{"as_of":"2026-08-17T08:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c5d35d058736b05c7455b314909918ed13dc334e596d654f7a5257ac36eb3f5a","coverage":[{"denominator":56,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":56,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T10:35:05.945635Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2412.16540/citation-record","integrity":"/paper/2412.16540/integrity","json":"/paper/2412.16540/citation-record.json","paper":"/paper/2412.16540"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:35:06.939870Z","title":"Long-tailed recognition via weight balancing","venue":null,"work_id":"88f81748-450b-4414-b7a5-f8ab19c29a76","year":2022},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.732910Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:8ee83425ce0c314d23c7f85decfd8ea50ca7367c0915dff84d1b13aa91adac1b","observation_id":"d27d92a6-5c5b-4e88-be0c-c79e8215cf5a","resolution":{"observed_at":"2026-08-11T10:35:06.943714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.927326Z","title":"Robust loss function for class imbalanced semantic seg- mentation and image classification","venue":null,"work_id":"9c875e1e-64ca-4313-8881-20cd1105e945","year":2023},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.737677Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:7b26d71d7ca07113e6494358a73862da51daa00fec05b85f2dce4cb59ebbfbf8","observation_id":"528119b9-9857-4e6b-b404-274c169c7b29","resolution":{"observed_at":"2026-08-11T10:35:06.931524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.915173Z","title":"A systematic study of the class imbalance problem in convo- lutional neural networks","venue":null,"work_id":"cf01b911-030b-4286-bda9-6807a7746c2d","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.741803Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:ab1a99ea988979a30b4b5d4a71999939ba0226bf95e3ba49c0e323a8c0009bc8","observation_id":"019dfc82-f648-4154-a926-d8f089cdb527","resolution":{"observed_at":"2026-08-11T10:35:06.919155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.902706Z","title":"Learning imbalanced datasets with label- distribution-aware margin loss","venue":null,"work_id":"3e198455-c660-472c-ac04-a86aa8d9551b","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.746183Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:813cf7bf6f5298330dc4c1beed163f8a7aa2df813db4e05bbf7b73c11cacdac3","observation_id":"4611ef65-49df-451a-9c8f-227cd6fa6a5e","resolution":{"observed_at":"2026-08-11T10:35:06.907468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.890003Z","title":"Area: Adaptive reweight- ing via effective area for long-tailed classification","venue":null,"work_id":"877f463d-de7a-4079-b052-44e0f460f6f8","year":2023},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.750138Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:bf59ccb1496ba4f23617b1f7bc31b7394c1c108dc1b6f37eeebdc6cedbe3abdd","observation_id":"387fc45e-a5d4-4c7d-b759-c3deea3e41a2","resolution":{"observed_at":"2026-08-11T10:35:06.894355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.876322Z","title":"Reslt: Residual learning for long-tailed recogni- tion","venue":null,"work_id":"a390510f-41fb-469c-a54e-2c4106bfd464","year":2022},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.754258Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:0af4a528960b4d5b946881617126379a9d6f3e8a9a8eee20df5f03304e27e292","observation_id":"c2dcbb3b-73a6-4076-bdf7-aedb85e5953e","resolution":{"observed_at":"2026-08-11T10:35:06.880877Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.862705Z","title":"Class-balanced loss based on effective number of samples","venue":null,"work_id":"57b138aa-5d4b-4cbd-8d72-89d82ba40843","year":2019},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.758191Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:256b67e4b9dff309505e07321da38cd84ede2f44efb97516d8618062895ad475","observation_id":"e197699a-6c08-4763-a497-c0c61b3cfeed","resolution":{"observed_at":"2026-08-11T10:35:06.867011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.850221Z","title":"Global and local mixture consistency cumulative learning for long-tailed visual recognitions","venue":null,"work_id":"f1ff2a43-7074-4f54-b0e8-4171a93c985d","year":2023},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.762279Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:b4083bebeeff165799e8bacc78f25df785a0a3b6eef9d7eaac2ac47c4c90905a","observation_id":"0e303561-1517-4b17-a18c-852d1a493a70","resolution":{"observed_at":"2026-08-11T10:35:06.854472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.836795Z","title":"On calibration of modern neural networks","venue":null,"work_id":"dda0542e-d884-4d5b-b9af-792022c25246","year":2017},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.766667Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:2fce632194d9e8c143a2cdd8098efb2fce6e760ede4863af6ce0f5382ba7ddf4","observation_id":"da4b4132-6b35-4a63-be0c-14e45256b35b","resolution":{"observed_at":"2026-08-11T10:35:06.841308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.824495Z","title":"Disentangling label dis- tribution for long-tailed visual recognition","venue":null,"work_id":"1f6ab57d-9238-42e6-9f00-970c77a85b40","year":2021},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.770345Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:875fea297110eeaaf3740c5e3ec4a6fabaf34a8b54349d5d0385391c7e317363","observation_id":"ee62d4b4-85f8-41fe-90ff-a531d1bccf7c","resolution":{"observed_at":"2026-08-11T10:35:06.828825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.810939Z","title":"Learning deep representation for imbalanced classi- fication","venue":null,"work_id":"0bc0b46a-efb9-45db-9965-c8d428aa58a4","year":2016},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.774120Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:087ed8b53e2b42524c759292cf33938e0aa958ce328807eab37afb474ad9d36f","observation_id":"7e18bf6f-b28c-4d12-a2d0-ee170cb7677a","resolution":{"observed_at":"2026-08-11T10:35:06.816232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.09217","last_updated":"2020-02-19T15:51:25Z","snapshot_observed_at":"2026-08-15T12:59:21.783827Z","submitted_at":"2019-10-21T09:03:19Z","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.09217","snapshot_observed_at":"2026-08-11T10:35:05.778004Z","title":"Decou- pling representation and classifier for long-tailed recogni- tion","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.778004Z"},"links":{"cited_paper":"/paper/1910.09217","citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:eb9e1393fc17d44e1b094b01add2df8991e58099ac2529aaeaf00a987c746a8a","observation_id":"4f968e5f-1502-4467-b786-3d9679a7d3df","resolution":{"observed_at":"2026-08-11T10:35:05.778004Z","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":"2026-08-11T10:35:05.782301Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.782301Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:5b1bd89ee0ee093c31892b961a84bf1732b0760c48959f1c187f038dfa151724","observation_id":"b8fcb5bf-5813-42bf-8ca5-780c5f4218db","resolution":{"observed_at":"2026-08-11T10:35:05.782301Z","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":"2026-08-11T10:35:06.790541Z","title":"Neural network classification and prior class probabilities","venue":null,"work_id":"8a1a94c2-cf4a-4fe0-af8d-a0fc18d45ad1","year":2002},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.786035Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:f4e247ce456a1d2c0dc0f586874f8f3967f994f76e73b10d62bb19f6aff8921e","observation_id":"9e873912-4ca6-49fe-b034-a3a52c774e82","resolution":{"observed_at":"2026-08-11T10:35:06.794813Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.779433Z","title":"Long-tailed visual recognition via gaussian clouded logit adjustment","venue":null,"work_id":"0bbf1e16-eeac-4a78-87a4-9400145a3c16","year":2022},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.789606Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:ea00bedc6ee0dc31a514dc4abc899b8b86140d4622dcfdaa651334c4c3685ff8","observation_id":"d2503283-78cd-4dae-bfc0-331e23580755","resolution":{"observed_at":"2026-08-11T10:35:06.782872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.768564Z","title":"Metasaug: Meta seman- tic augmentation for long-tailed visual recognition","venue":null,"work_id":"9e748a67-2b1a-4626-a058-8acd12fb5e24","year":2021},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.793456Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:eaf9fb89990d23f924792b88491a20ae023aeee10347892b3e9d5f736c12ae99","observation_id":"f32b9324-cf45-47d1-b2f0-a4b24e00857d","resolution":{"observed_at":"2026-08-11T10:35:06.772166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.757908Z","title":"Focal loss for dense object detection","venue":null,"work_id":"3fc6a901-07a5-4144-b558-10eb68400234","year":2017},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.797156Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:f269cf919602afe42b5c4ea8966e5b65218365884ba180e21027b3ef0fe97431","observation_id":"ad95231a-c290-45e2-aaa4-e4af2c7b44d0","resolution":{"observed_at":"2026-08-11T10:35:06.761428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.745922Z","title":"Inducing neural collapse in deep long- tailed learning","venue":null,"work_id":"7ff1414b-abe7-4dd4-a777-3b4d94bfd1d8","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.801020Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:e98a38454fdf422199fe058386da6ba468ee9b85f204588abb6ccf109fe80669","observation_id":"70112c32-df75-481f-b3ae-e4b729bda8ed","resolution":{"observed_at":"2026-08-11T10:35:06.750253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.733296Z","title":"Large-scale long-tailed recognition in an open world","venue":null,"work_id":"ee05c2a9-630c-44b7-9fbb-13ef4c521a49","year":2019},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.804984Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:6b12b32c594479d0a5097560bf6e3b1a5da0659221c1d8e7bb6079b3a7031266","observation_id":"28f20d1f-b957-42a4-a550-af6faae5a866","resolution":{"observed_at":"2026-08-11T10:35:06.737622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.721532Z","title":"Curvature-balanced feature manifold learning for long-tailed classification","venue":null,"work_id":"909276d5-c35f-40da-9ec9-6ad2889b46c4","year":2023},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.808859Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:59b07d093583040a605ae3f58ab96e988677e4138643a6544b2b67b3590ffcf7","observation_id":"14e5b90a-a70a-4558-9ca6-fef309d33486","resolution":{"observed_at":"2026-08-11T10:35:06.725738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.708893Z","title":"knn approach to unbalanced data distributions: a case study involving information extrac- tion","venue":null,"work_id":"0decc0ee-d27c-41fd-96df-472f01cc5b18","year":2003},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.812618Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:c2166707c5f1ead29fde35ea2cac8aa02ff4b923122ebc874cfd9b6b71d762a5","observation_id":"d781cc59-8d57-4304-9c5b-bd7541d2f78f","resolution":{"observed_at":"2026-08-11T10:35:06.713577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.696092Z","title":"When does imbalanced data require more than cost-sensitive learning","venue":null,"work_id":"53c2b4e0-13ef-49fe-93dd-a3a04ab8897b","year":2000},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.816480Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:9b29b17dae8f7240d3d0121bacce14b7d67410daf3d4cc9c4eb312922d14aa0c","observation_id":"041debcf-677e-435e-bbd9-7037d5c26aa2","resolution":{"observed_at":"2026-08-11T10:35:06.700887Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.07314","last_updated":"2021-07-09T21:23:25Z","snapshot_observed_at":"2026-08-08T11:03:52.719052Z","submitted_at":"2020-07-14T19:27:13Z","title":"Long-tail learning via logit adjustment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.07314","snapshot_observed_at":"2026-08-11T10:35:05.820125Z","title":"Long-tail learning via logit adjustment","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.820125Z"},"links":{"cited_paper":"/paper/2007.07314","citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:afae34ddb4c1e3ff87f8ddb5672182ef05ae0c8630f769af8ac86dcf28afcf13","observation_id":"9730ac3c-17cf-4d63-898f-cf0b242ef0eb","resolution":{"observed_at":"2026-08-11T10:35:05.820125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.09426","last_updated":"2023-04-19T05:35:09Z","snapshot_observed_at":"2026-08-16T15:39:23.797994Z","submitted_at":"2023-04-19T05:35:09Z","title":"Decoupled Training for Long-Tailed Classification With Stochastic Representations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.09426","snapshot_observed_at":"2026-08-11T10:35:05.824311Z","title":"Decoupled training for long-tailed classification with stochastic representations","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.824311Z"},"links":{"cited_paper":"/paper/2304.09426","citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:63b17c49543bc452691b1292c5110505aca55e25033a0e5d45f03f9f64460936","observation_id":"e3fcf2b0-fab4-4110-9989-9396f2e6a230","resolution":{"observed_at":"2026-08-11T10:35:05.824311Z","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":"2026-08-11T10:35:06.683281Z","title":"The majority can help the minority: Context-rich minority oversampling for long-tailed classifi- cation","venue":null,"work_id":"88dd3f1d-8bf5-4615-b886-dfd5e5f593ef","year":2022},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.828553Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:a6e4ec73eebcd15ce13d43c6e0735d455d50c10ad7b6f8a3adaa2d363e5235a8","observation_id":"9f4ac7af-b6fc-419c-bd66-c115511b93e3","resolution":{"observed_at":"2026-08-11T10:35:06.687924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.670178Z","title":"Feature directions matter: Long-tailed learning via rotated balanced represen- tation","venue":null,"work_id":"c86f6d06-f4d1-4e1d-8eae-af97bae8d66f","year":2023},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.832192Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:1fc896bd76f21b696ae8fac83e13d7d80fef2d56ff115ffd03e71f69daf7fab0","observation_id":"8157fea0-e826-4d38-9ae7-07922db0b842","resolution":{"observed_at":"2026-08-11T10:35:06.674881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.657402Z","title":"Optimal transport for long-tailed recognition with learnable cost matrix","venue":null,"work_id":"947fd005-c938-42c8-84be-1c90b6211566","year":2021},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.835893Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:3962d603177b9a2adfb201443a819c99a52e3359a012e726612119bacf2d95c5","observation_id":"e800ac07-638f-448b-9ec1-708316fee2ba","resolution":{"observed_at":"2026-08-11T10:35:06.661916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.644982Z","title":"Escaping saddle points for effective generalization on class- imbalanced data","venue":null,"work_id":"19fe35c6-a2ec-4f85-a5c0-6048b9cfd874","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.839943Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:0980da2dbd0ae7813fc5c160f70e5c36bfafc85a6e68f909b21154ba5e1d376c","observation_id":"5d1ab547-6562-442e-bc74-df3d62f083bf","resolution":{"observed_at":"2026-08-11T10:35:06.649396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.632352Z","title":"Balanced meta-softmax for long-tailed visual recogni- tion","venue":null,"work_id":"3015a288-5907-43ec-bbfd-d59a6d38f887","year":2020},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.843797Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:26edee7069d6ac26eb210e11b69b6264f94efdf51b4758f0aeb4bbff012de147","observation_id":"38aa92e4-3658-487b-a708-9f1e6432a12e","resolution":{"observed_at":"2026-08-11T10:35:06.636676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.618804Z","title":"Neural net- work classifiers estimate bayesian a posteriori probabilities","venue":null,"work_id":"1f543ffd-f214-4eba-b294-6fda328ffc48","year":1991},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.847410Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:76107a8c3be16be6ae8acae45ebaab6aad34f7fdac650df7b9245a0be558c5e8","observation_id":"8af51d58-c63a-4b83-b84a-1557e5b3ee4b","resolution":{"observed_at":"2026-08-11T10:35:06.623946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.572171Z","title":"Distributional robustness loss for long-tail learning","venue":null,"work_id":"649e079b-9e4d-4ade-84e6-6088ac657358","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.851110Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:ee644278a65bcd986ded5cd94f632b4f1e6c6171614e3605647efdedcf9c8626","observation_id":"f2ab269e-e8c9-4377-86b1-c7a605d69216","resolution":{"observed_at":"2026-08-11T10:35:06.606493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.425845Z","title":"Relative entropic optimal transport: a (prior-aware) match- ing perspective to (unbalanced) classification","venue":null,"work_id":"3aff8163-697b-4cf3-999e-8652e9ad4e9c","year":2024},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.854858Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:445dcc8019d991c98185ccecac16450f892e5a3b97b405090385ec5e542dc5e4","observation_id":"5037022b-d70d-41ff-85e3-f76df66b0735","resolution":{"observed_at":"2026-08-11T10:35:06.473067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.316032Z","title":"Meta-weight-net: Learn- ing an explicit mapping for sample weighting","venue":null,"work_id":"7ea4997b-9890-4d74-b1f9-0b2064d5bb26","year":2019},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.858635Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:bf5aeb3b91ae4438b2a703d721a03fd48fe95a6c673440c0e8d84fb9560e2668","observation_id":"302baa33-8c20-4665-8c71-dd5c4a8ec716","resolution":{"observed_at":"2026-08-11T10:35:06.363857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.303031Z","title":"Rethinking the inception ar- chitecture for computer vision","venue":null,"work_id":"16caf655-913f-4302-b665-6282d18137b4","year":2016},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.862476Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:d187c812499e2a14585c1fed281ca2b379c2bcf0c59b4137a85229cf48720c1b","observation_id":"4eb75d48-cde1-44dc-a095-c9ec29970d94","resolution":{"observed_at":"2026-08-11T10:35:06.307298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.289375Z","title":"Long- tailed classification by keeping the good and removing the bad momentum causal effect","venue":null,"work_id":"9658affb-852d-45ec-8e6c-358116e4306c","year":2020},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.866160Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:f2f27f86445c2c9e640ceffa17d20893f423788c78c000c2ca2cec583ac2615d","observation_id":"36fc4394-0885-4746-a677-5042d80ce773","resolution":{"observed_at":"2026-08-11T10:35:06.294093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.276183Z","title":"Improving tail-class representation with centroid contrastive learning","venue":null,"work_id":"ee059ef0-ead5-4150-94e8-277b6ab3face","year":2023},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.870207Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:2e56fba8e17b1fe9d6d4f603a23d7d61e55e65b9157eb9d26ef075e06abf04bf","observation_id":"ecf18e03-3996-4acd-93c4-ea6569aeab1a","resolution":{"observed_at":"2026-08-11T10:35:06.280600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.263394Z","title":"The inaturalist species classification and de- tection dataset","venue":null,"work_id":"dca9b292-917a-4f0c-92be-80c2b3f0e29b","year":2018},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.874067Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:da8d61b6bb0f2762941a6d5705b4d15993e7a83c281a1916f43acf6ee637692a","observation_id":"84b76aec-c90f-4bbc-b237-c6adfe950ee8","resolution":{"observed_at":"2026-08-11T10:35:06.267837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.251249Z","title":"Solar: Sinkhorn la- bel refinery for imbalanced partial-label learning","venue":null,"work_id":"93f41eb4-72b7-4bfa-b546-102f004a83e3","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.877943Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:4d417a259ec2387de6776d5f4c367c3f3d0fd51a968471835a051c0317fc2a2c","observation_id":"4e6b9c6d-df83-4188-bece-166be0a78937","resolution":{"observed_at":"2026-08-11T10:35:06.255439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.239551Z","title":"Rsg: A simple but effective mod- ule for learning imbalanced datasets","venue":null,"work_id":"7b15c3e9-ade1-4c50-9565-898300a7208b","year":2021},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.882292Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:9b09a83e4edf58e144c489b42c1ab2e34ffb4be52786f4dec2994940a89c2b4d","observation_id":"5e304cec-7466-47da-bcfc-f8a531d22c84","resolution":{"observed_at":"2026-08-11T10:35:06.243991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.226846Z","title":"Seesaw loss for long- tailed instance segmentation","venue":null,"work_id":"b8e9f2a4-007f-4221-a8e0-840b21abfdf1","year":2021},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.885858Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:a1958d5ac9f3ddb4d196e78b43e5ba8a871ef1aace9189bf145590c39b0bd4fb","observation_id":"db8dc2b0-ffb0-4223-b15f-c59746e30c0d","resolution":{"observed_at":"2026-08-11T10:35:06.231054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.213729Z","title":"Adaptive class suppression loss for long-tail object detection","venue":null,"work_id":"ec45f453-df88-483f-8ba8-f99d4829ecbe","year":2021},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.889509Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:f64a9d3782acce43c912a34e5dbcb73a67764037ecae3926d82dee64a0dbca9d","observation_id":"ed0b6077-ac5e-427b-a018-b86ffdf3e53f","resolution":{"observed_at":"2026-08-11T10:35:06.218394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01809","last_updated":"2022-05-01T18:00:20Z","snapshot_observed_at":"2026-08-16T19:15:55.160899Z","submitted_at":"2020-10-05T06:53:44Z","title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01809","snapshot_observed_at":"2026-08-11T10:35:05.893135Z","title":"Long-tailed recognition by rout- ing diverse distribution-aware experts","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.893135Z"},"links":{"cited_paper":"/paper/2010.01809","citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:1dc49f4476b3aa4ddc0c336fb5a9e998f3e0e62387f8c28e97ea7f40b57cb157","observation_id":"ea967dec-2ac3-45fe-b15c-d3057cf158a3","resolution":{"observed_at":"2026-08-11T10:35:05.893135Z","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":"2026-08-11T10:35:06.199617Z","title":"Margin calibration for long-tailed visual recognition","venue":null,"work_id":"36a9e7b6-9253-4d2e-8182-5a94f41cbf48","year":2023},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.897177Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:008f8bafaf3cae4ec5e81b647742ee50c7e9213cde9afbb73f84fa1e6c5215e8","observation_id":"9b9f3d07-3d7f-4080-adb1-99da4324c3ac","resolution":{"observed_at":"2026-08-11T10:35:06.204265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.186505Z","title":"Learn- ing to model the tail","venue":null,"work_id":"53e83e9b-2130-44f4-8037-5f86f4d9ce3c","year":2017},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.901050Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:215eb889e4b1c3562b769934fff9db31d06e1a62eb03eecdb9a0219daec442fd","observation_id":"5bb118a9-2c16-4357-ac69-d62127d40600","resolution":{"observed_at":"2026-08-11T10:35:06.190547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.172998Z","title":"Distribution alignment: A unified framework for long-tail visual recognition","venue":null,"work_id":"f755bcf3-28d0-443a-8f7b-92f290dfb41d","year":2021},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.904559Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:a59e2377870f736896b03f728236dc3f3f06e52b5403a31c1670c1482eabb1cd","observation_id":"28d3e8aa-8b41-4af9-829c-6ed19978b9f4","resolution":{"observed_at":"2026-08-11T10:35:06.177819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.160013Z","title":"Im- proving calibration for long-tailed recognition","venue":null,"work_id":"6e5f9ef8-4244-4f56-bf8a-19e02e4f7712","year":2021},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.908243Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:c26c67fde4104b700e809419b3a20e5960ddab234b9e6b26eafaf19c4940edc2","observation_id":"2dc63996-dd41-477f-b89b-5d35d6c517b7","resolution":{"observed_at":"2026-08-11T10:35:06.164726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.147114Z","title":"Class-conditional sharpness-aware mini- mization for deep long-tailed recognition","venue":null,"work_id":"8f3e8d8e-4f32-44b2-a287-2324d40ef14c","year":2023},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.911812Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:1ba636626198ab111db44960e13ff779666e68001fa82c29ccd1c6292a725b18","observation_id":"bc6c19d4-d3ab-4509-acde-6c7917ca6bcd","resolution":{"observed_at":"2026-08-11T10:35:06.151525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.134633Z","title":"Balanced contrastive learning for long-tailed visual recognition","venue":null,"work_id":"c52c40ad-d04c-4b5e-88dc-2f1c51091143","year":2022},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.915321Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:4a1fa92e1535162ca28f6145b1bfe4af85268929d4e533bfa23d89dcd14d359f","observation_id":"a0b36242-bf12-4f1e-a98d-a67cfa3df101","resolution":{"observed_at":"2026-08-11T10:35:06.138998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.122174Z","title":"In Stage 2, for both classifier and feature tuning cases, we train the models for 4000 iterations","venue":null,"work_id":"d2c59525-a337-4c60-918d-2fb87779778a","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.918995Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:b0598062c8d103b03e9c93116f24de3f824da32b4ecb0d9bcc57fa9d123512b7","observation_id":"201183fb-3efd-4645-8cd0-6b74e660ff70","resolution":{"observed_at":"2026-08-11T10:35:06.126528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.109836Z","title":"For the sake of complete- ness we provide a mathematical justification using the ap- proach of moment matching","venue":null,"work_id":"3621bf2c-ad5c-42a8-8a76-260182cd3650","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.922776Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:0876f5fa51b71005fd14b5bd5076a8992886bf4078f88b9cc06e1a4577e788b1","observation_id":"3c09dcdc-841f-4ad6-af0a-119f4c4ddeb9","resolution":{"observed_at":"2026-08-11T10:35:06.114294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.096405Z","title":"From the figure it is clearly observed that model bias is quite different from empirical bias estimated using class frequen- cies","venue":null,"work_id":"57635a81-bbc1-4037-9649-490878cdc69a","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.926646Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:7591887d0dc688ea6d93190013fcc52c1059480933968abd3491aa2ceaddc232","observation_id":"2199313a-0070-4791-8973-f07844136752","resolution":{"observed_at":"2026-08-11T10:35:06.101076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.082911Z","title":"We note from the table that proposed approach achieves highest overall accuracy while shot-wise accuracies are not affected much","venue":null,"work_id":"2fe14257-ebe1-47b8-87f9-858470b62f5a","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.930558Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:b474e44631312900a331fd5f12565ee4c4fc895ff8d7abc8bb49a75618e6875d","observation_id":"35b20472-538a-4d23-a2bf-7b9476b49b1a","resolution":{"observed_at":"2026-08-11T10:35:06.087147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.069930Z","title":"8 we compare model performance for test-time shifted distributions with additional baselines and a few more distribution shifts","venue":null,"work_id":"89be7e19-b7e3-4dbc-9e40-f0cbeae34d7e","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.934473Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:27c3561420f52cef4daaa31040693a07e5c746d1821fccc50e54f2203e63667b","observation_id":"06c1a375-4a90-4297-8481-84127b7228c4","resolution":{"observed_at":"2026-08-11T10:35:06.074330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.056046Z","title":"The performance on iNaturalist18 for Stage 1 baseline (CE) and Stage 2 (CL and FT) are shown","venue":null,"work_id":"29be8924-3eb1-4d5e-bd2c-f0f9e6a21113","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.938321Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:d88e931fc07296111b30786a88d3010d2fd1e1e06230827ca9e047fd9220b6fe","observation_id":"da4b393e-2178-4dd6-92f4-654105a27feb","resolution":{"observed_at":"2026-08-11T10:35:06.060334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.042919Z","title":"The manually specified smooth- ing guidance matrix Q can be seen as a generic representa- tion for the effective prior","venue":null,"work_id":"cede0be8-e1f8-43a6-a982-f94213fe6015","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.941971Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:1338579ee4c6f5f408cfa202d4d3a2b387091ad0262b2024cb6b4996e158f851","observation_id":"8257f381-0dab-469d-be15-ba685e7e903d","resolution":{"observed_at":"2026-08-11T10:35:06.047519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-11T10:35:06.027517Z","title":"The block diagram illustrates the different stages involved in the process starting from bias accumulation in traditional training to bias removal us- ing the proposed method","venue":null,"work_id":"448f8865-08cc-4114-8932-b82a6c959143","year":null},"citing_paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T10:35:05.945635Z"},"links":{"citing_paper":"/paper/2412.16540"},"observation_digest":"sha256:86d81ab1f678c4ff34419565f6522055214e33fa82ce5b7cbe2636c7affb5263","observation_id":"6ef7e385-535f-48a5-9062-bc38645d0485","resolution":{"observed_at":"2026-08-11T10:35:06.033615Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.16540","last_updated":"2024-12-21T08:49:02Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T07:40:29.341991Z","submitted_at":"2024-12-21T08:49:02Z","title":"Prior2Posterior: Model Prior Correction for Long-Tailed Learning"},"reference_resolution":{"displayed":56,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":51},"total_outbound_references":56},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 0 inbound Pith citation observations for arXiv:2412.16540."}