{"as_of":"2026-08-07T08:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:360de11cc380ea114d87865968d424744f834cdb484fa57430dc806983a7a41f","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T17:14:24.657287Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2509.05307/citation-record","integrity":"/paper/2509.05307/integrity","json":"/paper/2509.05307/citation-record.json","paper":"/paper/2509.05307"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T17:14:25.361900Z","title":"Patchswap: A regularization technique for vision transformers","venue":null,"work_id":"c2f0f01c-b96d-4e8c-b067-e135e3681a57","year":2022},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:22.106516Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:c4768bb32cc13b2f7bb5273e1201353195b63375bcd46ce2d6c88cd995d8a1cc","observation_id":"3ef1a5e0-da46-422c-857b-36d36cee510f","resolution":{"observed_at":"2026-08-05T17:14:25.366756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:25.345290Z","title":"Generative alignment of pos- terior probabilities for source-free domain adaptation","venue":null,"work_id":"aa3868dc-698d-4087-b4db-e283098d8d5e","year":2023},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:22.182340Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:912aa55a080c1f3372e6848d90391dd97ec97e723b54eac17d0eb5753a126298","observation_id":"d29c826d-b58a-4432-8c5d-47370baa9e71","resolution":{"observed_at":"2026-08-05T17:14:25.350544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:22.281100Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:22.281100Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:a94c4bf4e1054fe4fca858a83dfa8b73810f30bb6dd9050726ac6a618bd087b3","observation_id":"f8f595fc-18f2-4ed6-8c16-193e2705b639","resolution":{"observed_at":"2026-08-05T17:14:22.281100Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-05T17:14:22.351100Z","title":"BERT: pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:22.351100Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:06b380ce40aea0a4c57336f4ab20416b2a0132dc70e39a4f119e9959546c0966","observation_id":"af9fc86f-c320-462c-985e-460339796324","resolution":{"observed_at":"2026-08-05T17:14:22.351100Z","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":"2026-08-05T17:14:22.454863Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:22.454863Z"},"links":{"cited_paper":"/paper/1708.04552","citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:2b7706d8a028e71694957d986fe41abcb62c2bf4195215343a556501a30b6f3a","observation_id":"7d3ed51f-cc70-43df-b046-5f25f3e723b6","resolution":{"observed_at":"2026-08-05T17:14:22.454863Z","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":"2026-08-05T17:14:25.317406Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"f2b8bba0-d47d-4ea1-b512-db344ee37d43","year":2020},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:22.539330Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:d86f3f2b8c0dc6c90dd157aada24091d17c9fd4fd3b6b88aa87aa73c168eefea","observation_id":"d29781eb-5eea-4b17-8faa-8465f1e8d0b8","resolution":{"observed_at":"2026-08-05T17:14:25.322427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:25.301043Z","title":"Keepaugment: A simple information-preserving data augmentation approach","venue":null,"work_id":"42926fb4-2983-4163-8c51-977539e6bd2d","year":2021},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:22.610399Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:ba0a628684f07ef90198ac0cce6b82f89ba927911f2ec70ce8f500bb8c5dc8f7","observation_id":"c130d601-d43a-4d97-a567-02b99ec3b05b","resolution":{"observed_at":"2026-08-05T17:14:25.306591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:22.696425Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:22.696425Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:00bb96f67efefd40f4e78ccbe38108b4a701df9ace0940d9040efb77597f5b59","observation_id":"05b75ff4-9768-4432-b21f-ba03885f1169","resolution":{"observed_at":"2026-08-05T17:14:22.696425Z","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":"2026-08-05T17:14:25.272429Z","title":"Augmix: A simple data processing method to improve ro- bustness and uncertainty","venue":null,"work_id":"ac5329d8-222d-49ad-baa9-a706bb6f7298","year":2020},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:22.791143Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:1b07de8d3116d8f36d4b71d577ea4508abb4c03b02f7ef9309bc968216a80fa4","observation_id":"8c15742f-67d1-47b8-b54c-9a6fd50fccfa","resolution":{"observed_at":"2026-08-05T17:14:25.277346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-05T17:14:22.865119Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:22.865119Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:1c605549064f5a6cf8bdfcc3fdc104e5efc18c07b46dabdbc22c2e1704b85719","observation_id":"3cf0027b-6dad-4a22-84d0-9f48e0e0c2c6","resolution":{"observed_at":"2026-08-05T17:14:22.865119Z","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":"2026-08-05T17:14:22.983249Z","title":"Densely connected convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:22.983249Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:efd2fc655d75fd7ec4a9c27b2333d34a4a1247162ee3bcf2f1d0bd82cbca7627","observation_id":"67ed2edd-76a7-4e72-8e4a-a3030b5593da","resolution":{"observed_at":"2026-08-05T17:14:22.983249Z","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":"2026-08-05T17:14:25.244815Z","title":"Large-scale video classification with convolutional neural networks","venue":null,"work_id":"10cf56a7-2381-4135-93b7-d9457cf0122d","year":2014},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:23.096165Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:bb4a6ed45efbff7baebb443e5b8a6dff74722e0dee2b4e064cb66df22a8fce72","observation_id":"de92beb1-a2b2-485a-9266-1f244343294e","resolution":{"observed_at":"2026-08-05T17:14:25.249657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:23.163915Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:23.163915Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:f6593216e776d9b426aa518371b7e3f6a616752fc7a975a5a1c35fc66815816e","observation_id":"eff936a6-c6aa-4262-ad6c-5f32d1211720","resolution":{"observed_at":"2026-08-05T17:14:23.163915Z","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":"2026-08-05T17:14:25.217284Z","title":"Imagenet classification with deep convolutional neural networks","venue":null,"work_id":"de800b9e-8f20-4251-a086-60b9e454ff6e","year":2012},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:23.237275Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:2687a0610c1bd9793c9a9fe02426b4d916d3a890b5d3a0f75541695bbe7bd0f8","observation_id":"24d655df-4c27-4b8b-a0af-bfe77cd36348","resolution":{"observed_at":"2026-08-05T17:14:25.222144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:25.200735Z","title":"Hmdb: a large video database for human motion recognition","venue":null,"work_id":"9ede1619-3fc3-4362-b798-b9993f78377d","year":2011},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:23.309373Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:a447564c2a0c35784b02c8dde30992a1ef878b73b60ef6fc2c93453895996e70","observation_id":"d13ebb49-0ad2-48ee-8307-d3c43b28802b","resolution":{"observed_at":"2026-08-05T17:14:25.205638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:23.367606Z","title":"Gradient-based learn- ing applied to document recognition","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:23.367606Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:6687efc46e58a5e5c6a3d35a0c19faa9dcffb5a05bdec04370e417897f5cf394","observation_id":"8e214732-9705-4246-85c7-f066b427fe85","resolution":{"observed_at":"2026-08-05T17:14:23.367606Z","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":"2026-08-05T17:14:25.172246Z","title":"Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation","venue":null,"work_id":"a14eacfc-598a-4cd3-8599-b4169f77eeb8","year":2020},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:23.437137Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:e8aa4f554ceea8066288d9ada0e210ccf07b3f6b8ff61559c00ced256374da11","observation_id":"554ed806-e14d-4ef2-879a-6762ad0da9c3","resolution":{"observed_at":"2026-08-05T17:14:25.178172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:23.497021Z","title":"Focal loss for dense object detection","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:23.497021Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:e081ee23fe6af8da45ffd0942d8f411f1c0a2527103b2f2dd8789ca365dd93f2","observation_id":"1af19263-0dde-4c84-95c2-1e8e505a479b","resolution":{"observed_at":"2026-08-05T17:14:23.497021Z","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":"2026-08-05T17:14:25.145535Z","title":"The devil is in the margin: Margin-based label smoothing for network calibration","venue":null,"work_id":"4cee11a6-fb74-41d1-a27e-515975cac4e9","year":2022},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:23.519474Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:64f98fea9efcca524099dd4eebb9433dc075093f5aaa273d8c462fa7c857ccc4","observation_id":"b0da0372-ab55-4f92-a309-d216502fba37","resolution":{"observed_at":"2026-08-05T17:14:25.150431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:25.128296Z","title":"Calibrating deep neural networks using focal loss.Advances in Neural Information Processing Systems, 33:15288–15299, 2020","venue":null,"work_id":"4910a695-5866-4333-8b25-b1514a8f7bf3","year":2020},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:23.618076Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:f4353f1a2e12d73aae0f1706cdf463323f38c09b7996789cc77ac8df32a9c2af","observation_id":"9728b592-9295-4ae7-a44d-9ca4245f8f5f","resolution":{"observed_at":"2026-08-05T17:14:25.133329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:25.111650Z","title":"When does label smoothing help? Advances in neural information processing systems , 32, 2019","venue":null,"work_id":"c121cd8d-8fd7-46b5-9912-c81c54753caa","year":2019},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:23.691181Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:da7af82e51d3384bad3a56be4c0428fec04a38168b0f181af73bf447c80c9234","observation_id":"ee4c1c03-921b-431f-99a1-f9b9e9ba05c9","resolution":{"observed_at":"2026-08-05T17:14:25.116860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:23.787416Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:23.787416Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:446eb63d45ea523d34cada449af0c29c8a02a574b98f4652c0fb60d2ffde3198","observation_id":"ddfe7bc7-3653-4c86-8606-a68691a08859","resolution":{"observed_at":"2026-08-05T17:14:23.787416Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.11154","last_updated":"2020-11-13T19:09:09Z","snapshot_observed_at":"2026-08-02T13:56:50.027940Z","submitted_at":"2020-07-22T01:31:44Z","title":"Rethinking CNN Models for Audio Classification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.11154","snapshot_observed_at":"2026-08-05T17:14:23.933814Z","title":"Rethinking CNN models for audio classification","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:23.933814Z"},"links":{"cited_paper":"/paper/2007.11154","citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:504ebf0acf397fdf939991f45c6921dc0bdb97cf1da13d9b9a3f7ca020002ddc","observation_id":"5d758765-0317-4234-962e-c2f3b1f49df1","resolution":{"observed_at":"2026-08-05T17:14:23.933814Z","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":"2026-08-05T17:14:25.082400Z","title":null,"venue":null,"work_id":"79517972-cdae-41bb-95bc-1cba0e8ed214","year":2017},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.001694Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:4256ef68e32f71d1efb297a4b9e6f955569e8d238e770f591907c46f85548546","observation_id":"1d56fcae-7aff-4a47-bf23-01bd3e4baf87","resolution":{"observed_at":"2026-08-05T17:14:25.087463Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:25.066093Z","title":"SELFIE: Refurbishing unclean sam- ples for robust deep learning","venue":null,"work_id":"e4724a77-0c2a-4a25-8275-35069279d74f","year":2019},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.135370Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:7796fbd62e9ad174f3e405b9705ae78cbac9dc37cead76a9ed1f621683c4b831","observation_id":"d8bd59c9-a4f4-4f24-aa5f-1b77edc1dff6","resolution":{"observed_at":"2026-08-05T17:14:25.071091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.0402","last_updated":"2012-12-03T14:45:31Z","snapshot_observed_at":"2026-07-06T03:01:10.229407Z","submitted_at":"2012-12-03T14:45:31Z","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.0402","snapshot_observed_at":"2026-08-05T17:14:24.268518Z","title":"UCF101: A dataset of 101 human actions classes from videos in the wild","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.268518Z"},"links":{"cited_paper":"/paper/1212.0402","citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:a7f41d50cf8f32640c99069192780584259cabfa4260d376a5726034b665a4ce","observation_id":"15cf4dd5-70e1-42b5-9514-e4443c1987fd","resolution":{"observed_at":"2026-08-05T17:14:24.268518Z","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":"2026-08-05T17:14:25.049429Z","title":"Rethinking the inception architecture for computer vision","venue":null,"work_id":"e887c05e-9c05-4de2-a6f6-f9dfb4502b7c","year":2016},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.362955Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:a054c25d10a58514bbd74c261f8bb198280d653fb9f43c96a2d457b4978b32c5","observation_id":"9b144952-b1e6-49cf-811f-0fda0f0d55da","resolution":{"observed_at":"2026-08-05T17:14:25.054646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:25.032371Z","title":"Learning spatiotemporal features with 3d convolutional networks","venue":null,"work_id":"46a3c6a1-23c7-4dc3-adac-bd5883e3ff6d","year":2015},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.547701Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:4735e819f49cb5e2deef424b250a805342fcd8092703557e705e3673e13f26cb","observation_id":"c455a007-772b-4d40-9027-d401fa15a1f8","resolution":{"observed_at":"2026-08-05T17:14:25.037294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:25.015581Z","title":"Automatic musical genre classification of audio signals","venue":null,"work_id":"523819fe-40f9-416e-b0fa-39f2e9d84f39","year":2001},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.579380Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:976ff3393ea5e366b4c30a4a02065a633de75eb53f24e76d281d5eb60ba8d7c2","observation_id":"f7d2ca07-6159-4678-bc35-b74684fda34f","resolution":{"observed_at":"2026-08-05T17:14:25.020671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:24.614682Z","title":"Visualizing data using t-sne","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.614682Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:24c56bb7e215cbc985a0df134c7ac03d406fc82f034953ba04d479c42210e03a","observation_id":"2de467d2-22d0-4ce3-9c5e-6d79272db600","resolution":{"observed_at":"2026-08-05T17:14:24.614682Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03209","last_updated":"2018-04-09T19:58:17Z","snapshot_observed_at":"2026-07-06T06:32:32.083176Z","submitted_at":"2018-04-09T19:58:17Z","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.03209","snapshot_observed_at":"2026-08-05T17:14:24.619349Z","title":"Speech commands: A dataset for limited-vocabulary speech recognition","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.619349Z"},"links":{"cited_paper":"/paper/1804.03209","citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:55fbab2d58f87ba7313f99fc73f3dd3f9ed03dfdbeccc0a82914a7d6f856f968","observation_id":"2fd2de89-1083-46c8-9859-506acc3af0cd","resolution":{"observed_at":"2026-08-05T17:14:24.619349Z","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":"2026-08-05T17:14:24.624545Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.624545Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:1146d63908793af2bb2c6c618e5ef4ba12342a49bb12aac966b2f278efcf7dfd","observation_id":"a0c00bc9-63c7-4de7-a550-7093015ca682","resolution":{"observed_at":"2026-08-05T17:14:24.624545Z","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":"2026-08-05T17:14:24.975924Z","title":"Revisiting knowl- edge distillation via label smoothing regularization","venue":null,"work_id":"b35611e3-72ea-42eb-83b5-8f6f3e7c6eea","year":2020},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.629094Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:d5884f506e825e84213657e3c08b1858f7dfaab3889bcd6c01b639482cca7d88","observation_id":"4d9dced0-330f-4f65-8498-3b08b9cd9d60","resolution":{"observed_at":"2026-08-05T17:14:24.981357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:24.959326Z","title":"Cutmix: Regularization strategy to train strong classifiers with local- izable features","venue":null,"work_id":"853fbc72-ed07-4341-bdb5-e108fd733901","year":2019},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.633598Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:2b41d71509b468a8b989efba301e2f103596dc156eb568fb03a287c7f6c22644","observation_id":"32afbd33-e185-4539-868a-249f8e8f2e9f","resolution":{"observed_at":"2026-08-05T17:14:24.964459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:24.643395Z","title":"Delving deep into label smoothing","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.643395Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:ed65f1ea444319731f064bdb82b078ec04041d779c7482dee2aad9a832e16f03","observation_id":"4c58e38b-6428-43a7-b338-0e1e9bf13480","resolution":{"observed_at":"2026-08-05T17:14:24.643395Z","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":"2026-08-05T17:14:24.930378Z","title":"Dauphin, and David Lopez-Paz","venue":null,"work_id":"04b67d9a-a1fc-4b37-9278-18f858d7713d","year":2018},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.648139Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:e454851bf6cdede6f0d6ec5ae6a8a0387447102d5120e05b812570418543e859","observation_id":"86d990eb-e0bf-4a4b-80c9-2ca20d1337fe","resolution":{"observed_at":"2026-08-05T17:14:24.935239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:24.914023Z","title":"Character-level convolutional networks for text classification","venue":null,"work_id":"65f80fe0-8e22-481d-aa8b-4cbbb4dcbdb5","year":2015},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.652645Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:f1663ce3784829c7adecb6d57e79502135d8c4adac144987b9f416b57a687039","observation_id":"a1198006-8837-40c4-8252-c9c0fbaa35a5","resolution":{"observed_at":"2026-08-05T17:14:24.918911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:24.895249Z","title":"Shufflenet: An extremely efficient convolutional neural network for mobile devices","venue":null,"work_id":"b0b4d036-caee-44ce-97bf-aa91b38d32ad","year":2018},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.657287Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:0e1728b467fc2dc443f726ed414213e23da61822b91482cfa1ae0c5c4bd57013","observation_id":"419ac6af-8c0a-4e94-91ad-74fb90c7c3f0","resolution":{"observed_at":"2026-08-05T17:14:24.902253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T17:14:24.637967Z","title":"doi: 10.1109/ICCV .2019.00612","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","version":1},"reference_index":6031,"source":"pdf_text","source_observed_at":"2026-08-05T17:14:24.637967Z"},"links":{"citing_paper":"/paper/2509.05307"},"observation_digest":"sha256:477e1daa53231f949e0ee11ef032b9eca62a1b3d5be4871f4912838dcfad0931","observation_id":"5b6704d2-6471-47e3-b79c-9be3f0849f92","resolution":{"observed_at":"2026-08-05T17:14:24.637967Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.05307","last_updated":"2025-08-22T23:11:43Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-05T17:14:21.380295Z","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":0,"verified_fuzzy":21},"total_outbound_references":39},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2509.05307."}