{"as_of":"2026-08-22T19:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9b8b6cadf72676648fe71ad95fc80a898accbf6cb075d1ff8c28429e62ed01b3","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:27:20.022776Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2505.12952/citation-record","integrity":"/paper/2505.12952/integrity","json":"/paper/2505.12952/citation-record.json","paper":"/paper/2505.12952"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:27:20.606388Z","title":"Latent space autore- gression for novelty detection","venue":null,"work_id":"b6338a8a-e979-4aa3-9ffc-b1ebe034baaf","year":2019},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.857310Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:2d2fdbfb7feea7bb2aa54876f92801fd07075e1beb3b62179fca10cb09e49c9e","observation_id":"4ba39bc2-2cc0-4683-96b5-ede86dc30d64","resolution":{"observed_at":"2026-08-15T20:27:20.609980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03502","last_updated":"2024-02-05T20:36:33Z","snapshot_observed_at":"2026-08-19T19:30:09.852084Z","submitted_at":"2024-02-05T20:36:33Z","title":"How Does Unlabeled Data Provably Help Out-of-Distribution Detection?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03502","snapshot_observed_at":"2026-08-15T20:27:19.892958Z","title":"How does unlabeled data prov- ably help out-of-distribution detection?arXiv preprint arXiv:2402.03502,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.892958Z"},"links":{"cited_paper":"/paper/2402.03502","citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:594211350f3c0824e6c9261cfbe7eaf1bd0651423b13c314530bb9fe828b12fc","observation_id":"7dc145c2-9d0a-4a24-9da1-5ed0af216fbb","resolution":{"observed_at":"2026-08-15T20:27:19.892958Z","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":"2026-08-15T20:27:20.538122Z","title":"On the learnability of out-of-distribution de- tection.Journal of Machine Learning Research, 25,","venue":null,"work_id":"5f930b6c-7bb1-450b-adcf-9ee9fc129d87","year":2024},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.896994Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:4c788ec9f61b8c3e79d475e09bf39daf776d025dd4827a865a8109a476069222","observation_id":"65c45275-2594-45a0-9f5f-7f8a6126b795","resolution":{"observed_at":"2026-08-15T20:27:20.542199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.04461","last_updated":"2022-12-08T18:36:41Z","snapshot_observed_at":"2026-08-19T19:30:34.354840Z","submitted_at":"2022-12-08T18:36:41Z","title":"Leveraging Unlabeled Data to Track Memorization","version":1},"cited_work":{"arxiv_id":"2212.04461","doi":null,"metadata_source":"pith","pith_arxiv_id":"2212.04461","snapshot_observed_at":"2026-08-15T20:27:20.213741Z","title":"Leveraging Unlabeled Data to Track Memorization","venue":"cs.LG","work_id":"5298e487-a343-4eb1-b912-2daeac0b2f5f","year":2022},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.900606Z"},"links":{"cited_paper":"/paper/2212.04461","citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:47cb2c2f82f9d310bcffa8628402a35f378ce649e0a5d0b82683c16fc0581f3e","observation_id":"01a2c8a5-1087-41bc-9a22-dc7c7c5d0c4e","resolution":{"observed_at":"2026-08-15T20:27:20.218723Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.525432Z","title":"Who said what: Modeling indi- vidual labelers improves classification","venue":null,"work_id":"6367c612-1bbd-43e2-877b-9c9cab9cb26b","year":2018},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.904650Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:904e3d106537bad2677443cecc27ce54837daf569707abb10534ea0f3906620a","observation_id":"9c832b88-d17a-45ce-9f20-5ba35a1b10eb","resolution":{"observed_at":"2026-08-15T20:27:20.529427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-15T20:27:19.908037Z","title":"A baseline for detecting misclassified and out-of- distribution examples in neural networks.arXiv preprint arXiv:1610.02136,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.908037Z"},"links":{"cited_paper":"/paper/1610.02136","citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:3e6c9efaee9948781982ba9b16da370379e9725fc195517b3998889c13311794","observation_id":"3a55f1d2-7201-4cdd-8a37-b4b35edd92ef","resolution":{"observed_at":"2026-08-15T20:27:19.908037Z","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":"2026-08-15T20:27:20.513675Z","title":"Training ood de- tectors in their natural habitats","venue":null,"work_id":"6309296e-3bf9-4dd8-b04c-807165cbcffe","year":2022},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.915573Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:1be5f94e2a807a227604e11892d3b77343c813d69ea673d3e92d485c4a1a107f","observation_id":"80b2202b-a974-447a-b99f-858044fc2883","resolution":{"observed_at":"2026-08-15T20:27:20.517722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.502355Z","title":"Learning multiple lay- ers of features from tiny images","venue":null,"work_id":"63f9ac52-9644-4226-8b3d-5e5f54ab7771","year":2009},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.919493Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:aceced1afdde873d38a07048382ad3b64f891316e9ef2be5521758541e6f4190","observation_id":"72e171af-52d9-457c-bb00-83edc5ee218f","resolution":{"observed_at":"2026-08-15T20:27:20.506244Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.09325","last_updated":"2018-02-23T19:42:15Z","snapshot_observed_at":"2026-08-14T20:10:11.251346Z","submitted_at":"2017-11-26T02:50:39Z","title":"Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.09325","snapshot_observed_at":"2026-08-15T20:27:19.923170Z","title":"Training confidence-calibrated classifiers for detecting out-of-distribution samples.arXiv preprint arXiv:1711.09325,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.923170Z"},"links":{"cited_paper":"/paper/1711.09325","citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:6e983b5b619a8067814bee75e64048dafda5bf39ff775632652ba7397c294f9b","observation_id":"94e07c3e-5284-49da-988e-212f5d9f6e24","resolution":{"observed_at":"2026-08-15T20:27:19.923170Z","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":"2026-08-15T20:27:20.489659Z","title":"A simple unified framework for detect- ing out-of-distribution samples and adversarial attacks","venue":null,"work_id":"a1e5db24-4b44-496b-855c-7d3e3074ce1e","year":2018},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.927097Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:6db4efe014d8c205899a05b228470ad9b199f6e50da1058645843b13f76bda2e","observation_id":"dad90616-7ddd-404f-8914-53294a4c5906","resolution":{"observed_at":"2026-08-15T20:27:20.494251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.477748Z","title":"Disc: Learning from noisy labels via dynamic instance-specific selection and correction","venue":null,"work_id":"c080b21a-cabb-4374-a78b-646683617fcc","year":2023},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.930965Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:582e49183a873774f34be1f1b007b97a6e396b1d1722257f186092188733084d","observation_id":"5c9549a4-2a33-4c97-bd4e-fb0ef2186c83","resolution":{"observed_at":"2026-08-15T20:27:20.481635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.02690","last_updated":"2020-08-30T16:50:36Z","snapshot_observed_at":"2026-08-21T16:29:45.619602Z","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":"2026-08-15T20:27:19.934727Z","title":"Enhancing the reliability of out-of-distribution image detection in neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.934727Z"},"links":{"cited_paper":"/paper/1706.02690","citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:5f4def941c14b3b95fc79f8522d1169e91456391721197969c2c982eb3716f52","observation_id":"b634f056-a99c-4f86-b8fa-d33a2e2a9921","resolution":{"observed_at":"2026-08-15T20:27:19.934727Z","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":"2026-08-15T20:27:20.466815Z","title":"Mitigating label noise through data ambigua- tion","venue":null,"work_id":"095efc00-6b5f-4a97-a5b7-ed0867af2227","year":2024},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.938436Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:1b86433794cbdedd9b6ea404ca7e2458c85a3d6f78f8a9a4203701b10ac9b7a1","observation_id":"58639689-8084-49a9-9b01-b5d4f99c3018","resolution":{"observed_at":"2026-08-15T20:27:20.470710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.455992Z","title":"Learning the latent causal structure for modeling label noise","venue":null,"work_id":"11c9932f-b96e-4d74-8c23-9af084aa9dd3","year":2024},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.941867Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:193945c438a48755df4ffb301acd2c13ae57e2c6ec2d6223ed0cc88d6eab6e5e","observation_id":"41dbebfe-93bd-42a0-a532-0db231f2a84e","resolution":{"observed_at":"2026-08-15T20:27:20.459808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.432895Z","title":"Open set learning with counterfactual images","venue":null,"work_id":"6b7abcde-225b-49ad-b613-dc56adf763ea","year":2018},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.948548Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:75cc5e0e0d77964ebc5fa9c49aed0421106d6d4ede32bc23beb33a4b25589e6b","observation_id":"41651771-4d40-46c6-92ad-814cb19000e0","resolution":{"observed_at":"2026-08-15T20:27:20.436827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:19.952407Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.952407Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:1fb826f0ac6e11d45ce5ed710f37cd45d0985ec37a27842db18fbb3dfe1b4d19","observation_id":"ecfd6e2a-368c-4102-aba3-801740c7509d","resolution":{"observed_at":"2026-08-15T20:27:19.952407Z","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":"2026-08-15T20:27:20.380316Z","title":"Dice: Lever- aging sparsification for out-of-distribution detection","venue":null,"work_id":"06d2e1fd-4950-4033-af4f-84e5bf46058b","year":2022},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.967246Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:c659a6f555dafbb4c34fdd74e1a4e45d58cb1c5ab08021926f5351d899a0b043","observation_id":"a291e811-63c2-4f2a-8ec2-b144798ff65a","resolution":{"observed_at":"2026-08-15T20:27:20.384718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.368544Z","title":"React: Out-of-distribution detection with rectified activa- tions.Advances in Neural Information Processing Sys- tems, 34:144–157,","venue":null,"work_id":"f8c1bc50-bce3-40c4-bc43-0e8af05a5c5f","year":2021},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.970865Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:7202e3e8729aa7f241a68f5d3e47a400f064214cf225f1ea7eb5029419377fe6","observation_id":"4cc727ec-376d-4dbf-a356-7078403d6211","resolution":{"observed_at":"2026-08-15T20:27:20.372451Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.357249Z","title":"Out-of-distribution detection with deep near- est neighbors","venue":null,"work_id":"97dd380e-4c81-4ed7-8555-661e5a7ae2db","year":2022},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.974212Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:f9a4364ea42548ab7cf9ea39c117d433ebb913c96d649a53c759090d76fb9cdf","observation_id":"2acedaa0-278f-4965-9164-82844ce4c01b","resolution":{"observed_at":"2026-08-15T20:27:20.361137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.345470Z","title":"Csi: Novelty detection via contrastive learning on distributionally shifted in- stances.Advances in neural information processing sys- tems, 33:11839–11852,","venue":null,"work_id":"478bec22-5c03-4c74-9f2e-ce202d0c8cec","year":2020},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.977654Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:a5a2e1e1187ceca759b8a85e01e31749c5324ec5ed2850fcacf8327b5dbacae2","observation_id":"6ca1e30e-abd4-4699-a2f5-331a818fd576","resolution":{"observed_at":"2026-08-15T20:27:20.349455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06207","last_updated":"2022-04-13T17:59:07Z","snapshot_observed_at":"2026-08-16T17:49:53.757905Z","submitted_at":"2021-10-12T17:58:59Z","title":"Open-Set Recognition: a Good Closed-Set Classifier is All You Need?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.06207","snapshot_observed_at":"2026-08-15T20:27:19.981021Z","title":"Open-set recognition: A good closed-set classifier is all you need.the International Con- ference on Learning Representations, abs/2110.06207,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.981021Z"},"links":{"cited_paper":"/paper/2110.06207","citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:fc8a145ff0f61a275660959fee7aa2b74020011b6554b19736f14618a45d8dea","observation_id":"019c12d3-0942-41b4-a003-dcce3d609190","resolution":{"observed_at":"2026-08-15T20:27:19.981021Z","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":"2026-08-15T20:27:20.333574Z","title":"Vim: Out-of-distribution with virtual- logit matching","venue":null,"work_id":"2269e780-37c9-4d2e-bc60-aa89f3df5f91","year":2022},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.984602Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:25c7c4fd7e6e69ff31c20def5ae7e71778d765b3cf6ca7740c11e715e68634b8","observation_id":"5bc2d8ca-4502-4525-aa80-b32a0503ad43","resolution":{"observed_at":"2026-08-15T20:27:20.337894Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:19.991670Z","title":"Generalized out-of-distribution detec- tion: A survey.International Journal of Computer Vision, 132(12):5635–5662,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.991670Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:ab4915e1f4b23c049cc459514f8b0c60d6a1b72b07716a7b72d1aad4507afc15","observation_id":"aec83461-6a52-4845-b857-a6a770f801e4","resolution":{"observed_at":"2026-08-15T20:27:19.991670Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1506.03365","last_updated":"2016-06-04T09:51:30Z","snapshot_observed_at":"2026-08-08T13:26:17.517503Z","submitted_at":"2015-06-10T15:38:47Z","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.03365","snapshot_observed_at":"2026-08-15T20:27:19.995111Z","title":"Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop.arXiv preprint arXiv:1506.03365,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.995111Z"},"links":{"cited_paper":"/paper/1506.03365","citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:c7dec913f08c7f19bba9244ef7c1e11494cd62cd890ba2c46d2ca56d557bbab3","observation_id":"cf0cfb44-4266-4f9e-ae38-c9b0afd3c24b","resolution":{"observed_at":"2026-08-15T20:27:19.995111Z","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":"2026-08-15T20:27:20.302310Z","title":"Ctrl: Clus- tering training losses for label error detection.IEEE Trans- actions on Artificial Intelligence,","venue":null,"work_id":"16eaa942-1bcf-48ac-a2fc-2416c3c24396","year":2024},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.999462Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:08eac82ebde5c894d82dbb76eaff9891df0d13d396f826716892205ef307fad6","observation_id":"056bd60c-9705-4b1c-a5d7-77f801f83903","resolution":{"observed_at":"2026-08-15T20:27:20.306196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07146","last_updated":"2017-06-14T06:06:48Z","snapshot_observed_at":"2026-08-16T07:54:28.918946Z","submitted_at":"2016-05-23T19:27:13Z","title":"Wide Residual Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07146","snapshot_observed_at":"2026-08-15T20:27:20.003888Z","title":"Wide residual net- works.arXiv preprint arXiv:1605.07146,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:20.003888Z"},"links":{"cited_paper":"/paper/1605.07146","citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:3738545d18883a4fd299c6c42dbc2c9c39a174e6aa603140d98ad7b8d375d088","observation_id":"ec2788e7-ac04-4d3b-81bc-b55369a84781","resolution":{"observed_at":"2026-08-15T20:27:20.003888Z","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":"2026-08-15T20:27:20.290675Z","title":"Out-of-distribution detection learning with unreliable out- of-distribution sources.Advances in Neural Information Processing Systems, 36:72110–72123,","venue":null,"work_id":"ad53bbf6-5fa9-4854-a21f-3a382eb69a7c","year":2023},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:20.007936Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:5d4f4033604ea860f07b81c316d85d538fc54409a87e7faec86e6a6559fd9a4a","observation_id":"fa5be5e6-c937-48d5-b051-5917683a95c9","resolution":{"observed_at":"2026-08-15T20:27:20.295032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.279644Z","title":"Places: A 10 million image database for scene recognition.IEEE transactions on pattern analysis and machine intelligence, 40(6):1452–1464,","venue":null,"work_id":"2dc63f06-e0ef-4d4a-99cc-227ec450ef89","year":2017},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:20.011454Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:31b84d2704229c95ce54d79570e5ccf9994416d5dc535082f2e8868bfe7b2ae9","observation_id":"c6a742a2-ce4c-4ab6-a877-a226cb74779b","resolution":{"observed_at":"2026-08-15T20:27:20.283393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.268526Z","title":"Diversified outlier exposure for out- of-distribution detection via informative extrapolation","venue":null,"work_id":"828deb9e-7127-4c2b-9b3c-3b6442ba7421","year":2023},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:20.015067Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:48d854aa6f284c228518dcab7569bfd433306ba2a72408d17c44a11f6efe5f44","observation_id":"e7caf53d-1784-4260-96c9-a54c937281f0","resolution":{"observed_at":"2026-08-15T20:27:20.272420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.257451Z","title":null,"venue":null,"work_id":"a9c06887-e99f-4c9a-a114-b07d71092b4c","year":2024},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:20.018892Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:0ac961b2ad0c70d50e31172297dbe17e517d26dcab943fa6c64a646f8a34d3e8","observation_id":"cca61f43-93f7-4dac-816d-d6f4d0f73f70","resolution":{"observed_at":"2026-08-15T20:27:20.261005Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"7398.7817","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:27:20.121097Z","title":"Letx=v+z i, wherezi∼N(0,σ 2Id×d)","venue":null,"work_id":"9b374459-f9ff-4eb9-ae45-7803836ba496","year":null},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:20.022776Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:ae1c9dd2c6d8b2c437681d39447a1e31ef84b5402f7a5f2b38e0e61eface9086","observation_id":"7a441b8d-c496-4b8b-9688-178a9463e41c","resolution":{"observed_at":"2026-08-15T20:27:20.130526Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.09858","last_updated":"2023-05-01T22:27:08Z","snapshot_observed_at":"2026-08-16T16:31:08.845997Z","submitted_at":"2022-09-20T17:09:49Z","title":"Extremely Simple Activation Shaping for Out-of-Distribution Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.09858","snapshot_observed_at":"2026-08-15T20:27:19.885352Z","title":"Extremely simple ac- tivation shaping for out-of-distribution detection.arXiv preprint arXiv:2209.09858,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.885352Z"},"links":{"cited_paper":"/paper/2209.09858","citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:fcac331cd19ec1ca03f0eedee1147972395a0565a863cdad3e8c0da023665d0d","observation_id":"f72d01a0-ace5-4150-b319-b1d833eb832f","resolution":{"observed_at":"2026-08-15T20:27:19.885352Z","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":"2026-08-15T20:27:20.415651Z","title":"Deep neural networks are easily fooled: High con- fidence predictions for unrecognizable images","venue":null,"work_id":"32cc7ac0-6673-45cb-85a1-c1f8fae370a1","year":2015},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2011,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.956041Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:ead39caf92f2c63b2570ad92d6c0d1186bba7d263df1b5f16870fb97c48ff119","observation_id":"75e2a0ef-c3f7-4d43-8dfb-0c24bea800f7","resolution":{"observed_at":"2026-08-15T20:27:20.419202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:19.881633Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.881633Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:8cd73f14243361489b98eb0ddb174b4f678d61a80ddf315268c45d6d086a0ef1","observation_id":"189e4239-0712-4e2e-b038-9fdbc18156db","resolution":{"observed_at":"2026-08-15T20:27:19.881633Z","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":"2026-08-15T20:27:20.404882Z","title":"Gradient- regularized out-of-distribution detection","venue":null,"work_id":"8421144d-8790-450f-8d6c-437f93e74ccb","year":2025},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.959951Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:f050ce41700e7ae70ef6268d6ac05b7932d78a84068f496630d7c2aab15b12a7","observation_id":"3e4d5327-01e5-40e8-aac1-8c2b8f2f98c6","resolution":{"observed_at":"2026-08-15T20:27:20.408493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.04606","last_updated":"2019-01-28T20:34:44Z","snapshot_observed_at":"2026-08-14T17:45:07.132382Z","submitted_at":"2018-12-11T18:49:50Z","title":"Deep Anomaly Detection with Outlier Exposure","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.04606","snapshot_observed_at":"2026-08-15T20:27:19.911859Z","title":"Deep anomaly detection with out- lier exposure.arXiv preprint arXiv:1812.04606,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.911859Z"},"links":{"cited_paper":"/paper/1812.04606","citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:1d19c2de8e98aeff59a5eab182762226140fdf4459b3faaecdba22fb30c2cf49","observation_id":"7f5920a7-244c-4e42-a241-a6c0b00a2cd1","resolution":{"observed_at":"2026-08-15T20:27:19.911859Z","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":"2026-08-15T20:27:20.584049Z","title":"Gradorth: a simple yet efficient out-of-distribution detection with or- thogonal projection of gradients.Advances in Neural In- formation Processing Systems, 36,","venue":null,"work_id":"25cde1b3-1f1d-47ad-ad5b-e1c53f370f3d","year":2024},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.865490Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:554a1f19274cc12b49dbbfb9bb5643662e793cdc217834970d7e7b4aa43ac99d","observation_id":"294d49e9-29a0-42be-ba7f-8f3b8ff90798","resolution":{"observed_at":"2026-08-15T20:27:20.588292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.572851Z","title":"Atom: Robustifying out-of- distribution detection using outlier mining","venue":null,"work_id":"aa1c8d15-feb8-454a-ba46-cf99f16fd652","year":2021},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.873673Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:e12651313f252d14bb988839173baa04ffcb9034643282fef6d9f9e68650d00d","observation_id":"9e805fc3-e312-4ede-a0a1-3a846f6ef47c","resolution":{"observed_at":"2026-08-15T20:27:20.577004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.595401Z","title":"A closer look at memo- rization in deep networks","venue":null,"work_id":"cd1fb1ed-3269-4ece-98f1-7a4d3138e63b","year":2017},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.861548Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:629300cfe0e331c264f78792e9b1c69f95a88ea71f8d3318f472f215f33a5591","observation_id":"aff01ac8-f2e1-4d24-bf8c-0dc36009701a","resolution":{"observed_at":"2026-08-15T20:27:20.599326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.444730Z","title":"Predictive uncertainty estimation via prior networks.Ad- vances in neural information processing systems, 31,","venue":null,"work_id":"205c3b52-640a-414c-9404-b472eda7e6df","year":2018},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.945256Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:35ebb2f70169334079ecbad7ad74f990a8aa32ce0d145e712994c9db62f5ceb7","observation_id":"db6ce2bd-ee11-484f-b25a-23efb1177582","resolution":{"observed_at":"2026-08-15T20:27:20.448561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:19.877510Z","title":"Describing textures in the wild","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.877510Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:3e0c2aafd481bef387a8a1b41f0c87c31641584309e71c0e0d61d118a1ecb84b","observation_id":"b7633e28-fb52-460d-b0b0-b4cfceccc9c0","resolution":{"observed_at":"2026-08-15T20:27:19.877510Z","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":"2026-08-15T20:27:20.549295Z","title":"Unknown-aware object detection: Learn- ing what you don’t know from videos in the wild","venue":null,"work_id":"df6d9044-6abd-4a54-aa81-8951abfbbff9","year":2022},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.889292Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:b9dbb6ae6d773087e29e61400cb90f2f91bceeb6d0f29a50ff9ef550ef1381df","observation_id":"39392d3a-b17b-4e27-9ac5-43920367839d","resolution":{"observed_at":"2026-08-15T20:27:20.553320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:27:20.322403Z","title":"Mitigating neural net- work overconfidence with logit normalization","venue":null,"work_id":"3bcda8e2-b968-4966-bec2-1909092c175a","year":2022},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.988306Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:65e26b5105938740e5e1014cdf6d1453f9f95b38d0cc3731490851a614acc4a2","observation_id":"ae3eee74-7f21-4b77-95aa-44fd264cb724","resolution":{"observed_at":"2026-08-15T20:27:20.326351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1808.07703","last_updated":"2018-10-01T09:19:58Z","snapshot_observed_at":"2026-08-14T18:37:58.408406Z","submitted_at":"2018-08-23T11:28:34Z","title":"Discriminative out-of-distribution detection for semantic segmentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.07703","snapshot_observed_at":"2026-08-15T20:27:19.869518Z","title":"Discriminative out-of- distribution detection for semantic segmentation.arXiv preprint arXiv:1808.07703,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.869518Z"},"links":{"cited_paper":"/paper/1808.07703","citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:47cc01466a78513824728d293c420cb6f42ae338ed217772a8974f722872878d","observation_id":"7d7ab5e2-85bd-4d92-a584-e6b0e30d98a0","resolution":{"observed_at":"2026-08-15T20:27:19.869518Z","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":"2026-08-15T20:27:20.393652Z","title":"Learning from noisy labels with deep neural networks: A survey.IEEE transactions on neural networks and learning systems, 34(11):8135–8153,","venue":null,"work_id":"5e2cd276-03f5-48cf-ae6d-670c758e5655","year":2022},"citing_paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T20:27:19.963321Z"},"links":{"citing_paper":"/paper/2505.12952"},"observation_digest":"sha256:0eba04546322bd3ff5c23ebdd581f08c1f25f6a6bc1ff8914390b226f90bf5a6","observation_id":"cff0b620-97f4-4e0f-9644-06adf442aea7","resolution":{"observed_at":"2026-08-15T20:27:20.397500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.12952","last_updated":"2025-05-19T10:44:52Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T19:30:13.129031Z","submitted_at":"2025-05-19T10:44:52Z","title":"LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":1,"verified_fuzzy":28},"total_outbound_references":45},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2505.12952."}