{"as_of":"2026-08-10T08:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a64f47f573147d5a8d3c79956900589a12ee3fe6be445c8f248230354721aca0","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T08:24:39.829152Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2601.19947/citation-record","integrity":"/paper/2601.19947/integrity","json":"/paper/2601.19947/citation-record.json","paper":"/paper/2601.19947"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T08:24:33.793362Z","title":"Food-101 – mining discriminative components with random forests","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:33.793362Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:31be3755f1e64024082fa741a6f337d5ffd0789df5f496a9e4946ceb37ade328","observation_id":"c77c11ee-4a88-44c2-b491-353b3ca41a04","resolution":{"observed_at":"2026-08-03T08:24:33.793362Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.13173","last_updated":"2024-09-20T03:01:13Z","snapshot_observed_at":"2026-08-07T04:36:34.092351Z","submitted_at":"2024-09-20T03:01:13Z","title":"Bilateral Sharpness-Aware Minimization for Flatter Minima","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.13173","snapshot_observed_at":"2026-08-03T08:24:34.540131Z","title":"Bilateral sharpness- aware minimization for flatter minima.arXiv preprint arXiv:2409.13173,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:34.540131Z"},"links":{"cited_paper":"/paper/2409.13173","citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:245ffabf9f26a53255615109f9739cb2e9e870a182778e3a854cd2c9baa3f949","observation_id":"f7fb3e0f-bafa-488f-832b-e1d1232317cf","resolution":{"observed_at":"2026-08-03T08:24:34.540131Z","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":"2026-08-03T08:24:35.000687Z","title":"Generalized jensen-shannon divergence loss for learning with noisy labels.Advances in Neural Information Processing Systems, 34:30284–30297,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:35.000687Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:8bac541d44cb6415f96ae23ad2491f9b4e00c22f6e5c95f803039bf537d7683f","observation_id":"78a79d3d-5a4d-430a-ae84-17ca7d77b157","resolution":{"observed_at":"2026-08-03T08:24:35.000687Z","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":"2026-08-03T08:24:35.156451Z","title":"Sharpness-aware min- imization for efficiently improving generalization.Inter- national Conference on Learning Representations,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:35.156451Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:f383a222513fe09f773b2a64805260e010d2d5d370cf36ca5671572d04fee227","observation_id":"d5118454-5b9f-4ed5-a669-6f02cb63c99e","resolution":{"observed_at":"2026-08-03T08:24:35.156451Z","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":"2026-08-03T08:24:35.329280Z","title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels.Advances in neural information processing systems, 31,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:35.329280Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:43e7279585e0c674422ac2079ed364c7962dfa5ce36f8f9b628efa958e4770ce","observation_id":"80e030f4-b7c4-4fd8-a480-8125c607acef","resolution":{"observed_at":"2026-08-03T08:24:35.329280Z","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":"2026-08-03T08:24:36.055947Z","title":"On large-batch training for deep learning: Generalization gap and sharp minima","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:36.055947Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:dd8e156ac6277fd019e4cbf46249c2824d729471bb8ce7191a3ae6eb371eb98f","observation_id":"88d23a42-c804-4d0c-b974-6b9e8c5bd903","resolution":{"observed_at":"2026-08-03T08:24:36.055947Z","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":"2026-08-03T08:24:36.176274Z","title":"Learning multiple layers of features from tiny im- ages","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:36.176274Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:6cd719619e14adf5b6b9d2fbd976c04d045d4e87ff68f7531905cde5519ba5a5","observation_id":"5189a60a-3b0e-4b00-afef-f39821c7b8da","resolution":{"observed_at":"2026-08-03T08:24:36.176274Z","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":"2026-08-03T08:24:36.364330Z","title":"Tiny ima- genet visual recognition challenge.CS 231N, 7(7):3,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:36.364330Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:f1d4ce5d2e05463c760868c6bbd9d22367bb875481aa4ed0bdbf13e5984ba3bc","observation_id":"ed8ec372-6860-41b1-8903-d55a29eae80e","resolution":{"observed_at":"2026-08-03T08:24:36.364330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07394","last_updated":"2020-02-18T06:20:06Z","snapshot_observed_at":"2026-08-06T03:18:08.960708Z","submitted_at":"2020-02-18T06:20:06Z","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07394","snapshot_observed_at":"2026-08-03T08:24:36.665560Z","title":"Dividemix: Learning with noisy labels as semi- supervised learning.arXiv preprint arXiv:2002.07394,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:36.665560Z"},"links":{"cited_paper":"/paper/2002.07394","citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:9c39ad677afe9c71560a0f4dd7e4b21b9a1df5ea50d8d201b1b38901f406fec7","observation_id":"a2d848a0-2042-4698-bb23-3db4f315e544","resolution":{"observed_at":"2026-08-03T08:24:36.665560Z","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":"2026-08-03T08:24:36.813816Z","title":"Learning from noisy data with robust representation learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:36.813816Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:58629c9d50d1745a3d2fd051332d5b46911d2fcf1e38ab98248dab1c773dfe02","observation_id":"278ee0d3-e365-47d4-bf21-4a8a38845d25","resolution":{"observed_at":"2026-08-03T08:24:36.813816Z","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":"2026-08-03T08:24:36.948014Z","title":"Disc: Learning from noisy labels via dynamic instance-specific selection and correction","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:36.948014Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:6dae038722e93e6efb9e5ce5bef877c8a4720348c56e72fa7636d6224695386a","observation_id":"74ea2fc3-fd89-4af4-a469-3871843dd46a","resolution":{"observed_at":"2026-08-03T08:24:36.948014Z","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":"2026-08-03T08:24:37.051313Z","title":"Peer loss functions: Learning from noisy labels without knowing noise rates","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:37.051313Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:55a5de1d288257cf782c6183afe138260f6e8febd2cbc21d6a5cbe0d14d63873","observation_id":"6ab16cea-da61-45ba-8891-4c1445f147aa","resolution":{"observed_at":"2026-08-03T08:24:37.051313Z","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":"2026-08-03T08:24:37.206608Z","title":"Balanced sharpness-aware minimization for im- balanced regression","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:37.206608Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:06bd2837bb8d7ab16b2d5c636ae05e211ebc9536ef9d4f694f6c9b750c8179ba","observation_id":"5a4c883c-0178-4446-aaf8-05cbc1e2635d","resolution":{"observed_at":"2026-08-03T08:24:37.206608Z","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":"2026-08-03T08:24:37.370014Z","title":"Loss factorization, weakly supervised learning and label noise robustness","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:37.370014Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:73cbfd95ed43aa35b200add3f02a0309b0b8ab8a94313bfb47afde59adc3ab5b","observation_id":"eba8f418-3fd2-4371-8773-f047e26fe4aa","resolution":{"observed_at":"2026-08-03T08:24:37.370014Z","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":"2026-08-03T08:24:37.468688Z","title":"Making deep neural networks robust to label noise: A loss correction approach","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:37.468688Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:fa96428ff33da0c558e0453fa83325ce5362c0ce44eda2ff0163495c7bb583d7","observation_id":"0e0e83db-7f15-438b-9a06-99113ccee51f","resolution":{"observed_at":"2026-08-03T08:24:37.468688Z","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":"2026-08-03T08:24:37.576404Z","title":"Learning to reweight examples for robust deep learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:37.576404Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:15cf393dd3bf6d0f34e027215e686542cd4c62b9b4e24a714d2af6a40df0c176","observation_id":"e15fd1d7-5436-49dd-8100-8dac2d204c78","resolution":{"observed_at":"2026-08-03T08:24:37.576404Z","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":"2026-08-03T08:24:37.635159Z","title":"Noisy concurrent training for effi- cient learning under label noise","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:37.635159Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:a2f59242fb15714f92cdcabc693062c897373992cd5bef2f907efcb9d60a579f","observation_id":"581c1608-e7d8-4a0a-8a81-cfb68a15a531","resolution":{"observed_at":"2026-08-03T08:24:37.635159Z","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":"2026-08-03T08:24:37.688764Z","title":"Classification with asymmetric label noise: Consistency and maximal denoising","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:37.688764Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:9b0453966622d18b76e14feefbc367703d497ea3e2f0f72947a1109787b03b3d","observation_id":"4caa3a69-77c3-4a64-9e67-99a9450b624f","resolution":{"observed_at":"2026-08-03T08:24:37.688764Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-07-06T03:53:32.549552Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-03T08:24:37.973955Z","title":"Very deep convolutional networks for large-scale image recognition.arXiv preprint arXiv:1409.1556,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:37.973955Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:e4f1c2d6d185da2952a9aeb0bb473a07b24794fb05961b9334211cad5351e306","observation_id":"952fc2e0-6a8a-46d5-8e2f-ac4608335560","resolution":{"observed_at":"2026-08-03T08:24:37.973955Z","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":"2026-08-03T08:24:38.031580Z","title":"SELFIE: Refurbishing unclean samples for robust deep learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:38.031580Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:d60403360c2869ae9d3d10d6327d06460eb20a1e07503197972073c86b8b9ce1","observation_id":"91bf79c3-1729-46ec-bb89-c211d536d64e","resolution":{"observed_at":"2026-08-03T08:24:38.031580Z","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":"2026-08-03T08:24:38.125692Z","title":"Joint optimization framework for learning with noisy labels","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:38.125692Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:40ab76c3312e3c62f0a7f91e3c7a8ffc37d20abcd22eea6ca288a5fba7706e94","observation_id":"f298edad-9c3f-4c70-8536-ceff1d78cfbf","resolution":{"observed_at":"2026-08-03T08:24:38.125692Z","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":"2026-08-03T08:24:38.185088Z","title":"Mean teachers are better role models: Weight- averaged consistency targets improve semi-supervised deep learning results.Advances in neural information pro- cessing systems, 30,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:38.185088Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:8e67c50bbad4e17ed2224679370501c9be76eb10c2acbdc5d1d57f5e8ed2c21c","observation_id":"4c25d0fb-51ab-4ddf-9ffa-4c0bfc523cc3","resolution":{"observed_at":"2026-08-03T08:24:38.185088Z","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":"2026-08-03T08:24:38.244212Z","title":"Snuba: Automating weak supervision to label training data","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:38.244212Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:36551e7fd62ad9c0c60c5d6d6fc0a1003e4924de99ede0bfdd198c708c65b224","observation_id":"907a9860-14db-4602-b955-77ea73cd7477","resolution":{"observed_at":"2026-08-03T08:24:38.244212Z","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":"2026-08-03T08:24:38.355169Z","title":"Symmetric cross entropy for robust learning with noisy labels","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:38.355169Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:29dcc19ed1dc2a880f7ed5a0be9486e348fab046aa194bedc1b080aec862df79","observation_id":"08c68121-a0d0-4be2-ae5c-c2c60e013821","resolution":{"observed_at":"2026-08-03T08:24:38.355169Z","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":"2026-08-03T08:24:38.475686Z","title":"Combating noisy labels by agreement: A joint training method with co-regularization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:38.475686Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:ae5d0efd0656346579a22b0f6325fe60bf0e2e1647f8890e780f83321f59ebef","observation_id":"e1b57c64-5f3b-4220-a0e2-5285dde151a5","resolution":{"observed_at":"2026-08-03T08:24:38.475686Z","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":"2026-08-03T08:24:38.554339Z","title":"Are anchor points really indispensable in label-noise learn- ing?Advances in neural information processing systems, 32,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:38.554339Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:99aa839a084f5b0d995b9e3b81eb7002e3381dc2c25461680233aa3c1c12a491","observation_id":"100d0c94-c102-46a2-913c-7301a6df23a6","resolution":{"observed_at":"2026-08-03T08:24:38.554339Z","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":"2026-08-03T08:24:38.704605Z","title":"Learning from massive noisy labeled data for image classification","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:38.704605Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:77df90f0967c14d3d3fcf0a4f3ec7e43be08707372a52345d22eb74e814bf65e","observation_id":"24fac4ed-93b4-4a1e-a479-8b9feaca3f82","resolution":{"observed_at":"2026-08-03T08:24:38.704605Z","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":"2026-08-03T08:24:38.828005Z","title":"Label correction using contrastive proto- typical classifier for noisy label learning.Information Sci- ences, 649:119647,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:38.828005Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:639e905d7eca91769b1f5cd1a05c0000f932368eb5de5f4476b93a1c6218eb3e","observation_id":"3bce0185-9229-418f-8b9f-6b539b2d1438","resolution":{"observed_at":"2026-08-03T08:24:38.828005Z","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":"2026-08-03T08:24:38.906547Z","title":"How does dis- agreement help generalization against label corruption? InInternational conference on machine learning, pages 7164–7173","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:38.906547Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:4673fa48f768219aea31503842fe660d6988bddb6262a694e2ebee9a8fb04d75","observation_id":"29c515a6-c3f8-4e45-ada7-f04d49bbd723","resolution":{"observed_at":"2026-08-03T08:24:38.906547Z","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":"2026-08-03T08:24:38.996806Z","title":"Generalized cross entropy loss for training deep neural networks with noisy labels.Advances in neural informa- tion processing systems, 31,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:38.996806Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:1ac36a242efb47ea41fcae01e5b302ee1dd207be1724bbeef3bc6c894bfcf105","observation_id":"37636dc6-a66b-417d-ab45-7ab6c972062d","resolution":{"observed_at":"2026-08-03T08:24:38.996806Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.09412","last_updated":"2018-04-27T21:39:25Z","snapshot_observed_at":"2026-08-08T10:28:19.597631Z","submitted_at":"2017-10-25T18:30:49Z","title":"mixup: Beyond Empirical Risk Minimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.09412","snapshot_observed_at":"2026-08-03T08:24:39.019882Z","title":"mixup: Be- yond empirical risk minimization.arXiv preprint arXiv:1710.09412,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:39.019882Z"},"links":{"cited_paper":"/paper/1710.09412","citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:ef33e3fdcc9ed32fadac67d638a87d88f9df01413357ae9e9705b793c7176d42","observation_id":"4f3d610f-e69c-4182-bdd5-8d6bc81575c5","resolution":{"observed_at":"2026-08-03T08:24:39.019882Z","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":"2026-08-03T08:24:39.097525Z","title":"mixup: Beyond empirical risk minimization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:39.097525Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:68599e9744ee23b14231e2010bcee69b999bc9ed8eb729c18e6fe9cacefbcb52","observation_id":"c0155e87-e9e0-4004-bb27-bb236eb47b0e","resolution":{"observed_at":"2026-08-03T08:24:39.097525Z","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":"2026-08-03T08:24:39.191400Z","title":"Learn- ing with feature-dependent label noise: A progressive ap- proach","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:39.191400Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:2aed56b8e0026466c011af12d05bf5b85d5a721b3bab1d28147ccee13a8c95da","observation_id":"63fcd7bd-33ea-4b86-9135-2351643ceb81","resolution":{"observed_at":"2026-08-03T08:24:39.191400Z","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":"2026-08-03T08:24:39.372205Z","title":"Centrality and consistency: Two-stage clean samples identification for learning with instance-dependent noisy labels","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:39.372205Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:d6c6d4be77359c238e0f85cb39f398099d013e4a7f55a9d05d393d2deb57fb35","observation_id":"7fd03e8e-70f7-4c11-a4e9-99acff24caf2","resolution":{"observed_at":"2026-08-03T08:24:39.372205Z","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":"2026-08-03T08:24:39.485206Z","title":"Error-bounded correction of noisy labels","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:39.485206Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:783171580909d4c87ce6e29a2610bc0d0f87b9205708fac162677aa7754e5838","observation_id":"26420005-c35b-4dae-9c42-27f284565b0b","resolution":{"observed_at":"2026-08-03T08:24:39.485206Z","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":"2026-08-03T08:24:39.570919Z","title":"Meta label correction for noisy label learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:39.570919Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:84fecba2bc154c409c7421659bab0f1c6b26cfa696e0760bdcd7cc41fb238790","observation_id":"0f6ea24e-3ae8-4416-9f96-1f519d28c5ce","resolution":{"observed_at":"2026-08-03T08:24:39.570919Z","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":"2026-08-03T08:24:39.639613Z","title":"Curriculum learning by dynamic instance hard- ness.Advances in Neural Information Processing Systems, 33:8602–8613,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:39.639613Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:c70516efde07fd9e5b700eccef4b1511ad87da494bc2d76b1702d47efb92abcc","observation_id":"78150c14-5130-4b6f-b1a8-6e4032d8e9c1","resolution":{"observed_at":"2026-08-03T08:24:39.639613Z","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":"2026-08-03T08:24:39.721822Z","title":"Asymmetric loss functions for noise-tolerant learning: Theory and applica- tions.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(7):8094–8109,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:39.721822Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:79241bc0b9f1db860edc2908cdba1eb3311f216928f35d11449dd3ed5002c1da","observation_id":"484dce27-b2e6-432f-b711-732dbe73919d","resolution":{"observed_at":"2026-08-03T08:24:39.721822Z","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":"2026-08-03T08:24:39.829152Z","title":"A second-order approach to learning with instance- dependent label noise","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:39.829152Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:277223a297d4989e4c05a14f26bee206a53dc8ea0ac9f141f2b4b52433e37026","observation_id":"cac89339-8d13-43a2-9dbf-4ee7b92e616d","resolution":{"observed_at":"2026-08-03T08:24:39.829152Z","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":"2026-08-03T08:24:37.898920Z","title":"Meta- weight-net: Learning an explicit mapping for sample weighting.Advances in neural information processing sys- tems, 32,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2002,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:37.898920Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:d206ffa8eb0dbf01a12aad8d634727e5c403cd604aaf5ea6a1ca57a0c7d96f3e","observation_id":"feb09336-90de-4a69-9ae8-dbbf4b7171e3","resolution":{"observed_at":"2026-08-03T08:24:37.898920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.02242","last_updated":"2017-03-15T14:22:41Z","snapshot_observed_at":"2026-08-01T18:35:12.430501Z","submitted_at":"2016-10-07T12:15:42Z","title":"Temporal Ensembling for Semi-Supervised Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.02242","snapshot_observed_at":"2026-08-03T08:24:36.303907Z","title":"Tem- poral ensembling for semi-supervised learning.arXiv preprint arXiv:1610.02242,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:36.303907Z"},"links":{"cited_paper":"/paper/1610.02242","citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:7f252f6f35b18eba5f0eef24b20edf504b781ad5697e3d93dddf94962641ed00","observation_id":"605b1669-926a-43c8-98c0-612b8ee43803","resolution":{"observed_at":"2026-08-03T08:24:36.303907Z","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":"2026-08-03T08:24:37.777444Z","title":"Pac-bayesian generalisation error bounds for gaussian process classification.Journal of machine learning research, 3(Oct):233–269,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:37.777444Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:0d38d323256588060f4f0bcc89bed04480ff74d063b92f03b48e04912df9d392","observation_id":"697d07a4-8b14-4c61-9da6-97bcea9c6112","resolution":{"observed_at":"2026-08-03T08:24:37.777444Z","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":"2026-08-03T08:24:33.959887Z","title":"Understanding and utilizing deep neural networks trained with noisy labels","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:33.959887Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:b60d1a4b22d4c3c78c31665b091f44b1551045bd4618dd63c6e9d219f5365e83","observation_id":"a42e48b4-ddaf-4728-af9c-171fe7a27d7e","resolution":{"observed_at":"2026-08-03T08:24:33.959887Z","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":"2026-08-03T08:24:36.487529Z","title":"Visualizing the loss landscape of neural nets.Advances in neural information processing systems, 31,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:36.487529Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:8d7bb48c4c6722c87d8537ad30d328dac30845fe5d3cbc21d3f918e1044ff881","observation_id":"db3f2324-e975-4394-acb8-e5fd92817542","resolution":{"observed_at":"2026-08-03T08:24:36.487529Z","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":"2026-08-03T08:24:35.609594Z","title":"Asymmetric valleys: Beyond sharp and flat local minima","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:35.609594Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:bc88ee2a5a7ee43e5fff3fdc0225f85e30a0d4d2108e7947350efb67ceee9d5f","observation_id":"509fb31c-5921-4a24-95a4-2f25f6615c84","resolution":{"observed_at":"2026-08-03T08:24:35.609594Z","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":"2026-08-03T08:24:34.907405Z","title":"Sharp minima can general- ize for deep nets","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:34.907405Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:beb9bc7da02e227655ac0cd53cf31cbd5a33afda644ffb938762113cd303cf3a","observation_id":"dcc7f456-953d-492f-b0d1-4e3891c67728","resolution":{"observed_at":"2026-08-03T08:24:34.907405Z","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":"2026-08-03T08:24:35.496125Z","title":"Deep residual learning for image recog- nition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:35.496125Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:8a7e0721d82124e6af826f0d31a3952c0a834dc61865a223dbb13b10e677e299","observation_id":"bed4cbab-3218-425b-ad8b-0f846777fabd","resolution":{"observed_at":"2026-08-03T08:24:35.496125Z","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":"2026-08-03T08:24:34.119499Z","title":"Beyond class- conditional assumption: A primary attempt to combat instance-dependent label noise","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:34.119499Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:f08207fb04b1b623548873a4bdd7bb7d7d6ff84696343d9c5cf120234c9d2672","observation_id":"7356572c-b3e3-4049-8ac9-1f65ac2f437b","resolution":{"observed_at":"2026-08-03T08:24:34.119499Z","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":"2026-08-03T08:24:34.440426Z","title":"Learning with instance-dependent label noise: A sample sieve approach","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:34.440426Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:58a4cbd7e926055c088cd8602c6efdc71f05e326c667504b6a922e22e7700f14","observation_id":"4069eb29-5a78-4105-b767-2f5c2300dd75","resolution":{"observed_at":"2026-08-03T08:24:34.440426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02347","last_updated":"2021-03-22T22:01:05Z","snapshot_observed_at":"2026-07-06T10:01:44.473772Z","submitted_at":"2020-10-05T21:44:09Z","title":"Learning with Instance-Dependent Label Noise: A Sample Sieve Approach","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02347","snapshot_observed_at":"2026-08-03T08:24:34.273575Z","title":"Learning with instance-dependent label noise: A sample sieve approach","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:34.273575Z"},"links":{"cited_paper":"/paper/2010.02347","citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:d23784c8e1f333f9cfb51830df09296aceae3a8c2274630a2c19d5958c921d50","observation_id":"10e4f5ca-23de-4860-8a0f-35b3a627e8d0","resolution":{"observed_at":"2026-08-03T08:24:34.273575Z","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":"2026-08-03T08:24:35.774755Z","title":"Combining layered label correction and mixup super- vised contrastive learning to learn noisy labels.Informa- tion Sciences, 642:119242,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:35.774755Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:c6bf724b5d03387cf6af8e4061e84033e395c840c3645219182e4951222e49aa","observation_id":"02632347-db16-4c5b-86f5-adbd1e636f6c","resolution":{"observed_at":"2026-08-03T08:24:35.774755Z","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":"2026-08-03T08:24:35.931015Z","title":"Unicon: Combating label noise through uniform selection and contrastive learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:35.931015Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:f4924593665d21368eae287b2a13347739ad4a7fb0ec2c74acc18f5432edf77f","observation_id":"b81ad490-87a8-4948-8702-c9ae782aa724","resolution":{"observed_at":"2026-08-03T08:24:35.931015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.04552","last_updated":"2017-11-29T14:51:40Z","snapshot_observed_at":"2026-07-06T05:55:22.966528Z","submitted_at":"2017-08-15T15:21:53Z","title":"Improved Regularization of Convolutional Neural Networks with Cutout","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.04552","snapshot_observed_at":"2026-08-03T08:24:34.701822Z","title":"Improved regularization of convolu- tional neural networks with cutout.arXiv preprint arXiv:1708.04552,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:34.701822Z"},"links":{"cited_paper":"/paper/1708.04552","citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:182851125d1f33b0538519a189d48bbb5cf19ef458737f4579138253b388c613","observation_id":"d54e9fb8-6276-42fc-85e6-7cd9a21df049","resolution":{"observed_at":"2026-08-03T08:24:34.701822Z","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":"2026-08-03T08:24:37.286676Z","title":"Exploring generalization in deep learning.Advances in neural infor- mation processing systems, 30,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","version":3},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-03T08:24:37.286676Z"},"links":{"citing_paper":"/paper/2601.19947"},"observation_digest":"sha256:83ee6b89a426ab49d4ddd1f9c3fdb064a209787bfd211dd762595dde841ccade","observation_id":"4e67933e-5c88-4f45-bfa0-25766a5b0e20","resolution":{"observed_at":"2026-08-03T08:24:37.286676Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2601.19947","last_updated":"2026-05-28T12:22:28Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T05:33:16.577137Z","submitted_at":"2026-01-24T11:10:29Z","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":54,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":54},"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 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2601.19947."}