41cf-9d25-49b1-a66f-27aea1c860bf","year":2022},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.718680Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:519ba1c94b58b1660a8ac0da63e6ba63bd03cb355c74d207fd93b8f0e2449580","observation_id":"1d1adcaa-0f85-43ad-9885-553ee59778df","resolution":{"observed_at":"2026-08-11T19:01:51.191364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.161227Z","title":"Non- parametric outlier synthesis","venue":null,"work_id":"dfcab820-f186-4925-98bc-59631bc88e71","year":2023},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.725414Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:9157200ede423d8e04fd5341015431128a883f6f230285abf1eeffa23c8f003b","observation_id":"bb07a881-0ebd-4513-b5fb-839bf3e2acdd","resolution":{"observed_at":"2026-08-11T19:01:51.165646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.128461Z","title":"Out-of- distribution detection with implicit outlier transformation","venue":null,"work_id":"76cf4dab-3083-4906-bdb6-3ded74e434ac","year":2023},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.734643Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:a0a2ed060101255297296fb7125b995b491ac3dfa6ecb87b40816320f07fb7ee","observation_id":"2774c2d4-f52e-4c6c-a32e-bebb43902259","resolution":{"observed_at":"2026-08-11T19:01:51.151832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.108375Z","title":"Mitigating neural network overconfidence with logit normalization","venue":null,"work_id":"874d66e2-f60a-4b0f-a9d8-a58572cccffa","year":2022},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.739845Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:ed5135d5deab1c5de7fe6090340fd9aeb6f2c2f060d70524e20093e30da5b4c6","observation_id":"cce1bba4-908b-4c92-b9fb-affd46527175","resolution":{"observed_at":"2026-08-11T19:01:51.116359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1504.06755","last_updated":"2015-05-20T18:51:23Z","snapshot_observed_at":"2026-08-14T22:51:02.620922Z","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":"2026-08-11T19:01:50.745422Z","title":"Turkergaze: Crowdsourcing saliency with webcam based eye tracking","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.745422Z"},"links":{"cited_paper":"/paper/1504.06755","citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:47f96c53a7ce2449786b35dab0e618ed53f8e5e7de06290d7cbcfc3f85b637e2","observation_id":"ba40a2d0-a47c-4e85-acd6-badd0c0a0f0c","resolution":{"observed_at":"2026-08-11T19:01:50.745422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-11T19:01:50.756064Z","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":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.756064Z"},"links":{"cited_paper":"/paper/1506.03365","citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:8900eedb716255dbb0af2adf8175a6fd127228322ec10fbf1c73d0cfb5b1cb25","observation_id":"77965c9b-8639-493f-90e1-481a74de2dc7","resolution":{"observed_at":"2026-08-11T19:01:50.756064Z","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":"2026-08-11T19:01:51.079742Z","title":"Wide residual net- works","venue":null,"work_id":"d626a851-b81e-43ad-9669-e66c51663d70","year":2016},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.767122Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:9db6e0f0c9104c0a542f5d20ff4f3eec40959f9650a3abe0212ea15f5c145f3c","observation_id":"0675c33e-7096-4610-9f49-bf57fe1e8e81","resolution":{"observed_at":"2026-08-11T19:01:51.091033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.055981Z","title":"Mixture outlier exposure: Towards out-of-distribution detection in fine-grained environments","venue":null,"work_id":"e87dbd06-91f9-467c-adec-4d5fbf19340b","year":2023},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.774903Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:445a938110d3dc55644f9babd566e08653318ad12a680b89aff7032703b39a26","observation_id":"4562a4a3-9e33-46d3-8301-70be83efa89d","resolution":{"observed_at":"2026-08-11T19:01:51.067687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.034219Z","title":"Generalized cross entropy loss for training deep neural networks with noisy labels","venue":null,"work_id":"c13417b5-7d67-4a46-828c-2f7e23758001","year":2018},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.786391Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:5af2b8d290752d410bbe0aa35586a594d204ebf12fd63d2dccb99712a2604d0c","observation_id":"fb235428-4ea3-4b85-91a4-99c399b84963","resolution":{"observed_at":"2026-08-11T19:01:51.040368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:51.006533Z","title":"Places: A 10 million image database for scene recognition","venue":null,"work_id":"20e43ea4-3846-4558-b2d4-b642e419cced","year":2017},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.798024Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:4496dda6f254593abaaaaad55cc86f4b7d6b6874852941f268936cc7e4f2fa01","observation_id":"33026f2c-143c-4eb8-8dad-96f96926884c","resolution":{"observed_at":"2026-08-11T19:01:51.013817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:01:50.975235Z","title":"Diversified outlier ex- posure for out-of-distribution detection via informative ex- trapolation","venue":null,"work_id":"da5c62c3-f9ab-40e4-9e54-cc57c7697411","year":2023},"citing_paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T19:01:50.805371Z"},"links":{"citing_paper":"/paper/2412.07219"},"observation_digest":"sha256:d7d04f775efcae58cf239766ee1a878ac1db8bd20cc4a1a295dd18599d2744aa","observation_id":"e629c6e6-60c7-436d-b320-61ce26c56a7e","resolution":{"observed_at":"2026-08-11T19:01:50.986562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.07219","last_updated":"2024-12-10T06:17:07Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T23:08:23.726662Z","submitted_at":"2024-12-10T06:17:07Z","title":"Taylor Outlier Exposure"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":31},"total_outbound_references":37},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2412.07219."}