{"as_of":"2026-08-10T15:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4097eb0654c013420ddf859416f5af6e1d6e93ddc6a2db377c3098c56790c77b","coverage":[{"denominator":56,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":56,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:40:25.431563Z","state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T05:30:14.277852Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-06-28T23:42:49.385989Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"cited_work":{"arxiv_id":"2505.18032","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.18032","snapshot_observed_at":"2026-06-28T23:42:49.385989Z","title":"Mahalanobis++: Improving ood detection via feature normaliza- tion.arXiv preprint arXiv:2505.18032,","venue":null,"work_id":"8798aee8-5006-4f5d-b02a-54b20685b8bb","year":2025},"citing_paper":{"arxiv_id":"2604.26409","last_updated":"2026-04-29T08:23:38Z","snapshot_observed_at":"2026-07-06T23:12:06.349884Z","submitted_at":"2026-04-29T08:23:38Z","title":"Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-07T11:26:20.416828Z"},"links":{"cited_paper":"/paper/2505.18032","citing_paper":"/paper/2604.26409"},"observation_digest":"sha256:ac7dc2630fe3ae03952edf4d4d3429f91ae1dff2fb6020770d473716fe9e2ad0","observation_id":"c1b75fa5-9bf2-4bc7-91e8-aa4ecdab86fb","resolution":{"observed_at":"2026-05-12T09:21:25.518989Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"cited_work":{"arxiv_id":"2505.18032","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.18032","snapshot_observed_at":"2026-06-28T23:42:49.385989Z","title":"Mahalanobis++: Improving ood detection via feature normaliza- tion.arXiv preprint arXiv:2505.18032,","venue":null,"work_id":"8798aee8-5006-4f5d-b02a-54b20685b8bb","year":2025},"citing_paper":{"arxiv_id":"2605.18988","last_updated":"2026-05-18T18:06:20Z","snapshot_observed_at":"2026-07-06T23:29:47.081347Z","submitted_at":"2026-05-18T18:06:20Z","title":"Surviving the Unseen: Predictive Defense for Novel Multi-Turn Multimodal Attacks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-20T09:07:47.278074Z"},"links":{"cited_paper":"/paper/2505.18032","citing_paper":"/paper/2605.18988"},"observation_digest":"sha256:75f1a6ad731cda88097fe40da6477934e39440519a6492b81d6248457da62887","observation_id":"460b1b83-82f1-4fcf-98aa-07f205ca9fa1","resolution":{"observed_at":"2026-05-20T09:08:09.481754Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"cited_work":{"arxiv_id":"2505.18032","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.18032","snapshot_observed_at":"2026-06-28T23:42:49.385989Z","title":"Mahalanobis++: Improving ood detection via feature normaliza- tion.arXiv preprint arXiv:2505.18032,","venue":null,"work_id":"8798aee8-5006-4f5d-b02a-54b20685b8bb","year":2025},"citing_paper":{"arxiv_id":"2605.31155","last_updated":"2026-05-29T11:04:34Z","snapshot_observed_at":"2026-08-05T20:23:12.034499Z","submitted_at":"2026-05-29T11:04:34Z","title":"Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-28T23:42:01.927845Z"},"links":{"cited_paper":"/paper/2505.18032","citing_paper":"/paper/2605.31155"},"observation_digest":"sha256:0dee59a2a637a434d1de8a1e2db4ce87dfc5898617d3b52a8acb2b590b627bc9","observation_id":"b792a0df-6280-459a-99c7-f5e991c21f97","resolution":{"observed_at":"2026-06-28T23:42:49.387449Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.18032","snapshot_observed_at":"2026-08-02T05:30:14.277852Z","title":"Mahalanobis++: Improving ood detection via feature normalization.arXiv preprint arXiv:2505.18032, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13368","last_updated":"2026-07-15T01:10:25Z","snapshot_observed_at":"2026-08-09T16:29:47.029113Z","submitted_at":"2026-07-15T01:10:25Z","title":"Fine-Grained Open-Set Fault Diagnosis via Metric-Guided Time-Frequency Configuration Selection and Class-Specific Autoencoders","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T05:30:14.277852Z"},"links":{"cited_paper":"/paper/2505.18032","citing_paper":"/paper/2607.13368"},"observation_digest":"sha256:8c65ca8020d869919fdc1162bec9df124082239f5715358aa525c1e7d4d66b94","observation_id":"417b084a-b48d-4cd5-b1b9-7c94448ea68b","resolution":{"observed_at":"2026-08-02T05:30:14.277852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.18032/citation-record","integrity":"/paper/2505.18032/integrity","json":"/paper/2505.18032/citation-record.json","paper":"/paper/2505.18032"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:19.962326Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:19.962326Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:646c43328ec669fc09ced9bfd6af10d07178b02c973308c5420874c2d35d2b69","observation_id":"82737790-8798-48ef-b7b7-116c11e6ad66","resolution":{"observed_at":"2026-08-07T14:40:19.962326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:20.054611Z","title":"B., Belkhir, N., Popescu, S., Manzanera, A., and Franchi, G","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.054611Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:e24ac15ef7ca32830d60302184dedbe482a1f8d78362b8cd65480006434925b1","observation_id":"dfe82aa1-ceb3-4437-b620-b98442ca34ac","resolution":{"observed_at":"2026-08-07T14:40:20.054611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:20.171785Z","title":"and Kamnitsas, K","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.171785Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:98e993d867d61a0cb3730da75d47d397d6cc845d0d39ceef4e121d750a9d58c6","observation_id":"05cac976-c30f-42de-93dd-a4c859660cdd","resolution":{"observed_at":"2026-08-07T14:40:20.171785Z","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":"2026-08-07T14:40:31.303093Z","title":"In or out? fixing imagenet out-of-distribution detection evaluation","venue":null,"work_id":"7db595ba-f453-4138-8c4c-592630ad08de","year":2023},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.249526Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:3e9865f764250c9371bf85b75252c21cb44a0a1a62cd5e135ad29cac1496a814","observation_id":"58ed46d7-b4b6-4477-b1db-4d30afbcc0eb","resolution":{"observed_at":"2026-08-07T14:40:31.370283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:20.356074Z","title":"Describing textures in the wild","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.356074Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:aeaedf542d5f2138660f6f56cefa43c25af6fa8060408a2781e8b4ec86abc647","observation_id":"f41b7255-5ae3-4cec-9628-dd54e4f5dcb6","resolution":{"observed_at":"2026-08-07T14:40:20.356074Z","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":"2026-08-07T14:40:31.044044Z","title":"Extremely simple activation shaping for out-of-distribution detection","venue":null,"work_id":"8eafcb06-cb9b-43fd-9c51-96204a87db4d","year":2023},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.451217Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:fa8bae017343d301dcc7ed22c0bda8ab4cce562be84edccf51b84f8e3aacc3d9","observation_id":"4a7a970a-cbaa-4d17-bba1-90100e2e44d8","resolution":{"observed_at":"2026-08-07T14:40:31.174103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:30.862353Z","title":"A framework for benchmarking class-out-of-distribution detection and its application to imagenet","venue":null,"work_id":"8157a26a-e493-483e-b410-c70ee8de3a0b","year":2023},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.521024Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:9ef65421518a75ff2bc3e0c463b1adde2f63579b3507c4ca5d3be2d14e797841","observation_id":"fa3ab2e0-7783-42e1-a537-f2243b074d9e","resolution":{"observed_at":"2026-08-07T14:40:30.937862Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.15288","last_updated":"2024-04-08T10:48:22Z","snapshot_observed_at":"2026-08-09T08:35:43.236090Z","submitted_at":"2023-12-23T16:05:47Z","title":"Understanding normalization in contrastive representation learning and out-of-distribution detection","version":2},"cited_work":{"arxiv_id":"2312.15288","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.15288","snapshot_observed_at":"2026-08-07T14:40:26.859030Z","title":"Understanding normalization in contrastive representation learning and out-of-distribution detection","venue":"cs.CV","work_id":"c5e9d6de-18f2-4be8-b700-36ea3b65dca1","year":2023},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.638292Z"},"links":{"cited_paper":"/paper/2312.15288","citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:0d1a7e03dd0791d926736ff577cfb62ca64ebf25f05b9bbdec4c04c39c13c096","observation_id":"901702ae-c71b-4024-98ce-ea6edd98418b","resolution":{"observed_at":"2026-08-07T14:40:26.982307Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:20.733951Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.733951Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:ce8b6aecc5fa94fb30f2b304dabf3434338fb27affa2f5367ab3351482f0e848","observation_id":"f4dd95d0-a165-43f8-8a84-45fff9e97fbd","resolution":{"observed_at":"2026-08-07T14:40:20.733951Z","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":"2026-08-07T14:40:30.606787Z","title":null,"venue":null,"work_id":"20cb9e98-1f90-4523-9bff-0e82b7df69cc","year":2024},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.807610Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:f444e8e397fa7763fe292f09a3fec4894e7b55e1f2ec1720d5132b67f46eefc1","observation_id":"091a0cde-eb03-44c1-b398-73f2cebbef80","resolution":{"observed_at":"2026-08-07T14:40:30.745385Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:30.520177Z","title":"Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem","venue":null,"work_id":"de912a59-c420-4563-826e-9ae20feb93b4","year":2019},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.889351Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:686510bf14dd10e126ae163593babcfe341b180f9b9e343f4a0c6dcce9356bad","observation_id":"fe8827ce-9052-44d1-92e0-7a77302916cd","resolution":{"observed_at":"2026-08-07T14:40:30.530879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:30.361050Z","title":"and Gimpel, K","venue":null,"work_id":"4e25bab4-6086-4d62-af59-3b9b5d03d676","year":2017},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.968133Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:2a10974ec9b983726d3d020bcd0c70ff4e5e8d85e223601c50e3ea7051e1a186","observation_id":"3ba25226-5d13-4897-a3de-7c796da39e51","resolution":{"observed_at":"2026-08-07T14:40:30.435952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:30.177358Z","title":"Scaling out-of-distribution detection for real-world settings","venue":null,"work_id":"398c6548-938c-4fe0-b55b-1e93d2852c95","year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.082274Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:b04b0497e095fe5c6088e44ceb9e7b4944c5808aec9815ff344bf0dd083bc0b4","observation_id":"a4062068-5289-458a-85d2-5a492051b3cb","resolution":{"observed_at":"2026-08-07T14:40:30.266305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.953005Z","title":"Oodformer: Out-of-distribution detection transformer, 07 2021","venue":null,"work_id":"f93103df-6eaa-47ab-9ca5-d9d213a6db7d","year":2021},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.204048Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:d944e43acd56801283c1347fe241a433adae56082032e679680423c6adc90633","observation_id":"950beb2d-3efc-402a-b4fa-b8799d56f3db","resolution":{"observed_at":"2026-08-07T14:40:30.055100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.717929Z","title":"Openimages: A public dataset for large-scale multi-label and multi-class image classification","venue":null,"work_id":"50b387da-2d87-4b8e-9d85-6f00441dd3d6","year":2017},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.297210Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:d708de922545ba5140642244cf3bae9a993cec07089052a403ecbb9f213eb4ed","observation_id":"a2a06d16-be6f-498c-94d8-9009d67e2fff","resolution":{"observed_at":"2026-08-07T14:40:29.829364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:21.379767Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.379767Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:26456c630faac717c8aa2af5a364168b00ccdd0034e6c95d7b49b23f50f02d40","observation_id":"29a78970-4b69-40b7-93a6-d9bde1df7176","resolution":{"observed_at":"2026-08-07T14:40:21.379767Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:21.455021Z","title":"and Yang, X","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.455021Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:35637ad5d6198caa6506b4c3d0aaa06919c22fcccd0c06d33a4a413ba55714f6","observation_id":"a56d50a3-044e-4758-9241-7f8948e0303c","resolution":{"observed_at":"2026-08-07T14:40:21.455021Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:21.574590Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.574590Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:4e2d4681aa7d3313e4cbcf633816f235bd77d15c8a86b7cd64e4a874f668937b","observation_id":"d4657043-ea7b-43d3-b310-339368223c6f","resolution":{"observed_at":"2026-08-07T14:40:21.574590Z","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":"2026-08-07T14:40:29.593277Z","title":"Training confidence-calibrated classifiers for detecting out-of-distribution samples","venue":null,"work_id":"ec7e7ead-8e92-472f-b860-8007c5172400","year":2018},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.664697Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:0dcf2a678f79ba2a7df0a8d8284479dd29a8e2cffb7426c303708330858f432e","observation_id":"4504b486-2e18-43b2-9e81-e19c52b70752","resolution":{"observed_at":"2026-08-07T14:40:29.632483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.486626Z","title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","venue":null,"work_id":"c1aaea68-31e8-4849-94e9-fc5c2bbd7ea5","year":2018},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.711499Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:fef643b2cac42dc7aa42a8062ec19ddc881c27e769957a832fa9517dec91c52c","observation_id":"616c231e-1ea3-43c2-b277-0a550cea6410","resolution":{"observed_at":"2026-08-07T14:40:29.529118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.388772Z","title":"and Qin, Y","venue":null,"work_id":"5c0b6c08-2b91-4fca-a818-5dc079b9a500","year":2024},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.836496Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:232fad7ae5c2d3671d1746248581b8fab7c9e91b07c96db6bf651164755dcb81","observation_id":"9c2586d3-7220-4fa6-987d-00bc4a385cf3","resolution":{"observed_at":"2026-08-07T14:40:29.422947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.08063","last_updated":"2018-01-29T23:24:56Z","snapshot_observed_at":"2026-07-06T05:39:22.578719Z","submitted_at":"2017-04-26T11:37:22Z","title":"SphereFace: Deep Hypersphere Embedding for Face Recognition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.08063","snapshot_observed_at":"2026-08-07T14:40:21.924362Z","title":"Sphereface: Deep hypersphere embedding for face recognition, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.924362Z"},"links":{"cited_paper":"/paper/1704.08063","citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:bc7c37400119742c7d7a5e102736ab6bf7783a48def24ed2f8e7c357e9fa9078","observation_id":"3698c83f-dfc9-417b-8cc3-ec08c85278a8","resolution":{"observed_at":"2026-08-07T14:40:21.924362Z","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":"2026-08-07T14:40:29.300932Z","title":"Energy-based out-of-distribution detection","venue":null,"work_id":"124ea823-7ab3-4ac8-8ea6-e76092c73f68","year":2020},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.041895Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:016d814dc2fd730f362841dd953c7b78ef1a48ec773317bfa129c0c87a577574","observation_id":"64fbfe4d-42ba-4721-b0ae-7792478303d3","resolution":{"observed_at":"2026-08-07T14:40:29.335943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.184236Z","title":"Gen: Pushing the limits of softmax-based out-of-distribution detection","venue":null,"work_id":"bec61bc4-617c-4553-9744-652bd3edff89","year":2023},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.118217Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:03196857a2b17dafded518c8d64fc37cebe1f7bbd52aba172537acd489f060f2","observation_id":"6470caef-2e13-43c2-b08e-055b52cd34e8","resolution":{"observed_at":"2026-08-07T14:40:29.238066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.09883","last_updated":"2022-04-11T16:03:17Z","snapshot_observed_at":"2026-08-09T14:31:05.781911Z","submitted_at":"2021-11-18T18:59:33Z","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.09883","snapshot_observed_at":"2026-08-07T14:40:22.207327Z","title":"Swin transformer v2: Scaling up capacity and resolution","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.207327Z"},"links":{"cited_paper":"/paper/2111.09883","citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:a8e165d1202a7478b006b027d202dd186b687552dffc10bb9090db8fef60bf17","observation_id":"46ab2a1c-346d-44af-b5dc-24a36fec54a4","resolution":{"observed_at":"2026-08-07T14:40:22.207327Z","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":"2026-08-07T14:40:29.079217Z","title":"Delving into out-of-distribution detection with vision-language representations","venue":null,"work_id":"25a9795c-f489-4ee7-a2b4-d6cedf98f2fc","year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.314597Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:50d47649280ac0e21274de15461a3ed589d28526cd29978701498ec6b0e98391","observation_id":"eef5062a-7595-463d-8938-2f5e86c13f3b","resolution":{"observed_at":"2026-08-07T14:40:29.124875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.975257Z","title":"How to exploit hyperspherical embeddings for out-of-distribution detection? In The Eleventh International Conference on Learning Representations, 2023","venue":null,"work_id":"ab7e8394-e945-47ed-94fb-6baeb38ead2c","year":2023},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.437102Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:22c4c16368f7c1b8290bccb54455a41f819bde9936c79cb2cc851e811c0053a2","observation_id":"a764a9cd-286d-4fb3-934e-3d520121af9f","resolution":{"observed_at":"2026-08-07T14:40:29.013217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17447","last_updated":"2024-05-21T08:36:30Z","snapshot_observed_at":"2026-08-10T01:25:08.923066Z","submitted_at":"2024-05-21T08:36:30Z","title":"How to train your ViT for OOD Detection","version":1},"cited_work":{"arxiv_id":"2405.17447","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.17447","snapshot_observed_at":"2026-08-07T14:40:26.715132Z","title":"How to train your ViT for OOD Detection","venue":"cs.CV","work_id":"124d2ce5-f1d0-40c0-a0cb-83b64709df3b","year":2024},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.546055Z"},"links":{"cited_paper":"/paper/2405.17447","citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:82d5f01af2bd126a7210af578cc2f6d7136873ef05d1e85a39fe1c413e757778","observation_id":"90a5cf1a-3256-45f8-9959-6170b9a73019","resolution":{"observed_at":"2026-08-07T14:40:26.760130Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.849493Z","title":"H., and Gal, Y","venue":null,"work_id":"18f96cf1-4e17-4386-a8a9-5d94ef3157d1","year":2023},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.625513Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:86928dc86452f4047b8a2362e57ac4786ca293aa32cd825bee7507c6daec03a1","observation_id":"bfa07372-7377-4cfa-932a-41047d3102b5","resolution":{"observed_at":"2026-08-07T14:40:28.899730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.745494Z","title":null,"venue":null,"work_id":"33dea3fa-4404-4d12-bb90-fa62d4f75e5e","year":2011},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.713705Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:87772817bad21f63767f9e5943b84aebdb39a0b38e2abee263ff13875bc6c03e","observation_id":"eb1455d9-265c-45d0-a90b-06ba42675b53","resolution":{"observed_at":"2026-08-07T14:40:28.792843Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.631044Z","title":"G., and Teoh, A","venue":null,"work_id":"79ff8884-4b6c-4871-908b-578d2bef1c20","year":2023},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.810998Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:836cd37667c522c84e47802a5ab4f856ce044d728c5d2d7c8deee2c886e691ef","observation_id":"eba3f7af-ed78-4c6f-b5b5-e0dde0353a2b","resolution":{"observed_at":"2026-08-07T14:40:28.685010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:22.883675Z","title":"C., Yoon, J., and Jin Teoh, A","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.883675Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:a5113dce924da57a2395b261daac81b01f9f9ab6c3ffbea1c824e0c8f5aac66c","observation_id":"ab7027aa-384c-4799-b0ac-8d0681046971","resolution":{"observed_at":"2026-08-07T14:40:22.883675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:22.992211Z","title":"W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., and Sutskever, I","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.992211Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:90fd3f49af3dfe8d394b1b3aaf21e57add1861b45837d7ef12ce4252ac737ea5","observation_id":"b07af905-35fd-4289-aa64-b4fa1367ee2b","resolution":{"observed_at":"2026-08-07T14:40:22.992211Z","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":"2026-08-07T14:40:28.517491Z","title":"K., Stoyanov, D., and Bhattarai, B","venue":null,"work_id":"eb8c6a37-6481-4095-af11-8e926791dfed","year":2024},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.127858Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:19eb1cb4b35b14793d69194269c9da670d74a7fbea38fa956f13949f7499c0cd","observation_id":"828cec6b-caf4-4708-b085-297a073a936f","resolution":{"observed_at":"2026-08-07T14:40:28.564153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09022","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":"2026-08-07T14:40:23.217297Z","title":"G., Padhy, S., and Lakshminarayanan, B","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.217297Z"},"links":{"cited_paper":"/paper/2106.09022","citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:bfe3a96a91230e85355c6ab272fbb0b4ad23b6a4e17aa10d6de084e4bb9d8de2","observation_id":"afd41902-d8c4-4b79-8967-9dc60e2de417","resolution":{"observed_at":"2026-08-07T14:40:23.217297Z","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":"2026-08-07T14:40:28.425818Z","title":"Spreading vectors for similarity search","venue":null,"work_id":"c638931d-10f0-4705-ae4f-b77a90900192","year":2018},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.335586Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:e98bca338061e795b8372ce10f3c3cbf8a29df048fa69078458d237a58d42792","observation_id":"a801aa1d-2280-4367-a33d-9ce42eef2d77","resolution":{"observed_at":"2026-08-07T14:40:28.457111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.307267Z","title":"Ssd: A unified framework for self-supervised outlier detection","venue":null,"work_id":"a24228ed-1a1a-49b5-ad0e-a1dedf145708","year":2021},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.460948Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:62a6b1efa7408428a4e797ae0dde58a71022b4862e8270c329d9c09545096800","observation_id":"c685b093-65a2-4864-8358-08a74f15e18d","resolution":{"observed_at":"2026-08-07T14:40:28.358926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.195232Z","title":"P., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., and Beyer, L","venue":null,"work_id":"e0cc2fe4-3055-4bd2-9f94-62ca82058fe2","year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.581373Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:4a6d3a926cff8e4679388cdc633085fe8f92c600fbea5c306777ff0304a43166","observation_id":"2d32bf22-cc6f-40a8-88e5-c2b13b7e31bd","resolution":{"observed_at":"2026-08-07T14:40:28.246126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.031838Z","title":"React: Out-of-distribution detection with rectified activations","venue":null,"work_id":"f1f640b3-d9fb-4794-8f4b-96b536f3d8a0","year":2021},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.672180Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:3280044c46a1b4715cb3cf78e8046766edd5b6c004e6f76b3517609bb064e9d9","observation_id":"c6d31dec-d772-449e-9357-3c625da9605f","resolution":{"observed_at":"2026-08-07T14:40:28.135868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:27.907113Z","title":"Out-of-distribution detection with deep nearest neighbors","venue":null,"work_id":"ff5d536c-fb19-4c9d-8d1f-955ff3f8bbd6","year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.763063Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:c2a7dac480d2033350c1157a03a82413a720ee1ba22d9ef0cd549b596952a033","observation_id":"e0d13251-92d5-4fed-9950-f08a30bd858e","resolution":{"observed_at":"2026-08-07T14:40:27.961753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:27.815003Z","title":"Csi: Novelty detection via contrastive learning on distributionally shifted instances","venue":null,"work_id":"30066ec4-38fb-428b-8981-18890689858c","year":2020},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.882210Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:41105c41623c6d24ec77619397b4602fd4838744466e3be1adf69f6bfad5495c","observation_id":"3b4c13de-9ad9-4356-beea-004d4b9d2c2e","resolution":{"observed_at":"2026-08-07T14:40:27.858147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:27.726986Z","title":"Hyperparameter-free out-of-distribution detection using cosine similarity","venue":null,"work_id":"8f43826d-7277-46cc-a938-4cbcae389eba","year":2020},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.980692Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:f2f7efab0ec9481731d491683047b90f41ab6237be9e335466779a63bd8b62ae","observation_id":"453932ac-aa92-4765-b293-a0425cd85386","resolution":{"observed_at":"2026-08-07T14:40:27.757331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:27.628337Z","title":"Deit iii: Revenge of the vit","venue":null,"work_id":"357d2dd4-dedc-4167-bebe-b0bb0ea46406","year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.083265Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:6ff5d40f4e0b3c89f26793c2759e81e3c4df4a1557de86e4a8dbc788d603c92b","observation_id":"3eb997f6-dc1f-41a1-b262-8cb8a99be4c5","resolution":{"observed_at":"2026-08-07T14:40:27.672457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:27.531022Z","title":"The inaturalist species classification and detection dataset","venue":null,"work_id":"3f8c6c3a-121c-4101-8908-1f6bdeec842f","year":2018},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.179435Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:db2c8655559eb0e8eedf6fd01b0c3fb6974a13f4e75070654946702ca2751e6c","observation_id":"e920e250-9ac4-4eed-957c-10a7d55b4fec","resolution":{"observed_at":"2026-08-07T14:40:27.568784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:27.418270Z","title":"Open-set recognition: a good closed-set classifier is all you need? In International Conference on Learning Representations, 2022","venue":null,"work_id":"945e1c8a-bfee-467b-8777-cbcafc6fae72","year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.281813Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:f02d4c52cb5f3e98a7a09447fb0d271357345e7d9ce09ef02dee3868c13763b7","observation_id":"c43afc05-19b7-4b9b-9d66-7717533a8967","resolution":{"observed_at":"2026-08-07T14:40:27.471053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:27.319298Z","title":"Vim: Out-of-distribution with virtual-logit matching","venue":null,"work_id":"eb06218b-02ca-4598-82fb-69708e2966b2","year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.397142Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:fd36548b14cd76bb887875e61e69fda9c31d5fbecaba9a847e7908dcefaff45f","observation_id":"b3364385-0d71-4c01-95b0-80518b03c72b","resolution":{"observed_at":"2026-08-07T14:40:27.358038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:27.213876Z","title":"Mitigating neural network overconfidence with logit normalization","venue":null,"work_id":"203b84d4-2812-4d3b-8824-978517a4a44d","year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.538450Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:a9b569041b57e0ead1aa67f8fc7aa4fd638deb3242fb4b4c6773b379c0a4ff1d","observation_id":"624f374c-4538-4efc-8619-6aa5ec82c1ed","resolution":{"observed_at":"2026-08-07T14:40:27.256471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:24.616716Z","title":"Pytorch image models","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.616716Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:319aaecc0e432f95e9145cbeca616971c5705643440af41ffd7a5b2d93c7b4e6","observation_id":"5a21c0bd-46b4-4280-84ba-ea5f7e19f0f3","resolution":{"observed_at":"2026-08-07T14:40:24.616716Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:24.720506Z","title":null,"venue":null,"work_id":null,"year":1968},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.720506Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:148a9efe74c35f07008566ae4b4b00d886f15f7ab8a0ccf8483b3823a4ede7fa","observation_id":"772b4dbe-d10a-4391-b2f3-348acdb043ab","resolution":{"observed_at":"2026-08-07T14:40:24.720506Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.00808","last_updated":"2023-01-02T18:59:31Z","snapshot_observed_at":"2026-08-08T08:01:57.986531Z","submitted_at":"2023-01-02T18:59:31Z","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.00808","snapshot_observed_at":"2026-08-07T14:40:24.811478Z","title":"S., and Xie, S","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.811478Z"},"links":{"cited_paper":"/paper/2301.00808","citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:a1a055f0c42ae43774ed2e705d400351794632a083b82489ca4c663640aca961","observation_id":"9c340e9d-7bb0-4343-a145-7ed149a86112","resolution":{"observed_at":"2026-08-07T14:40:24.811478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07242","last_updated":"2022-10-13T17:59:57Z","snapshot_observed_at":"2026-08-03T10:41:24.763234Z","submitted_at":"2022-10-13T17:59:57Z","title":"OpenOOD: Benchmarking Generalized Out-of-Distribution Detection","version":1},"cited_work":{"arxiv_id":"2210.07242","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.07242","snapshot_observed_at":"2026-08-07T14:40:26.392382Z","title":"OpenOOD: Benchmarking Generalized Out-of-Distribution Detection","venue":"cs.CV","work_id":"55adf863-b8a9-4ea8-9d3d-01b625a4eead","year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.913676Z"},"links":{"cited_paper":"/paper/2210.07242","citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:7a1d8c5e9d942bdb384661ac0d403310f67aff2e825285b8523c6d3eaacdb18d","observation_id":"3a4c49d6-02a2-4ac7-a3fe-8109ba404f1f","resolution":{"observed_at":"2026-08-07T14:40:26.472567Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:27.107108Z","title":"Neural collapse with normalized features: A geometric analysis over the riemannian manifold","venue":null,"work_id":"8a0ee225-1bed-48ef-b0fd-45cbddd35b92","year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.032057Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:b814561e005d0e68e585c3e94658569cb34c0a0415b804d730a43de0ef494277","observation_id":"97df6245-0c6c-4d48-b2a9-709aa54cf2ee","resolution":{"observed_at":"2026-08-07T14:40:27.151468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2020.29881","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:26.143072Z","title":null,"venue":null,"work_id":"95cd4d03-6f48-48fd-8ff1-38686e51d962","year":2020},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.131238Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:6701a681c2369c4fa6a41e4a47ed0fdcfc4bbb6a3c61da8525bf27956f4e2d2e","observation_id":"4cfea677-b615-47e9-8295-adbe5950b0f7","resolution":{"observed_at":"2026-08-07T14:40:26.271030Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s40747-022-00695-9","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":"Anomaly detection for high-dimensional space using deep hypersphere fused with probability approach","venue":"Complex & Intelligent Systems","work_id":"5acdd57c-537e-4723-9b84-a8d70f4f64a6","year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.215284Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:3f6a3906ccddd70bb6b8a5529d6aa82b7cea3f82689165ca569710ed11d8b583","observation_id":"05e20f2c-7406-482f-972a-870f1f232aed","resolution":{"observed_at":"2026-08-07T14:40:25.682398Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:25.319404Z","title":"Places: A 10 million image database for scene recognition","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.319404Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:1744aeb9c7b0beb713aa7fa742aa2d27e836b1b46e6ce8d278e30b95f33a14cf","observation_id":"3a97fd66-afd2-4f0e-a574-2707c7bb3a5e","resolution":{"observed_at":"2026-08-07T14:40:25.319404Z","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":"2020.30431","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:25.910812Z","title":"M., and Ou, W","venue":null,"work_id":"8e0b559f-3fd7-4cdc-a862-239118bf339d","year":2022},"citing_paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.431563Z"},"links":{"citing_paper":"/paper/2505.18032"},"observation_digest":"sha256:98b6ce16b991e41f1b1cf78691fbf598a0d0af77641383bd58ac1de1483e90a5","observation_id":"367d7ad5-db52-4bc6-b26a-6f849e762ea4","resolution":{"observed_at":"2026-08-07T14:40:25.979365Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.18032","last_updated":"2025-05-23T15:36:22Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T08:34:49.462191Z","submitted_at":"2025-05-23T15:36:22Z","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization"},"reference_resolution":{"displayed":56,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":19,"verified_exact":4,"verified_fuzzy":31},"total_outbound_references":56},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 4 inbound Pith citation observations for arXiv:2505.18032."}