{"as_of":"2026-08-10T06:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:34b6429144395a401f3f340f564c40737ddc75ee50e47d345dc8115938624ec6","coverage":[{"denominator":68,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":68,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:42:57.596725Z","state":"measured"},{"denominator":68,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":68,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2507.10225/citation-record","integrity":"/paper/2507.10225/integrity","json":"/paper/2507.10225/citation-record.json","paper":"/paper/2507.10225"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1610.02136","last_updated":"2018-10-03T07:32:57Z","snapshot_observed_at":"2026-08-02T06:41:33.803920Z","submitted_at":"2016-10-07T04:06:01Z","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.02136","snapshot_observed_at":"2026-08-06T17:42:52.930151Z","title":"A baseline for detecting misclassified and out-of-distribution examples in neural net- works,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:52.930151Z"},"links":{"cited_paper":"/paper/1610.02136","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:760ef01e46de8936f094af69f93226ce55056e1a400f59d5d407c33a9d32a789","observation_id":"cf9abb15-6ede-4a93-b900-dfe52dbf2608","resolution":{"observed_at":"2026-08-06T17:42:52.930151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.02690","last_updated":"2020-08-30T16:50:36Z","snapshot_observed_at":"2026-08-05T05:04:04.733091Z","submitted_at":"2017-06-08T17:43:56Z","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.02690","snapshot_observed_at":"2026-08-06T17:42:52.967283Z","title":"Enhancing the reliability of out-of-distribution image detection in neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:52.967283Z"},"links":{"cited_paper":"/paper/1706.02690","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:ffce16c269c064bd258b19b1f65ea68175b101e7db9c12a3080346a09bc98e03","observation_id":"188da8e2-0827-4085-9829-d84e98fb749a","resolution":{"observed_at":"2026-08-06T17:42:52.967283Z","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":"2026-08-06T17:42:59.274575Z","title":"Energy-based out-of- distribution detection,","venue":null,"work_id":"751de8dc-0527-4ac2-adec-add28cfa2efd","year":2020},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.022934Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:6bd866bbcb33e38530c667aa416ac70e8fc9f4ca842c7f4711ae2d3b908e2a64","observation_id":"f18eaa75-72a3-46f0-9712-0552146cc16d","resolution":{"observed_at":"2026-08-06T17:42:59.278516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.266622Z","title":"On the importance of gradi- ents for detecting distributional shifts in the wild,","venue":null,"work_id":"0cb4a396-dd4b-4282-928f-c849e6cb497d","year":2021},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.097160Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:3b073b952465ec4e604717e317a95bad01e8f3a4af8acc798910e863b7bfde46","observation_id":"2207667a-918b-40c4-9b1d-d63cf739d21e","resolution":{"observed_at":"2026-08-06T17:42:59.269181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.259373Z","title":"Vim: Out-of- distribution with virtual-logit matching,","venue":null,"work_id":"63930a49-5c8b-4963-b8e4-5d98661f1222","year":2022},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.170982Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:da320d01a55bce0324fd9426c2713f1bf3f7f6e5a95ce9a2018efdbb155b8966","observation_id":"91718b0e-9859-438a-aa7b-adfac60a9916","resolution":{"observed_at":"2026-08-06T17:42:59.262246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.251257Z","title":"Out-of-distribution de- tection with deep nearest neighbors,","venue":null,"work_id":"90c13f41-0774-4801-84ed-6756936c78e6","year":2022},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.218709Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:4bff763cf62d0c2fa8eb3c558218c2f8532947fede0b33d3af8baaaa515686dc","observation_id":"e17fa9e2-ffba-4c7a-989f-813dbadc06a5","resolution":{"observed_at":"2026-08-06T17:42:59.253974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.01197","last_updated":"2022-05-09T20:12:32Z","snapshot_observed_at":"2026-08-05T13:42:39.716639Z","submitted_at":"2022-02-02T18:43:01Z","title":"VOS: Learning What You Don't Know by Virtual Outlier Synthesis","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.01197","snapshot_observed_at":"2026-08-06T17:42:53.278103Z","title":"V os: Learning what you don’t know by virtual outlier synthesis,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.278103Z"},"links":{"cited_paper":"/paper/2202.01197","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:93be957dc839a55c7bf8e06f127d550b0f9a467824e7f8d75bc5f35e02500b8a","observation_id":"55aa44ff-f4b2-41d3-bfbf-040a5324e93e","resolution":{"observed_at":"2026-08-06T17:42:53.278103Z","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":"2026-08-06T17:42:59.244214Z","title":"Dice: Leveraging sparsification for out- of-distribution detection,","venue":null,"work_id":"c535f01d-b243-4579-bb7a-1f43ad387cee","year":2022},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.365708Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:bb9ab5b50449f8d8d00efbb751602b263cddd7c11c9dce15415b516d6038213b","observation_id":"90f3f5e7-765a-4874-9dcf-d6124773699b","resolution":{"observed_at":"2026-08-06T17:42:59.247009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.235421Z","title":"React: Out-of-distribution detec- tion with rectified activations,","venue":null,"work_id":"7eab3713-963b-4371-91f9-a8c7fd206e46","year":2021},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.464867Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:0887cbe63af84879c6e4a0c29daf8ccbdf03d3de4895c6cf24f756815450c24b","observation_id":"17811ade-7d80-4470-bdeb-ed04fc958a00","resolution":{"observed_at":"2026-08-06T17:42:59.239109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.228809Z","title":"Zero-shot out-of-distribution detection based on the pre-trained model clip,","venue":null,"work_id":"6f22a8bc-f481-4964-99bf-fe8c26dc62fd","year":2022},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.525595Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:a29435c2b68c01dd9c1bf8f3861412bcfb06ae48f5b037b70c943e2cdb6546f1","observation_id":"2dc6cb87-62fc-4177-9931-958444a7ecef","resolution":{"observed_at":"2026-08-06T17:42:59.231265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.221467Z","title":"Delving into out-of-distribution detection with vision-language repre- sentations,","venue":null,"work_id":"f42f60d8-dc0d-491b-a772-45635b22d615","year":2022},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.606883Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:dda9c50c5e05ecb0c47f199d119424b299ac4b7c16cb7732440a4abe16543aff","observation_id":"7d17151a-0bcf-487a-b0d2-6d01ed0cd072","resolution":{"observed_at":"2026-08-06T17:42:59.224477Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.213847Z","title":"Learning to prompt for vision-language models,","venue":null,"work_id":"c6e9a16d-9de1-42c0-96e2-2b9b30581cf3","year":2022},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.675564Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:f72a54ed2763761b4501abc6e2ce6eeeeeda61f0e703275c2bcce6d016d3f6c3","observation_id":"c1fd30d2-a45d-4131-80f9-6385e4fa1782","resolution":{"observed_at":"2026-08-06T17:42:59.216529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.204330Z","title":"Conditional prompt learning for vision-language models,","venue":null,"work_id":"a6140eb3-78bb-41ac-b0a1-eb3b50b3d722","year":2022},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.761245Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:12b0dd5d914987071e0615b8df2d40ed546b26069fe9829724db7a0ebd91c5ad","observation_id":"08d38643-6ae9-407a-870e-6c14633ef0a0","resolution":{"observed_at":"2026-08-06T17:42:59.208063Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.02966","last_updated":"2023-03-06T08:51:00Z","snapshot_observed_at":"2026-08-03T10:22:00.703928Z","submitted_at":"2023-03-06T08:51:00Z","title":"Non-Parametric Outlier Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.02966","snapshot_observed_at":"2026-08-06T17:42:53.801100Z","title":"Non-parametric outlier synthesis,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.801100Z"},"links":{"cited_paper":"/paper/2303.02966","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:56b1da8307a6f80877f152dd8a6ac2d0a19e48268bd60c32ca79e924ddb30c44","observation_id":"87477dcb-3171-4eab-9d19-f826e9259aaa","resolution":{"observed_at":"2026-08-06T17:42:53.801100Z","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":"2026-08-06T17:42:59.195486Z","title":"Clipn for zero-shot ood detection: Teaching clip to say no,","venue":null,"work_id":"d0bec124-bc3c-4555-b0b9-a554b05eb186","year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.841606Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:87991bcdd9595fc7a472749daf923445f1ef1b58a624f2adbd74ef31a854e393","observation_id":"36cb76b6-1b19-4851-8d71-79e1a861396c","resolution":{"observed_at":"2026-08-06T17:42:59.198739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.186678Z","title":"Out-of-distribution detection with negative prompts,","venue":null,"work_id":"1cd787df-3d5b-4a99-a077-f107065d0e11","year":2024},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:53.921217Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:22f741a6fb0ad3a7d527013c1fe531e61929ec21e5bd1dcf50ad2ec417312461","observation_id":"0640e19b-52e1-4f94-8668-18aa9634244c","resolution":{"observed_at":"2026-08-06T17:42:59.190143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.179211Z","title":"Locoop: Few-shot out-of-distribution detection via prompt learning,","venue":null,"work_id":"de7fc7ff-8978-4033-9c2e-eae30fd8b136","year":2024},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.013686Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:ea89cfa3ce9de11b88d4edd19313b05c699171266681add4deb22edccb43d0ca","observation_id":"295e75e1-5113-4fef-bd10-4f44600c75d0","resolution":{"observed_at":"2026-08-06T17:42:59.182148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.20078","last_updated":"2024-03-29T09:19:52Z","snapshot_observed_at":"2026-08-05T22:28:05.334165Z","submitted_at":"2024-03-29T09:19:52Z","title":"Negative Label Guided OOD Detection with Pretrained Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.20078","snapshot_observed_at":"2026-08-06T17:42:54.109330Z","title":"Negative label guided ood detection with pretrained vision-language models,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.109330Z"},"links":{"cited_paper":"/paper/2403.20078","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:4934b92dfb79bdcac050014eca3b09ec6642f703acf04e9fa12e21b0102a2d7c","observation_id":"7ffff836-eacd-4598-aac4-f43e03250826","resolution":{"observed_at":"2026-08-06T17:42:54.109330Z","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":"2026-08-06T17:42:59.171002Z","title":"Hierarchical visual categories modeling: A joint representation learning and density estimation frame- work for out-of-distribution detection,","venue":null,"work_id":"6de458c7-1926-4af2-b77a-c88e91df6c9c","year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.173358Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:66547fc465b61ac20c9a93386fa47af4382a6f5907af3b07dd248f70a0e14223","observation_id":"5440a562-9cdc-4d19-9534-3e47cd73d75a","resolution":{"observed_at":"2026-08-06T17:42:59.174891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15566","last_updated":"2024-08-28T06:37:59Z","snapshot_observed_at":"2026-08-06T18:16:47.352730Z","submitted_at":"2024-08-28T06:37:59Z","title":"TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learning","version":1},"cited_work":{"arxiv_id":"2408.15566","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.15566","snapshot_observed_at":"2026-08-06T17:42:57.945582Z","title":"TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learning","venue":"cs.CV","work_id":"796bda8e-d96a-4a47-9e55-9b8ad0bce332","year":2024},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.251343Z"},"links":{"cited_paper":"/paper/2408.15566","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:863d1010e78b8d76627436f6c3251683741ee5f9e723db42e785e84bbceb696d","observation_id":"3a255ac3-e8fe-4f2f-9032-95359867ee82","resolution":{"observed_at":"2026-08-06T17:42:58.012953Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.163315Z","title":"Wordnet: a lexical database for english,","venue":null,"work_id":"d5f9c324-3ac3-4043-9457-ec785bf96a7c","year":1995},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.349930Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:69110f31dcf6fa31ce9ff3c5c6a781ffdb1a435739f62fc9da8a5c88277213c9","observation_id":"625fe983-5775-4f85-a761-2a41d51fdcff","resolution":{"observed_at":"2026-08-06T17:42:59.166064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.156407Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":"83ff441b-a3b2-4ac8-a8b7-1bbd99976808","year":2021},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.413663Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:f4254beed17e199c09b49a414744a90822c8d0b3b2991c4ea361245373086832","observation_id":"c879c597-8bd8-4148-99bb-cd47c346e383","resolution":{"observed_at":"2026-08-06T17:42:59.159263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.148302Z","title":"Visual instruction tun- ing,","venue":null,"work_id":"42485a23-c543-4136-acde-ae3c8a9e8282","year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.486457Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:f84ed581e9a82d28efe59204b8bc121a8e7de82c320eab6e2838918dc920da26","observation_id":"41dc0851-4139-4280-9f8a-f0e0dccb8174","resolution":{"observed_at":"2026-08-06T17:42:59.151407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16609","last_updated":"2023-09-28T17:07:49Z","snapshot_observed_at":"2026-08-09T21:25:20.369782Z","submitted_at":"2023-09-28T17:07:49Z","title":"Qwen Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16609","snapshot_observed_at":"2026-08-06T17:42:54.538234Z","title":"Qwen technical report,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.538234Z"},"links":{"cited_paper":"/paper/2309.16609","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:02a66d476db406a8f8f681f53c6ab63ce2399f1fa5ac70a9b397f74f6194445c","observation_id":"70cd693f-326c-4abf-b4a9-34f5896a87f6","resolution":{"observed_at":"2026-08-06T17:42:54.538234Z","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":"2026-08-06T17:42:59.140879Z","title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,","venue":null,"work_id":"55d7e52d-0631-4a02-a2b4-aeb27ecf5239","year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.618981Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:66e660f359723e1dc63e526f9ca9082030b8eca4c7b1b969cd14464e4671858d","observation_id":"0c5b1dce-6c84-4445-b099-e0f53089aca7","resolution":{"observed_at":"2026-08-06T17:42:59.143862Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.133727Z","title":"Gpt-4 technical report,","venue":null,"work_id":"189a955f-8bb3-415e-adf7-72035a036b5f","year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.681613Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:f11f405c4bdd5144eb419e20b41baaa18473931a4ef3e2a3576f07b30f2b1a34","observation_id":"a59495d0-bd17-4842-bd1c-73c8e02a1874","resolution":{"observed_at":"2026-08-06T17:42:59.136265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.126275Z","title":"Available: https://cdn.openai.com/papers/gpt- 4.pdf 1","venue":null,"work_id":"6e9ee252-c48c-45ff-82dc-d01dba6d692b","year":null},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.753545Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:85c413ae3dcc1db00eec3826a35ba9d77dbc9ade420b202b2754437a33ed45ce","observation_id":"452e1b4c-3945-40ff-9350-564ac90e5295","resolution":{"observed_at":"2026-08-06T17:42:59.129214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.118819Z","title":"High-resolution image synthesis with latent diffusion models,","venue":null,"work_id":"ee3987ba-58de-4edd-a2b7-4a99f5c7363b","year":2022},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.806363Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:70b0d56ec48b81e1d6071639b559e4e57c1562868ec490e982b19db853dab7b4","observation_id":"c2156ed3-97e5-4fa7-a411-1db3ca2d408d","resolution":{"observed_at":"2026-08-06T17:42:59.122130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.108846Z","title":"SDXL: Improving latent diffusion models for high-resolution im- age synthesis,","venue":null,"work_id":"52b03b68-4267-4257-9d12-25637dccfaff","year":2024},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.883971Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:f1a1f9e82e9cfbc3918671b145850024a1b5a9db0da45e3140a3f994485338d8","observation_id":"ab2ca178-37ae-4f1e-9066-3e2b9c032e63","resolution":{"observed_at":"2026-08-06T17:42:59.114379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-06T17:42:54.939749Z","title":"Auto-encoding variational bayes,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:54.939749Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:d29e365a96ab84a090d8633fbd918cc23fea209659536c2f58b4acbf334c52f8","observation_id":"3e7b8943-0a7f-480d-95f2-a5a341da0abf","resolution":{"observed_at":"2026-08-06T17:42:54.939749Z","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":"2026-08-06T17:42:59.100567Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":"670e3d01-c71e-4c89-8be2-60c27f584f74","year":2016},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.001838Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:411dce7a3740e1fa6a26df856deaf523c0ba259b21df27a06bf01d47d6f15ea2","observation_id":"65577c85-461a-4184-8a3a-2cd17a735017","resolution":{"observed_at":"2026-08-06T17:42:59.103736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.091993Z","title":"U-net: Con- volutional networks for biomedical image segmenta- tion,","venue":null,"work_id":"e4c38c61-972f-4936-bd0c-30c5895a0a48","year":2015},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.056072Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:5b1ea0baac2a43530d3a16ec227e17cba36a0798aa701429a24dab9cfad6eef5","observation_id":"fa4ecbe6-09c6-49f1-b4fe-f171b764fb98","resolution":{"observed_at":"2026-08-06T17:42:59.095335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.084933Z","title":null,"venue":null,"work_id":"f71ab058-2735-41f3-8a03-3ba2e87d4b63","year":2015},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.120891Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:32349c887ecc954aa013760bd2ef38b3d0220877316d590eedbde603573cfc98","observation_id":"abd796b8-547a-4d07-92f9-e5a812026da9","resolution":{"observed_at":"2026-08-06T17:42:59.087680Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.076740Z","title":"Content-based unrestricted adversarial at- tack,","venue":null,"work_id":"2bdb813c-4ab3-47a0-bf5e-396e230bd7a5","year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.179682Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:17ddcda6321f5a260c082b0dbe2372423a3532204b0a4698029af722dddc6ae3","observation_id":"b52b1d53-65bc-4a84-8082-dee442359570","resolution":{"observed_at":"2026-08-06T17:42:59.079985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.068965Z","title":"Mos: Towards scaling out-of- distribution detection for large semantic space,","venue":null,"work_id":"730589b0-889d-4317-bee0-f4321dde0eb4","year":2021},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.273445Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:35a09061d09cb7b48ce2388a19b0cc9f26091e6e5aa959720224638f2c43a08c","observation_id":"eb63a126-14e6-463a-8206-b927a2486564","resolution":{"observed_at":"2026-08-06T17:42:59.071874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.059910Z","title":"Imagenet large scale visual recognition challenge,","venue":null,"work_id":"ca9f3509-6288-42cd-915a-1308c6462dba","year":2015},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.341759Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:aca1ff028671644407f68cdf4cb298f63482146747a783ccf3805b86d6e4d913","observation_id":"35fdad93-372d-46ad-a575-4e2a7b1c27c5","resolution":{"observed_at":"2026-08-06T17:42:59.063574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.051092Z","title":"The inat- uralist species classification and detection dataset,","venue":null,"work_id":"1dfedd2e-e8b2-4733-8fdc-4611dcb33314","year":2018},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.410602Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:d0bdb651065f7017e052438b3deb4b829d9753e05b6df7e7c4ef97c8e7bc14d4","observation_id":"6c62a6de-f2b1-45da-87c5-b51d9e3996e7","resolution":{"observed_at":"2026-08-06T17:42:59.054501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.042150Z","title":"Sun database: Large-scale scene recognition from abbey to zoo,","venue":null,"work_id":"dfd32d24-1a5a-4b8c-930d-7c76e36e9783","year":2010},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.460781Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:17ea23487e2cc2cc83af5cb69fddbb35cf38069a1a44a8209df91308da2283d5","observation_id":"4fc7d802-50f1-4143-aeca-075762ccf0ff","resolution":{"observed_at":"2026-08-06T17:42:59.045512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.033509Z","title":"Places: A 10 million image database for scene recognition,","venue":null,"work_id":"8a528c6c-ed92-4cd2-a7b8-f63f5ed5e3a8","year":2017},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.541826Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:ba3d83ec014ff0af324294e8195b62b0b9974e5e6fd37582f40d76febb2a2ffa","observation_id":"d1710722-4aa1-4d2e-935e-34aeb77df5bb","resolution":{"observed_at":"2026-08-06T17:42:59.037008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.026043Z","title":"Describing textures in the wild,","venue":null,"work_id":"12dcd1bc-2490-418e-a8e2-4c24b4593e06","year":2014},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.607780Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:cc749e29d7be7891174edadb39b6fd42bf9c23d8bdc34703f9b73b2ba5ab015d","observation_id":"0544d393-ed7a-416d-8b1a-f84be94cc820","resolution":{"observed_at":"2026-08-06T17:42:59.028619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:59.018077Z","title":"Openood: Benchmarking generalized out-of-distribution detection,","venue":null,"work_id":"3ea7f8c9-099f-4da1-a744-15e4abc30a61","year":2022},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.686642Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:253d291fce45b2fa97dc51432b683a7b5f5b5fc270c35f56bd9e748c6ab5ceec","observation_id":"f62797d3-ff32-4b19-8160-2097ac03e9f2","resolution":{"observed_at":"2026-08-06T17:42:59.021248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09301","last_updated":"2024-12-16T23:09:28Z","snapshot_observed_at":"2026-08-07T21:55:34.598099Z","submitted_at":"2023-06-15T17:28:00Z","title":"OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09301","snapshot_observed_at":"2026-08-06T17:42:55.762759Z","title":"Openood v1. 5: Enhanced benchmark for out-of-distribution detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.762759Z"},"links":{"cited_paper":"/paper/2306.09301","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:0604ce234111a976a70664b3a75497bf79fcfaa488853cfe3c0391831a58d5e1","observation_id":"5a52233f-a769-458c-b683-e1c5f016c098","resolution":{"observed_at":"2026-08-06T17:42:55.762759Z","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":"2026-08-06T17:42:59.010190Z","title":"Open-set recognition: A good closed-set classifier is all you need,","venue":null,"work_id":"cac65172-5018-450d-a418-0e1b331d48a7","year":null},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.826521Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:0c5b045414ce1256353fb6883404ca00b44e0a335fee9ad54b9bb6b178653065","observation_id":"7b65e78d-5463-4d5f-96dd-339df81e7386","resolution":{"observed_at":"2026-08-06T17:42:59.013205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.00826","last_updated":"2023-06-01T15:48:10Z","snapshot_observed_at":"2026-08-10T03:30:13.149951Z","submitted_at":"2023-06-01T15:48:10Z","title":"In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.00826","snapshot_observed_at":"2026-08-06T17:42:55.909963Z","title":"In or out? fix- ing imagenet out-of-distribution detection evaluation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.909963Z"},"links":{"cited_paper":"/paper/2306.00826","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:14231efefccaaa5ae18af54ef2431a495ae92941ab125e2ffaf9a5cbb86f969e","observation_id":"7363c3f6-118b-4e4a-a5ba-40dfbb79b22c","resolution":{"observed_at":"2026-08-06T17:42:55.909963Z","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":"2026-08-06T17:42:59.001926Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows,","venue":null,"work_id":"7c94b0a5-00fd-453b-bfbc-0bc3b261eb4c","year":2021},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:55.985531Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:aeb1efe242f02256b50068b09f6277f6c7e8d016efab00be07560ec1cc165e86","observation_id":"ed647e26-0d2e-41ef-835b-54090828a275","resolution":{"observed_at":"2026-08-06T17:42:59.005125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-10T01:12:16.468283Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-06T17:42:56.038147Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.038147Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:7959ad17eb65734b75731356183b9b63259d265b5ba0e3efb9065c6aa40fc378","observation_id":"b554bbb1-1ec8-4283-ad57-306b1c2cea82","resolution":{"observed_at":"2026-08-06T17:42:56.038147Z","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":"2026-08-06T17:42:58.993044Z","title":"Densely connected convolutional networks,","venue":null,"work_id":"156d5cbd-d665-47da-a4ed-a85ebb3629bb","year":2017},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.085946Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:2e5e7611e8f0ae9ff7771407b8095b0d0ed7d97f83955024c91982e0d9261544","observation_id":"367f2179-22a0-4ef7-ba82-d9ed8ebb98fe","resolution":{"observed_at":"2026-08-06T17:42:58.996704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.984472Z","title":"Aggre- gated residual transformations for deep neural networks,","venue":null,"work_id":"fbc68fd9-77c5-46c7-a3c2-ea668ccc40c2","year":2017},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.186687Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:b88e8506397c76a960a4481b8e65a17437494c55f44f122582e50c45aad06ba0","observation_id":"f823966b-bc76-468f-b6d8-01016349d43a","resolution":{"observed_at":"2026-08-06T17:42:58.988171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.975654Z","title":"Pytorch: An imperative style, high-performance deep learning library,","venue":null,"work_id":"a914e805-3468-46cc-810f-40f922edeb83","year":2019},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.246722Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:3743b8b018527868d29cd734d457c49d9680da80242b31433941e204b7ba23b7","observation_id":"02d1ae8b-e4b8-47ba-b118-d1c9450048c1","resolution":{"observed_at":"2026-08-06T17:42:58.979309Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.967120Z","title":"Gen: Pushing the limits of softmax-based out-of-distribution detection,","venue":null,"work_id":"bb6b7d5f-c8d1-4c7b-bb4f-8955ec780ed1","year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.303957Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:26fecb0341ae8139cb584bed6ed43e9485bd0eb1e06e316b3d0e49613b91463a","observation_id":"352a7348-fa7d-4dbd-96d7-e43222faafd2","resolution":{"observed_at":"2026-08-06T17:42:58.970723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.02781","last_updated":"2020-02-17T06:16:13Z","snapshot_observed_at":"2026-07-06T08:42:24.926713Z","submitted_at":"2019-12-05T18:18:10Z","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.02781","snapshot_observed_at":"2026-08-06T17:42:56.359563Z","title":"Augmix: A simple data process- ing method to improve robustness and uncertainty,","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.359563Z"},"links":{"cited_paper":"/paper/1912.02781","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:923cd7d7915d62cb992baa9f90ffe8a0b7b993ef00ca67d18b77fac474041328","observation_id":"e3096930-bd40-4443-bb5a-ca48fcd65424","resolution":{"observed_at":"2026-08-06T17:42:56.359563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09022","last_updated":"2021-06-16T20:43:56Z","snapshot_observed_at":"2026-08-09T08:34:39.470859Z","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":"2026-08-06T17:42:56.414074Z","title":"A simple fix to mahalanobis dis- tance for improving near-ood detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.414074Z"},"links":{"cited_paper":"/paper/2106.09022","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:f5068e249c546d0335eb920c941620804e76ae284a8e6019d2947e300fb55da8","observation_id":"3d8616f1-7ebd-451a-b8e6-f0ca02eb46c2","resolution":{"observed_at":"2026-08-06T17:42:56.414074Z","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":"2026-08-08T09:05:49.544510Z","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":"2026-08-06T17:42:56.466740Z","title":"Extremely simple activation shaping for out-of-distribution detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.466740Z"},"links":{"cited_paper":"/paper/2209.09858","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:30df598313f9df880cbfdeae4ec1d855e23ff5f52d6bf17b9e0d995383a6fb60","observation_id":"887b8824-afba-4739-b035-564625101390","resolution":{"observed_at":"2026-08-06T17:42:56.466740Z","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":"2026-08-06T17:42:58.958400Z","title":"Natural adversarial examples,","venue":null,"work_id":"13174ae9-c966-4006-9184-25a8e33691e0","year":2021},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.564279Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:e0a8d45617d48bffd9742b5fcb6e0becc0bba0e24f9bb4c4292edbca733c8c64","observation_id":"adc90ba7-f64c-43b1-95ef-3c37cc9735e7","resolution":{"observed_at":"2026-08-06T17:42:58.961911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.949507Z","title":"A simple unified frame- work for detecting out-of-distribution samples and adversar- ial attacks,","venue":null,"work_id":"47052c19-428c-4751-b38e-f3866092b3d5","year":2018},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.647975Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:6b391889969a0a29eb94d6af0d97ce2bdbc7763db7beae6da59c3db6311e4f6a","observation_id":"2f119868-66a8-4e01-bce9-21d61071eee5","resolution":{"observed_at":"2026-08-06T17:42:58.952998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05566","last_updated":"2020-07-10T18:40:37Z","snapshot_observed_at":"2026-08-05T18:39:07.775274Z","submitted_at":"2020-07-10T18:40:37Z","title":"Contrastive Training for Improved Out-of-Distribution Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.05566","snapshot_observed_at":"2026-08-06T17:42:56.718878Z","title":"Contrastive training for improved out-of-distribution detection,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.718878Z"},"links":{"cited_paper":"/paper/2007.05566","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:368343a3b27a5f7fa61ee3ad03f59cd1df6db3c563c7da414a088372e300f0c6","observation_id":"dbf6493f-b6c7-4c90-9e1c-07c26bbc3668","resolution":{"observed_at":"2026-08-06T17:42:56.718878Z","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":"2026-08-06T17:42:58.941212Z","title":"A boundary based out-of-distribution classifier for generalized zero-shot learn- ing,","venue":null,"work_id":"17bb38ff-1031-4478-bebf-28ba978f7740","year":2020},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.778981Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:0cec802a6c0df565d730307b722a30804287ae2dbc5ea74ba8ed520f96e37458","observation_id":"7b5e77ba-fa0f-4f83-8990-bc8dc0bf431e","resolution":{"observed_at":"2026-08-06T17:42:58.944661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.933051Z","title":"Out-of-distribution detection using union of 1-dimensional subspaces,","venue":null,"work_id":"03bae90d-2db8-4a6d-96a7-871d1b1958e6","year":2021},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.886117Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:702e67da75f23be228b60e535c6975f158d89bcd6a2eb8e9e7d6996802a6b4f8","observation_id":"e263e5fa-8f7f-49c3-9b72-1e8eb95e4891","resolution":{"observed_at":"2026-08-06T17:42:58.936065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.924484Z","title":"Un- certainty estimation using a single deep deterministic neural network,","venue":null,"work_id":"dc8c2e7d-d5a6-4158-84d0-9b77ea4fd773","year":2020},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:56.949806Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:abbb7657ab825082b11d19f6cce79c3e0bc857a77e63b266fb50b0e1faab7282","observation_id":"44c341a3-e457-487f-8f1a-fa7597fd7884","resolution":{"observed_at":"2026-08-06T17:42:58.927519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.14654","last_updated":"2020-12-16T19:56:16Z","snapshot_observed_at":"2026-07-06T10:18:55.713047Z","submitted_at":"2020-11-30T09:47:20Z","title":"Feature Space Singularity for Out-of-Distribution Detection","version":2},"cited_work":{"arxiv_id":"2011.14654","doi":null,"metadata_source":"pith","pith_arxiv_id":"2011.14654","snapshot_observed_at":"2026-08-06T17:42:57.692346Z","title":"Feature Space Singularity for Out-of-Distribution Detection","venue":"stat.ML","work_id":"90092869-57a4-4436-8a1c-4f22a0ab6061","year":2020},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:57.033649Z"},"links":{"cited_paper":"/paper/2011.14654","citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:f30ed511ab1cf26a68bad0a05badd7bd1cb2446e81535af1fb4420732cb26345","observation_id":"3800114e-0f8c-4d2f-9f0f-2c4eeb3f233d","resolution":{"observed_at":"2026-08-06T17:42:57.752985Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.916290Z","title":"Exploring the limits of out-of-distribution detection,","venue":null,"work_id":"ffeb202a-a0bd-4922-9ca0-beac7486a230","year":null},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:57.087185Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:990cd6b2c47a6c48e0bb4f6dd82b92f634c1600aef944c07bf612b65570e087f","observation_id":"3cc2724e-f7ee-470c-bf26-ff564338cbed","resolution":{"observed_at":"2026-08-06T17:42:58.919263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.905178Z","title":"Visual instruction tuning,","venue":null,"work_id":"1ee32e7d-1fd6-49cd-afa0-fbbb2f09e822","year":2024},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:57.157660Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:2787691c70614b401e2a124c47de67cf9f747c130e0a2d4cec4e090702c69191","observation_id":"750559d0-7c72-48d4-84d0-b6ab28495fb6","resolution":{"observed_at":"2026-08-06T17:42:58.910965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.746460Z","title":"Lapt: Label-driven automated prompt tuning for ood detection with vision- language models,","venue":null,"work_id":"66cf7173-a663-4c47-b6fc-6abf64db9d3f","year":2024},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:57.227584Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:50736bc4b978aa0c659a357e4a4c0f8025d7569a9e49c8ce97f1e5d9abd8141a","observation_id":"dc9e15ae-57b1-4e61-a7b6-f0e57f3e3ad1","resolution":{"observed_at":"2026-08-06T17:42:58.839551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.610438Z","title":"Dream the impossi- ble: Outlier imagination with diffusion models,","venue":null,"work_id":"93f5984f-a690-49be-b9ce-e2176da53fbc","year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:57.303801Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:ce47c9f7219fe36e88e74ae0fa18db9b86a088d106e0140df6ef5e84a0aff6a2","observation_id":"ed5d0856-f01d-4162-a4d7-d380eea978a3","resolution":{"observed_at":"2026-08-06T17:42:58.691032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.451828Z","title":"Conjugated semantic pool im- proves ood detection with pre-trained vision-language mod- els,","venue":null,"work_id":"3657cfff-5c13-4908-8684-b3d71e500ec9","year":2024},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:57.388471Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:bc6eb407159713c0a904b8a17f1def747eb8c89bdf4294ffc8e231ae15b94a1b","observation_id":"70b55591-7b60-4c5d-907a-24f6964f1430","resolution":{"observed_at":"2026-08-06T17:42:58.500816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.365729Z","title":"Adaneg: Adaptive negative proxy guided OOD detection with vision-language models,","venue":null,"work_id":"24febb74-fc51-40e8-bb70-5244d8fae564","year":2024},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:57.454915Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:130c3d15e173192635e2e1cfd58db9de1c9a04a86bbe6b8f93db1a31a52a5d90","observation_id":"dde5ecae-00a7-42cb-803e-524e15783d35","resolution":{"observed_at":"2026-08-06T17:42:58.417011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.287300Z","title":"Is out- of-distribution detection learnable?","venue":null,"work_id":"731dc267-89d2-4340-9a65-7c0191be118e","year":null},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:57.519967Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:bce287b4ab59431e1119d726709fbff58c219e024c4d9cd1e1ca11981d52ccd2","observation_id":"ade941f8-716d-4bfd-b1ae-52fd883b85fd","resolution":{"observed_at":"2026-08-06T17:42:58.319562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T17:42:58.143158Z","title":"Out-of-distribution detection learning with unreli- able out-of-distribution sources,","venue":null,"work_id":"1ddbfa5b-10d4-4cdd-b2fb-c6417eb705e0","year":2023},"citing_paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T17:42:57.596725Z"},"links":{"citing_paper":"/paper/2507.10225"},"observation_digest":"sha256:8df3f890db04dd6769f5d0bbae26fbbc9c981e17a8534b56543fb8e0612ae80c","observation_id":"6e131da6-0473-460e-a55b-e9789ac3f492","resolution":{"observed_at":"2026-08-06T17:42:58.239512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.10225","last_updated":"2025-08-21T08:30:21Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T08:35:16.561233Z","submitted_at":"2025-07-14T12:43:50Z","title":"Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection"},"reference_resolution":{"displayed":68,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":2,"verified_fuzzy":51},"total_outbound_references":68},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 0 inbound Pith citation observations for arXiv:2507.10225."}