{"as_of":"2026-08-09T00:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cdc0d95d8d3e2bf2cb443ff9f9e35f35a7db37439bd1877c4f22e327d3e7a835","coverage":[{"denominator":67,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":67,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T22:45:49.519933Z","state":"measured"},{"denominator":67,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":67,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2508.06622/citation-record","integrity":"/paper/2508.06622/integrity","json":"/paper/2508.06622/citation-record.json","paper":"/paper/2508.06622"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T22:45:50.987771Z","title":"Asymmetric loss functions for learning with noisy labels,","venue":null,"work_id":"e46c5c36-7503-4602-99ab-cb071b256b87","year":2021},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:44.030497Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:dded7626b0e440b80c498163d00612e02fb81c4767235513bf46ea2aba3da415","observation_id":"1e40b76d-98d0-4e15-85b8-acda9915a59a","resolution":{"observed_at":"2026-08-05T22:45:50.992447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.973451Z","title":"Label distributionally robust losses for multi-class classification: Consistency, robustness and adaptivity,","venue":null,"work_id":"12db4b52-df7b-4643-b1b3-4d4122f9e187","year":2023},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:44.122460Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:f5846fa6809ad7caa0903e540dda773683a1bd8758d431305db40034108a3bb1","observation_id":"8ed0522b-4c8d-4daa-bfc1-3cef6288925c","resolution":{"observed_at":"2026-08-05T22:45:50.977938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.957812Z","title":"Asymmetric loss functions for noise-tolerant learning: Theory and applications,","venue":null,"work_id":"ddf84fe7-06c7-40db-ae33-63c98d959496","year":2023},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:44.181737Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:159a94f0279e136a7544c6ddfa44843f0361693756bff874df46bc0b1ef85f60","observation_id":"053e2d75-c832-4b12-9077-8d85c1976fa3","resolution":{"observed_at":"2026-08-05T22:45:50.963072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.942539Z","title":"ϵ-softmax: Approximating one- hot vectors for mitigating label noise,","venue":null,"work_id":"1ff4d102-59cf-4fc7-a61a-b948776f8b84","year":2024},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:44.252887Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:605a4709625c83806a9117d53659bd6925d70d3c3345041c740691c77303a779","observation_id":"73718063-76d8-4482-abc6-8d534d4308f8","resolution":{"observed_at":"2026-08-05T22:45:50.947376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.927441Z","title":"Learning with noisy labels,","venue":null,"work_id":"b3d9aa44-c16a-4d0d-b3f5-f6c34df10cb9","year":2013},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:44.336697Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:8d1542cd73560de293a9cf41009defc90a9b132cf76059ddcbaddb40039562cb","observation_id":"a7db535d-ee84-45c3-ae66-11718bf991a8","resolution":{"observed_at":"2026-08-05T22:45:50.931891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.911067Z","title":"Classification with noisy labels by importance reweighting,","venue":null,"work_id":"a56ba031-dab9-4bce-8851-1660ef556ba4","year":2015},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:44.424512Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:6db0b668104b8b299d0b035923d4878de4c176cedd2762ecc00f1e83f94fe380","observation_id":"4ab22b12-287a-4a84-a3e0-3e1b369044cf","resolution":{"observed_at":"2026-08-05T22:45:50.916040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.875448Z","title":"Are anchor points really indispensable in label-noise learning?,","venue":null,"work_id":"abfcb97a-695a-4b4c-a6cb-2d71bce9ad5a","year":2019},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:44.635347Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:67e2b0e75c48146f39a32bf7385c985d774664179a14a7103a585f5100078883","observation_id":"ca30c358-b221-42b5-82ef-ccce2a6003e7","resolution":{"observed_at":"2026-08-05T22:45:50.880767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.859116Z","title":"Dirichlet-based per-sample weighting by transi- tion matrix for noisy label learning,","venue":null,"work_id":"71ab63dd-0ee9-45bd-b2bf-7bee8e1b40f3","year":2024},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:44.757691Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:83a20ef5a980c459904b3ea7e56ced683e89d43b8344b7c1c9a1572fab7c5f38","observation_id":"b53c419e-ae76-40d0-a98f-668db5c1873b","resolution":{"observed_at":"2026-08-05T22:45:50.864215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.843553Z","title":"Contrast to divide: Self-supervised pre-training for learning with noisy labels,","venue":null,"work_id":"a57d98be-7a80-4caf-ac0c-3befa0a5a770","year":2022},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:44.850332Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:5ec384b28b7108ab26698a3cf58fd72bcdd5d940884e3e8f1f52ee40c9bc719d","observation_id":"3598fed4-7304-47c3-9216-0a889c07770d","resolution":{"observed_at":"2026-08-05T22:45:50.848308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.825788Z","title":"Early-learning regularization prevents memorization of noisy labels,","venue":null,"work_id":"1eca3d06-71fb-4f5a-9016-a68790a5f26a","year":2020},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:44.945001Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:d746fcf2cfa5c70d893e71d80ef8cf666a77d646f4c556c5859edbaf21d96605","observation_id":"095cd6b3-c958-41e3-8086-7ed616b50095","resolution":{"observed_at":"2026-08-05T22:45:50.831209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.811019Z","title":"mixup: Beyond empirical risk minimization,","venue":null,"work_id":"3a483f34-38bb-4977-a873-750bc1184964","year":2018},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:45.058332Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:d03c1098821a6f67c0edcbba89024e749912fabe4e97e875523e4504b4cb3ea3","observation_id":"bdb32e78-9c1f-40a7-8a38-b57d0a2c97cc","resolution":{"observed_at":"2026-08-05T22:45:50.815452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:45.149027Z","title":"Dividemix: Learning with noisy labels as semi-supervised learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:45.149027Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:68be6806adfa6a2e12158527774cbd6655f5ea2fe804ed1ee81fa9842ece7749","observation_id":"d1bb8be4-f55a-4ab6-b9d6-9d6bcdaec46c","resolution":{"observed_at":"2026-08-05T22:45:45.149027Z","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":"2026-08-05T22:45:50.783451Z","title":"Robust training of deep neural networks with extremely noisy labels,","venue":null,"work_id":"1ded2e06-3fdb-43d0-b0fd-66eb0ce04a7d","year":2020},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:45.233952Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:dcece7d11c9f965a3cc291e7737af27b123b93891b56cf4c4822595c5ed9ccf2","observation_id":"04bca06b-f0d8-44a6-b64a-cd8dbed1575c","resolution":{"observed_at":"2026-08-05T22:45:50.788885Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.766965Z","title":"Robust training under label noise by over-parameterization,","venue":null,"work_id":"fd5627de-582c-4e71-a73a-295dbb09ae88","year":2022},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:45.305711Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:e2e599e4db366051db0ee1e1f7ef505057c04b29cb6dbef32216957d6f8afdb5","observation_id":"4409c445-b92c-4e8f-bccb-d653a4c60d20","resolution":{"observed_at":"2026-08-05T22:45:50.771873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.751369Z","title":"Csot: Curriculum and structure-aware optimal transport for learning with noisy labels,","venue":null,"work_id":"daa79fb9-6f05-44b7-9540-863ff7d4c911","year":2023},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:45.415135Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:a9d2ad9a3ea0c9e22e50fcb23ced3a0bafd29ab930ca2543e4d3d0a46b2b020f","observation_id":"e04b0f24-5b23-4d59-8290-d2c401ea5834","resolution":{"observed_at":"2026-08-05T22:45:50.756404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.736057Z","title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence,","venue":null,"work_id":"0d50603c-a0bd-48f5-a0cb-0109cf8fcadc","year":2020},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:45.507730Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:a5f455cf61fdfbd6dc4bee6abee93f6e17e493b0cbd701cda067ba1c0a48e8c6","observation_id":"d6b316eb-ee56-49c5-acc6-daf027c9614d","resolution":{"observed_at":"2026-08-05T22:45:50.740653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.719302Z","title":"L2B: Learning to bootstrap robust models for combating label noise,","venue":null,"work_id":"d82f8a1e-b09c-48f3-a4c1-5c0dd6f5629a","year":2024},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:45.594505Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:9dcaf886d039149896e409fdf66da377d91dd52cf717e3fa7504e570c32359ab","observation_id":"7abfe8c2-d3ef-4743-ad03-5e512b5026c2","resolution":{"observed_at":"2026-08-05T22:45:50.724794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.701520Z","title":"Badlabel: A robust perspective on evaluating and enhancing label-noise learning,","venue":null,"work_id":"201045ae-710a-4141-83ea-b7e5be657105","year":2024},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:45.688406Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:6a1fe4b6a566355612a2b42971380865e376e6f2ba05e34695c7e1b0e407e4f6","observation_id":"2b169b21-d2f4-490b-847b-2b6a44715fcd","resolution":{"observed_at":"2026-08-05T22:45:50.706995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:45.771576Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:45.771576Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:6d07ff613018eb64b0c0b129fc636d7ef4cd1d964cbb094c797c81d5755fe855","observation_id":"64de6773-31e4-4859-951a-72ee7df6602c","resolution":{"observed_at":"2026-08-05T22:45:45.771576Z","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":"2026-08-05T22:45:50.675473Z","title":"Learning to reweight examples for robust deep learning,","venue":null,"work_id":"7f5acb54-eeb1-4e2f-b807-aa32a9c6337f","year":2018},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:45.860845Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:680b4221625c8b8e0c9ebb10e685ef587a701c60ad4af367b5214f71c6b6bf60","observation_id":"d32f72f3-9b48-4ff0-945a-6aed6278d05c","resolution":{"observed_at":"2026-08-05T22:45:50.679970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.660420Z","title":"Combating noisy labels with sample selection by mining high-discrepancy examples,","venue":null,"work_id":"5ffc57e8-a615-444c-882b-dcd532b90cf2","year":2023},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:45.920173Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:01c61e08ab3fc11ae9a70117527bcb3d35c30d3412d86d6eabb5df403c206592","observation_id":"9a3aa928-e818-4114-b555-170b0a98b079","resolution":{"observed_at":"2026-08-05T22:45:50.664972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.645799Z","title":"Focal loss for dense object detection,","venue":null,"work_id":"6688b5ff-2a44-4efb-9472-2168ab284848","year":2017},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:46.013815Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:c167ecff9d0920d26211c518556f54c232c71b2214d6df44e767f11c20b628d7","observation_id":"6d5eb326-1907-43ca-84a3-9597610da3ab","resolution":{"observed_at":"2026-08-05T22:45:50.650251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.630285Z","title":"Robust loss functions under label noise for deep neural networks,","venue":null,"work_id":"3f3d2b88-9514-495f-a6d9-8f239c98396d","year":2017},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:46.141729Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:1951256c33e1bdb970db7cc446439cddc1268b502fa40de6bebd0b241a0a60da","observation_id":"50ef488f-c405-4ebe-81f8-4671e11321d4","resolution":{"observed_at":"2026-08-05T22:45:50.635029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:46.215715Z","title":"Generalized cross entropy loss for training deep neural networks with noisy labels,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:46.215715Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:057ea78ed96e13abf81f16986c86d5ae1a6d5eb75844442a0a19ad22b36acb22","observation_id":"eab4654a-876d-44f6-a98c-014de55183f4","resolution":{"observed_at":"2026-08-05T22:45:46.215715Z","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":"2026-08-05T22:45:50.602198Z","title":"Symmetric cross entropy for robust learning with noisy labels,","venue":null,"work_id":"d59a0d29-78e4-4e78-a0b5-420c9a904c64","year":2019},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:46.407146Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:814a611bf2a31ed45c3a1dc78c77258437d89168801717ae4681f3266bca792f","observation_id":"201bc24b-ce76-4a21-9bbf-61652cd22ccd","resolution":{"observed_at":"2026-08-05T22:45:50.607394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:51.002798Z","title":"Normalized loss functions for deep learning with noisy labels,","venue":null,"work_id":"9864d0f5-ac27-4673-b65c-b3f80df9ad36","year":2020},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:46.496668Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:c804002dba8806b67d4ac4728973cfcbfb7f446721d4cdd227f6010010d0a9ba","observation_id":"b282c5ed-6257-4b9a-89a4-c0a6b428e3ec","resolution":{"observed_at":"2026-08-05T22:45:51.007881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.585858Z","title":"Mitigating memorization of noisy labels by clipping the model prediction,","venue":null,"work_id":"55abaeb5-542f-4678-a21f-9f8baa8d0fd5","year":2023},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:46.593471Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:c1e701a6ac8afd1f3651837628a0bbab85311373ac59f982777b777163e68003","observation_id":"73a5b8b0-8193-4ba4-9ce5-19e6b1a57c41","resolution":{"observed_at":"2026-08-05T22:45:50.590942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.571244Z","title":"When optimizing f-divergence is robust with label noise,","venue":null,"work_id":"4adc7a44-0982-48e2-99ba-51f9c6698188","year":2021},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:46.686886Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:ed03e6b77d57dee2ad841d30a630dbe620da29a9cde2a5e00f9a1385c2996c9a","observation_id":"77e90f1b-1a71-4693-af49-bb6eee7f82b3","resolution":{"observed_at":"2026-08-05T22:45:50.575406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.20531","last_updated":"2025-02-14T22:48:52Z","snapshot_observed_at":"2026-07-06T18:23:01.681030Z","submitted_at":"2024-05-30T23:13:01Z","title":"Mitigating the Impact of Labeling Errors on Training via Rockafellian Relaxation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.20531","snapshot_observed_at":"2026-08-05T22:45:46.782342Z","title":"Mitigating the impact of labeling errors on training via Rockafellian relaxation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:46.782342Z"},"links":{"cited_paper":"/paper/2405.20531","citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:1918e94f8c8d1757bcc1698de2860cfa364040b122aec048ff9bba74a144e584","observation_id":"985bfdfa-34f9-4c4d-85c9-7bfc909af5b7","resolution":{"observed_at":"2026-08-05T22:45:46.782342Z","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":"2026-08-05T22:45:50.555374Z","title":"How does disagreement help generalization against label corruption?,","venue":null,"work_id":"fba51fc3-9f08-4ac1-85f3-d2b2abb2870c","year":2019},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:46.875977Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:21f42eff601d29dbacc7af56b4d39b373e6d2a67033c9e377098df0e5eff48b3","observation_id":"6ebf05fa-4361-4151-90a7-5f1b014e641f","resolution":{"observed_at":"2026-08-05T22:45:50.561026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.540893Z","title":"A general class of coefficients of divergence of one distribution from another,","venue":null,"work_id":"9911a139-8df3-4069-8218-f1ae971f2096","year":1966},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:46.962218Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:3f898346bf7ed24e175332b3f03490272f4fd01f880437c27bfe5ebe68a2fd5b","observation_id":"e922b30f-3be4-4ab5-8a74-1bc2b52e41c5","resolution":{"observed_at":"2026-08-05T22:45:50.545294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.524826Z","title":"On information-type measure of difference of probability distributions and indirect observations,","venue":null,"work_id":"fb910d12-2de6-4435-a488-fbb1cfa66663","year":1967},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:47.083798Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:ee1c922544b255a022d9d7e86be1810447e8063442d10fcdf5d188946401c329","observation_id":"29a3c3a7-4969-48e1-9ec4-e0571e2790e0","resolution":{"observed_at":"2026-08-05T22:45:50.530311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.509669Z","title":"Minimization of divergences on sets of signed measures,","venue":null,"work_id":"99aa7b34-41e6-405a-ad22-617a5f75d019","year":2006},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:47.208303Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:d47d2e30efd7fdc531747826daf1549ee29e2fecf5d49ff3425883e2621e5b80","observation_id":"c2c31bc2-6e02-441f-9f87-f3ffe556fc8a","resolution":{"observed_at":"2026-08-05T22:45:50.514313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.493530Z","title":"Estimating divergence functionals and the likelihood ratio by convex risk minimization,","venue":null,"work_id":"05905ad3-c578-44b1-9211-8d83c1dad105","year":2010},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:47.304094Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:73913cc5dcd2086f9c42b30907f55a0e600a11c95afe8c92e08828152013ea5b","observation_id":"31c229f3-7a94-455f-a085-c1e2145b8dbb","resolution":{"observed_at":"2026-08-05T22:45:50.498704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.478252Z","title":"(f, Γ)-divergences: Interpolating between f-divergences and integral probability metrics,","venue":null,"work_id":"fdaec993-c43d-4355-8204-18c121cc32e3","year":2022},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:47.371195Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:7ce287bfd45854fd891e7edadfadd501f91ce68aaf9521bd0bb1a43f8a418719","observation_id":"591aabac-287d-4d2b-b3f3-6d1f85292d7c","resolution":{"observed_at":"2026-08-05T22:45:50.483328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.462688Z","title":"On divergences and informations in statistics and information theory,","venue":null,"work_id":"02f80d60-31b6-4080-9f99-48bcb4b1cb46","year":2006},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:47.461174Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:248a76853a9ef897e65973e624c86714979eee75a724c1558eab14ae23a4b04b","observation_id":"9128a903-e568-4095-b0b7-7dd50ae90fac","resolution":{"observed_at":"2026-08-05T22:45:50.467991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.447644Z","title":"Ponstein, Approaches to the Theory of Optimization","venue":null,"work_id":"389717be-c5c8-417a-9468-d0f27107a19e","year":2004},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:47.546400Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:7b7404ef40fb7a185025875b06362c3a22d2275c0ad631bc8f9e4a4adff95a86","observation_id":"08df948b-4379-42a7-8d5c-4f612103ee75","resolution":{"observed_at":"2026-08-05T22:45:50.452180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.431216Z","title":"An old-new concept of convex risk measures: The optimized certainty equivalent,","venue":null,"work_id":"e1634c38-ea91-4042-925e-5b682ecc77c7","year":2007},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:47.638607Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:be2fd379bf4c0b0c86765fa8797d216cedd6b3fc3601190563aab61ec0316ec9","observation_id":"1069cc57-7bce-4b85-961b-632259462679","resolution":{"observed_at":"2026-08-05T22:45:50.436639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.414835Z","title":"Entropic value-at-risk: A new coherent risk measure,","venue":null,"work_id":"2d97a59c-1c9f-40a1-9ef4-eeadd9c360f8","year":2012},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:47.732835Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:13e541e5f8c3959320e39d1d4db761230d6f6173d96bde16c260e3c0b5d32357","observation_id":"fbbee183-559b-499c-8053-dec696a0e9ba","resolution":{"observed_at":"2026-08-05T22:45:50.420137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.399488Z","title":"Theoretically principled trade-off between robustness and accuracy,","venue":null,"work_id":"9caafa56-0179-47e9-98f7-72d156cccc59","year":2019},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:47.835605Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:c2f6a691fac908dd6e75505694bcecac70ad2e583ec67815b873b6106da029bd","observation_id":"6c8a4428-5748-4a02-b5e4-fa4f77e105da","resolution":{"observed_at":"2026-08-05T22:45:50.404168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.383941Z","title":"Improving adversarial robustness requires revisiting misclassified examples,","venue":null,"work_id":"56dac65c-c56b-4c20-a510-6f3041c117b8","year":2020},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:47.917116Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:308f82406760be0737709e2e680df4de2a97e263ca77ff8039e74bd8f7f6a94e","observation_id":"7c90df48-931e-4144-895a-4ae47d67bef4","resolution":{"observed_at":"2026-08-05T22:45:50.388817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.362843Z","title":"A unified Wasserstein distributional robustness framework for adversarial training,","venue":null,"work_id":"7845dcc6-b89a-445d-847c-5b6df499250d","year":2022},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:47.975586Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:a30ff0faee4da7899a2f425ee7298cbb86860d4adf1060caa02b0d7623971600","observation_id":"252e1bd7-f3f2-44c4-b3d0-eb0958a6b38b","resolution":{"observed_at":"2026-08-05T22:45:50.371555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.03791","last_updated":"2025-07-24T15:47:29Z","snapshot_observed_at":"2026-07-06T16:15:47.081422Z","submitted_at":"2023-09-07T15:41:45Z","title":"Optimal Transport Regularized Divergences: Application to Adversarial Robustness","version":3},"cited_work":{"arxiv_id":"2309.03791","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.03791","snapshot_observed_at":"2026-08-05T22:45:49.726579Z","title":"Optimal Transport Regularized Divergences: Application to Adversarial Robustness","venue":"cs.LG","work_id":"c19af19d-639c-4c59-8813-b7a9dbf266a0","year":2023},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.034335Z"},"links":{"cited_paper":"/paper/2309.03791","citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:900d099c9ddc04303dcdaf399c2798e6e4ab70ba74d9e86b9b21e3faeecfbd4b","observation_id":"30fa6b75-c114-4a73-8f08-9044ea89e7b3","resolution":{"observed_at":"2026-08-05T22:45:49.793371Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.344695Z","title":"Nlnl: Negative learning for noisy labels,","venue":null,"work_id":"6001c90b-7bc2-44d4-b978-b01ccddf1b94","year":2019},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.107928Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:2081a0121de6bdcdb4be5920185548a72aa5f607fc9197df7971d241e6a71393","observation_id":"64f02eb4-9b04-4aa5-87c9-c5b9a2abb715","resolution":{"observed_at":"2026-08-05T22:45:50.350630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.893653Z","title":"Making deep neural networks robust to label noise: A loss correction approach,","venue":null,"work_id":"db8baa45-0d84-4fd9-8609-d5f2004393a1","year":1944},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.192432Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:fc06ad00ffcbb5198eeb9447491619dd4a64421f6f94ce5d8f7cbb20fedc5524","observation_id":"6bddb5ea-8768-4767-8b0a-045df919cbfe","resolution":{"observed_at":"2026-08-05T22:45:50.899220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.326193Z","title":"Peer loss functions: Learning from noisy labels without knowing noise rates,","venue":null,"work_id":"c99e5f86-c39d-4645-ab69-199b221bf774","year":2020},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.252916Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:50e4665c1e572d39a5a78cccbce9f38855055ed072ddab5da56a59420bf5d4a6","observation_id":"38796b1a-1caf-4f16-947f-7b45ebbfde63","resolution":{"observed_at":"2026-08-05T22:45:50.332846Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.308301Z","title":"Provably end-to-end label-noise learning without anchor points,","venue":null,"work_id":"7887ce6e-cbdc-4dbc-87d8-14895df8c064","year":2021},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.331925Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:20a6a558ddaa162e20cb853c0c6b42531410b588d27894ddf4dc2f99892655e6","observation_id":"66f35d8d-93f4-46ac-9182-c71273508708","resolution":{"observed_at":"2026-08-05T22:45:50.313798Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.290352Z","title":"To smooth or not? when label smoothing meets noisy labels,","venue":null,"work_id":"8c77a76d-c9bd-48b3-adda-0af54920a8ca","year":2022},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.407388Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:a50beac10c4c9245b1e08287b42d4f327d9fc0f66fb83a540ac0e135f1907863","observation_id":"47febcf2-e3ae-44a9-9900-2033f7127c67","resolution":{"observed_at":"2026-08-05T22:45:50.295259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.16889","last_updated":"2023-08-22T06:15:15Z","snapshot_observed_at":"2026-07-06T16:00:50.467537Z","submitted_at":"2023-07-28T10:57:38Z","title":"Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective","version":2},"cited_work":{"arxiv_id":"2307.16889","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.16889","snapshot_observed_at":"2026-08-05T22:45:49.560171Z","title":"Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective","venue":"cs.LG","work_id":"dac52057-961b-4a72-9bd8-5cfccc9c64b2","year":2023},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.464077Z"},"links":{"cited_paper":"/paper/2307.16889","citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:0b0e163e9fa2400d5b97fa8c4abe42f1da0136347013d2f28e67c1528e201525","observation_id":"3f19fe15-ec64-4642-96f6-c3e7acacc617","resolution":{"observed_at":"2026-08-05T22:45:49.634224Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.274359Z","title":"Understanding and improving early stopping for learning with noisy labels,","venue":null,"work_id":"3e54caca-c60d-4e09-bf76-bc94c2d548d5","year":2021},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.543990Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:356022eed40a3d2d317ce9e0142ea3e8e5ccc804f44f0ee0b45103629faea4cd","observation_id":"eada9ec6-cb45-48cc-9e0b-0abc9cc6f35c","resolution":{"observed_at":"2026-08-05T22:45:50.279871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.257060Z","title":"Learning with instance-dependent label noise: A sample sieve approach,","venue":null,"work_id":"29b5bc5d-89fc-4675-8434-52fd041a3017","year":2021},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.629960Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:8528f88a5b60d2872d2e7e4eb1882ca9affa848655c3145ee485ba59492518a2","observation_id":"0cda5d92-9715-4f68-b539-325b02e7fe5d","resolution":{"observed_at":"2026-08-05T22:45:50.263347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.240872Z","title":"A second-order approach to learning with instance-dependent label noise,","venue":null,"work_id":"fe222b2f-13d7-4b59-b0b6-3d61488c3313","year":2021},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.714256Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:8ab002550c2fd7165e3fad7b6afe558f50cba07a145e43534d09203d0a3bb495","observation_id":"8322d324-812f-4e24-8967-624cec688b77","resolution":{"observed_at":"2026-08-05T22:45:50.245924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.225531Z","title":"Luenberger, Optimization by Vector Space Methods","venue":null,"work_id":"25af8cb4-ab04-4dd0-b974-b7e5592225c3","year":1997},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.770264Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:8f1b3140597fc12e9e1221d2d8a8741616a9cbce83a12a5c49091b125090cd5b","observation_id":"d7b112ea-e86f-4439-819b-f36af949a8b7","resolution":{"observed_at":"2026-08-05T22:45:50.230642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.209929Z","title":"Optnet: Differentiable optimization as a layer in neural networks,","venue":null,"work_id":"abab8034-0812-4c18-8f59-6e81d09e16bf","year":2017},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.852358Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:a321d00168b5f211e680655b4c58ecc1ecd3dfc3e05f7559ff597edc89fea58c","observation_id":"8f63c7fc-147c-4c97-858f-0a4f7e264491","resolution":{"observed_at":"2026-08-05T22:45:50.214812Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.194982Z","title":"Differentiable convex optimization layers,","venue":null,"work_id":"8b41d935-2b43-4580-bb6a-dafd8e3e4e02","year":2019},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.905423Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:f096b4902ab6f415fe86d2fc8ecf8327b71ff24e33441c6283159142af7a4589","observation_id":"d4b19295-3680-4877-b33f-ceb07f6e5c74","resolution":{"observed_at":"2026-08-05T22:45:50.199803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.179415Z","title":"Dual t: Reducing estimation error for transition matrix in label-noise learning,","venue":null,"work_id":"71359a7b-1587-49f7-b73d-d384a3252d23","year":2020},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:48.985573Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:927b20b1b04383f742cd9c58da8dd20c145550fd3b272f71df5f9b916a84d7c0","observation_id":"b699c94c-6555-4c39-83d8-ceb7eb43238a","resolution":{"observed_at":"2026-08-05T22:45:50.184361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.164508Z","title":null,"venue":null,"work_id":"c7283038-6b1a-4a7a-adb1-4c56c7527732","year":null},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:49.068075Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:823761f8851ce54ad6342bd0335f17d43f708f5e1a01cb45b89cb5a478bde348","observation_id":"f071798b-90f4-49cc-b7cb-ec68a51ff0ea","resolution":{"observed_at":"2026-08-05T22:45:50.168823Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.149300Z","title":null,"venue":null,"work_id":"c3d65159-bfe4-4be1-b594-b129fca216ae","year":null},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:49.125303Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:096f5b0f96d97bc9eeb3e9b88e97964aac17af766b8c43a0b928cfb3da14ce59","observation_id":"b8e2caf7-81c5-44b1-b7b3-e4680f6f9b10","resolution":{"observed_at":"2026-08-05T22:45:50.153671Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.134236Z","title":"The training objective loss is defined by Lθ(x, y) := L(hθ(x), y)","venue":null,"work_id":"6054d3f5-081b-4ba1-a7af-52d5d3a503a0","year":null},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:49.208345Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:93f9bb989d9f5c5ef32d0bb599847edb2cb12bc41a9ef6080c7616243da0c812","observation_id":"f439574c-501f-4092-9e53-13ef50f8fe7d","resolution":{"observed_at":"2026-08-05T22:45:50.138747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.120095Z","title":null,"venue":null,"work_id":"347373df-8a9d-43b2-9165-ea2728c25599","year":null},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:49.293462Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:148a3862d99db7e838808ddf2acb7a7fdc6fb441673c2fcd8fcda3fd5584c7f8","observation_id":"0df46c72-09ce-40da-aaf1-68c5527ba185","resolution":{"observed_at":"2026-08-05T22:45:50.124131Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.104201Z","title":"(23) Note that the latter condition automatically follows from the former if r <1/2","venue":null,"work_id":"94fd1554-0925-40f4-8696-485987bc9ee6","year":null},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:49.375852Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:0c8e5132c48a075da8cd81afe7431baeccfaa8bb4ba62d848b7e29f8a6629f4b","observation_id":"5b1320c8-912c-48cf-8e25-db4112a8ad61","resolution":{"observed_at":"2026-08-05T22:45:50.109668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.088477Z","title":"We also suppose that there exists θ∗ ∈ Θ such that hθ∗ = h∗ (again, note that we identify each label with its corresponding one-hot vector)","venue":null,"work_id":"f8cb2053-a4fe-4b95-824e-c2f040211dd7","year":null},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:49.439821Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:765f79961bf0dffbc2b2b485b65cc2c0e3e4dd3cd47b5c9b40b56e982e50f470","observation_id":"b4c276c9-22b7-4504-8e43-b48818488689","resolution":{"observed_at":"2026-08-05T22:45:50.093210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.072428Z","title":null,"venue":null,"work_id":"c8c8f926-057e-401d-a714-ab88237319d3","year":null},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:49.486391Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:40d51184d39ee67d6b147b185c2174104476bdc9f1a8e5a52dd7b893d9409387","observation_id":"089da0ca-4e8e-45be-9a58-5f1f6aea0953","resolution":{"observed_at":"2026-08-05T22:45:50.077013Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.056821Z","title":null,"venue":null,"work_id":"8bc022aa-44b8-4336-abb3-d9c6fc624dbf","year":null},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:49.504379Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:9f12a1ed823b44c38eced3bf908db7ffff8c4e90009777ab84fb23f3eb922d52","observation_id":"feabe5f7-3e9f-44bc-a137-00224506c89f","resolution":{"observed_at":"2026-08-05T22:45:50.061004Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.041356Z","title":"Let δ := rf (0) + (1 − r)f (1/(1 − r))","venue":null,"work_id":"789b2f9d-17da-48e9-9ae0-3773fab402ed","year":null},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:49.509539Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:f1183356d927c3fb3314ce0c3882c366bf266301ffb55290488a9ff41d7ad365","observation_id":"05b7f104-a64a-47f5-bdd3-13aac780cef8","resolution":{"observed_at":"2026-08-05T22:45:50.046603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:50.025359Z","title":null,"venue":null,"work_id":"ce51d448-81d2-442e-a70a-beca67ec53f7","year":null},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:49.514734Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:4e933210586e9455a1138d2d6b1c2403358d0ec3c2fa502b793432616adfb5cc","observation_id":"58c31b20-9a35-45ad-b5f4-2d441f835a71","resolution":{"observed_at":"2026-08-05T22:45:50.030232Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T22:45:49.899011Z","title":null,"venue":null,"work_id":"38ec89e5-3441-42b7-8d60-4e94adabbbff","year":2024},"citing_paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-05T22:45:49.519933Z"},"links":{"citing_paper":"/paper/2508.06622"},"observation_digest":"sha256:cabc178ce41a4ea55fd9363ecfc6d84d5d8623464390ce7d3a91a32e882706d7","observation_id":"b332187e-d5c7-4b6a-93f0-26772c5ce39a","resolution":{"observed_at":"2026-08-05T22:45:49.978069Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.06622","last_updated":"2025-08-08T18:10:16Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T22:45:03.735763Z","submitted_at":"2025-08-08T18:10:16Z","title":"Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels"},"reference_resolution":{"displayed":67,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":2,"verified_fuzzy":54},"total_outbound_references":67},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 0 inbound Pith citation observations for arXiv:2508.06622."}