{"as_of":"2026-08-23T15:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2340a377b6f1f1997d9f9fbe061f1e3ae22f34674cb67a81e09b168fac3d9964","coverage":[{"denominator":55,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":55,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:38:40.630417Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2506.19496/citation-record","integrity":"/paper/2506.19496/integrity","json":"/paper/2506.19496/citation-record.json","paper":"/paper/2506.19496"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:38:42.526510Z","title":"Image classification with deep learning in the presence of noisy labels: A survey","venue":null,"work_id":"fcf24e7b-240b-4e7e-b188-a3aeb16a0887","year":2021},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.379988Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:69ac37d34c71023efc994d085590941f46c134e01a07b0f83eba7006e0928810","observation_id":"0a1789b6-5762-498c-af7c-a3f30b6390d5","resolution":{"observed_at":"2026-08-15T18:38:42.644213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:42.460431Z","title":"Wills aligner: Multi-subject collaborative brain visual decoding","venue":null,"work_id":"b019e406-9487-4c4c-b663-b6c1ae52b5c8","year":2025},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.383896Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:9d6ef3fd737cd98cff87af625944387bc465845b9993536b2cbf6f6e886a241f","observation_id":"231a4eed-9df2-4273-9a59-12d27bcf02fa","resolution":{"observed_at":"2026-08-15T18:38:42.467539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.10836","last_updated":"2022-09-19T08:17:13Z","snapshot_observed_at":"2026-08-21T02:18:51.088304Z","submitted_at":"2022-08-23T09:37:31Z","title":"Evaluating Machine Unlearning via Epistemic Uncertainty","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.10836","snapshot_observed_at":"2026-08-15T18:38:39.486513Z","title":"Evaluating machine unlearning via epistemic uncertainty","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.486513Z"},"links":{"cited_paper":"/paper/2208.10836","citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:e9aea3f363d999b9da12484a4fa1edebcbc8a0976799c08d46548a68eee417f4","observation_id":"68917ffa-c106-4407-b067-0fd647a7b0e1","resolution":{"observed_at":"2026-08-15T18:38:39.486513Z","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":"2026-08-15T18:38:42.452803Z","title":"On mixup regularization","venue":null,"work_id":"9fd6f149-196a-407f-8c38-24b4d529e0c5","year":2022},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.538097Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:896aefa0f46f7e264803666cf4177a4d4f65e90008de81f1370cb8cac5cc805c","observation_id":"f053c072-cb71-4f62-acd4-b5f681e2e90e","resolution":{"observed_at":"2026-08-15T18:38:42.455973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:42.446407Z","title":"Machine unlearning via null space calibration","venue":null,"work_id":"7762e8da-084d-46e5-83cd-cb17d0691a08","year":2024},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.541944Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:bc711a5e754d89eada071af9972683400bc5220a5ce0c67ac3b943ba1da39118","observation_id":"80c75f33-720b-4cad-955b-c3b9ff43cd56","resolution":{"observed_at":"2026-08-15T18:38:42.448789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:42.439465Z","title":"Learning with instance-dependent label noise: A sample sieve approach","venue":null,"work_id":"56218240-c40d-408c-9155-7e703d752477","year":2021},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.545913Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:de9a594df604ae4fc5e77e64ba55c20da0fbdd6d74d060d06d1e19d714567df8","observation_id":"abecd5b9-a3dd-4d4b-bf05-2c4e651ba719","resolution":{"observed_at":"2026-08-15T18:38:42.442225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:42.302964Z","title":"Label smoothing improves machine unlearning, 2024","venue":null,"work_id":"298b8b3f-f0ba-48fc-8dd4-e7cfca6dc63a","year":2024},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.549327Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:edda8334fabde8e2fdeb0be5f11389e8bd487732ed7b5a608d1dd67ca33a26fe","observation_id":"5a6d83bc-ed60-46dc-b12a-63d378207f58","resolution":{"observed_at":"2026-08-15T18:38:42.404388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:42.248092Z","title":"Learning, unlearning, and relearning: Using web 2.0 technologies to support the development of lifelong learning skills","venue":null,"work_id":"331abbcc-8235-44b7-b238-82bce57e7bd3","year":2011},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.552205Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:8f5fd2a0be741f5f5d5e6430011c78523ee6db655756cc6061a9673683edd114","observation_id":"ed6cd7d7-5570-4311-aad5-66ed0dcbf205","resolution":{"observed_at":"2026-08-15T18:38:42.250705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:42.241017Z","title":"Generalized jensen-shannon divergence loss for learning with noisy labels","venue":null,"work_id":"bca4c941-ce01-4c03-8e65-d7562a953abc","year":2021},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.554474Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:9c0c46cc7683be5f62633df2f0b2ce8125302b04a6b23637e7e954dab65d3d4e","observation_id":"02f6abf4-4f8a-4c54-90f3-96d5cee7d2d0","resolution":{"observed_at":"2026-08-15T18:38:42.243615Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:42.234383Z","title":"Salun: Empowering machine unlearning via gradient-based weight saliency in both image classification and generation","venue":null,"work_id":"afd7c03d-7ebb-445f-b6a4-e1157c016531","year":2024},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.557069Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:6090d3928c50573fd59cf3a1d4eb4a3985b33c39700ae0adb1a1850233664ec6","observation_id":"6c781f56-077b-46ff-a2e1-f524d23c9406","resolution":{"observed_at":"2026-08-15T18:38:42.237061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:42.228841Z","title":null,"venue":null,"work_id":"9cf59fbb-3eba-42fe-a5db-55ebbbb75c5c","year":2017},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.559201Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:1df4f8639d50fe6ba27f178e008a2cd28455effb518505dd25a6772cf04c4529","observation_id":"465b5445-954f-4356-ad6d-ef5ad7754c50","resolution":{"observed_at":"2026-08-15T18:38:42.230656Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:42.222311Z","title":"Eternal sunshine of the spotless net: Selective forgetting in deep networks","venue":null,"work_id":"364e1368-0598-4841-86f6-a71dd2a4bb94","year":2020},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.561380Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:5455e8138f57476fdd0f67dfe086d0a284a0222a7b5c050792a2d3aa50989a28","observation_id":"20a55bbd-6d6e-413e-bd62-6ef117e0cdb6","resolution":{"observed_at":"2026-08-15T18:38:42.224852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:42.082410Z","title":"Neuroclips: Towards high-fidelity and smooth fmri-to-video reconstruction","venue":null,"work_id":"184f3476-6016-460f-bb03-c249996626f8","year":2024},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.563449Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:9ab821ab3086208818519993a61d2c0f264d990c1da8f4ba3efeb950225d9477","observation_id":"3ec59e50-c560-479b-b5fb-1e2fa3509cc3","resolution":{"observed_at":"2026-08-15T18:38:42.170204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.989526Z","title":"Amnesiac machine learning","venue":null,"work_id":"d6939670-5be5-4616-8239-08505b110761","year":2021},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.566219Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:19b7a7943dd644a2bcf7c6f33563e35c01fe7929778df1db39ec9a8b9cd4db77","observation_id":"375d1e62-d279-4d74-a647-f921c4affd3b","resolution":{"observed_at":"2026-08-15T18:38:41.992933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.979933Z","title":"Tsang, and Masashi Sugiyama","venue":null,"work_id":"3f4c01d3-501d-4917-9020-f2d4eecaea1e","year":2018},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.569123Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:ad187f0437287e83dae1498f926a112d93b58c2d3f51bfac7466da5e32ab54c0","observation_id":"b6cdbb6f-1247-4808-9db5-bf9854f2cae7","resolution":{"observed_at":"2026-08-15T18:38:41.982996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.971591Z","title":"Approximate data deletion from machine learning models","venue":null,"work_id":"1766f177-9627-4ccd-a7c2-5795e214f30e","year":2008},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.571202Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:371ade446b99920a7898eba9c3407f2a97422ebab4aec0ef4e15e7726a6cb4f9","observation_id":"1500faee-0cb3-45ac-b0bc-58978650a30f","resolution":{"observed_at":"2026-08-15T18:38:41.974410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.960291Z","title":"Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels","venue":null,"work_id":"a1b240af-b075-48ad-926e-ec4da3668e04","year":2018},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.573058Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:cff619be6054ce9ec351596a23cfb58893982fb72ef4b77048410bbe5248f4c8","observation_id":"79f740bd-8464-4ead-b892-887a9dce59b6","resolution":{"observed_at":"2026-08-15T18:38:41.963891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.951373Z","title":"UNICON: combating label noise through uniform selection and contrastive learning","venue":null,"work_id":"d8eaa7d8-9ccf-4db2-bd61-b46b677fbc17","year":2022},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.575126Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:a15f36f1503d685350dd3c04b6c15992d963ed2385cc35a1a5d75cb7e358c16f","observation_id":"61ed062e-e874-4a1f-b00b-46a3411e195f","resolution":{"observed_at":"2026-08-15T18:38:41.953914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.806191Z","title":"Nlnl: Negative learning for noisy labels","venue":null,"work_id":"ef28356b-05f0-4e83-9adf-de30a22e50bf","year":2019},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.704717Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:5d2bf936e971ec7e5701579252796f041fcee04394a3ae38840f368da998256d","observation_id":"53b9bf5f-db7e-42e7-b13f-1d37424d0108","resolution":{"observed_at":"2026-08-15T18:38:41.868643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.769317Z","title":"Overcoming catastrophic forgetting in neural networks","venue":null,"work_id":"bfeb8f77-3ec8-401e-88fd-8a70f9b05b10","year":2017},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.832814Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:cf9b91a122e9c6c790737e936b5b93ed5f988310be6661d3485ff0a99fb5d2b8","observation_id":"fbe41bd1-914e-4f4e-ab12-3778c2f83751","resolution":{"observed_at":"2026-08-15T18:38:41.772104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.760238Z","title":"Learning, unlearning, and relearning: Lessons from one school's approach to creating and sustaining learning communities","venue":null,"work_id":"e40c3eac-ba66-4585-93c3-18cad20478e3","year":2008},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.917349Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:c67f7e4f6e62bfcb33d40c867be33c42a5f0c82cc1dde0a3701fc1b73a643c45","observation_id":"9a74c5bd-0c9d-49d7-89ce-40a04aec9ddb","resolution":{"observed_at":"2026-08-15T18:38:41.763988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.748300Z","title":"Understanding black-box predictions via influence functions","venue":null,"work_id":"a53c445e-e2b5-4c84-bd4a-cb032f255048","year":2017},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.921253Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:a6844f65cefa47f967be70447ef3135e887263c09d924f3dc98dde2073a30e17","observation_id":"d4447381-e407-4b22-a516-e1f9e6b05aa4","resolution":{"observed_at":"2026-08-15T18:38:41.752163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.723056Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"b4658321-f422-4b4e-ac71-8026310528b3","year":2009},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.924526Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:ca46bab2f1bdb566ec1393f31f09152b7b752f1c50a38468ab5b3c16b4091baf","observation_id":"b9b74346-0293-463b-97cd-ec5631535f11","resolution":{"observed_at":"2026-08-15T18:38:41.743964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.575804Z","title":null,"venue":null,"work_id":"404fff33-bf8d-42d4-a0ed-8cdb4f9f689e","year":2020},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.927357Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:89c25aed39528a03caca2ad229ee104d4a4b41af3f74aa7b967033eb457c3de1","observation_id":"bf97591c-9acb-48d5-bdde-0086a1e04f42","resolution":{"observed_at":"2026-08-15T18:38:41.634128Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.548406Z","title":null,"venue":null,"work_id":"a0f15018-05b0-4b65-83d0-94da7b3249dd","year":2021},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.930587Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:d4275ca18d513413a4a35c7e15e7123bfa30fc6a52589e9e72d1f7a58673fdde","observation_id":"01864ce0-d32a-49be-bcaa-a914fffa2695","resolution":{"observed_at":"2026-08-15T18:38:41.551099Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.540268Z","title":"Disc: Learning from noisy labels via dynamic instance-specific selection and correction","venue":null,"work_id":"e270871d-3525-4d91-a1e6-0d78728e89c3","year":2023},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.933744Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:2936065e361c46cc8cf3411cc44e164a026869f19102260044b4bda1930fb6a2","observation_id":"06c4e66d-e951-4e39-b091-2ac30d2e7819","resolution":{"observed_at":"2026-08-15T18:38:41.544020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.532585Z","title":"Early-learning regularization prevents memorization of noisy labels","venue":null,"work_id":"4990f629-a8a9-450b-9032-d7fcbc173467","year":2020},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:39.937076Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:a9f13e51a28de6237824a424666a89c24c6ee903977cb4c04c8286d9fdbc2af2","observation_id":"8336ce9d-9616-4c63-8937-c6c1b11b4b09","resolution":{"observed_at":"2026-08-15T18:38:41.536129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.524251Z","title":"Model sparsity can simplify machine unlearning","venue":null,"work_id":"0e458f74-94dc-4cf7-8c09-8cc7a5bf11db","year":2024},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.019320Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:abb314e53cbb1f2f589e7feeee1ea6042b9abd8e6e6816295e814f8d9c748421","observation_id":"5ed6283b-761f-4cc0-a6a6-f2a473565595","resolution":{"observed_at":"2026-08-15T18:38:41.527294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.336637Z","title":"Does label smoothing mitigate label noise? In ICML , pages 6448--6458","venue":null,"work_id":"9cb4b957-5f69-4b09-ab61-3167688d938d","year":2020},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.178311Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:a3a25446d1b55d9a7fb5da4b6ace93c144b8633d2e22a6276ea5944751de6532","observation_id":"2756a96f-0b34-4e15-afef-90ab46a27882","resolution":{"observed_at":"2026-08-15T18:38:41.444675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.329644Z","title":"when to update","venue":null,"work_id":"9dfe61c6-6370-4145-a72b-302fcc61e22c","year":2017},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.181377Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:21bd5e76bf42de31ce9265f228c9085fc63b9a4fd6902c50a4fdf4e605055e91","observation_id":"8b9e1e06-0840-4509-88c5-419b86bd6eec","resolution":{"observed_at":"2026-08-15T18:38:41.332508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.19183","last_updated":"2025-08-24T04:40:23Z","snapshot_observed_at":"2026-08-20T05:40:43.599015Z","submitted_at":"2024-07-27T05:50:54Z","title":"Graph Memory Learning: Imitating Lifelong Remembering and Forgetting of Brain Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.19183","snapshot_observed_at":"2026-08-15T18:38:40.184593Z","title":"Graph memory learning: Imitating lifelong remembering and forgetting of brain networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.184593Z"},"links":{"cited_paper":"/paper/2407.19183","citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:2eb32f4691c378fa548474de9ab9aaba58f0a63c778a6218c675867c5e37ea11","observation_id":"75a46866-f332-4d34-addd-c64806872be4","resolution":{"observed_at":"2026-08-15T18:38:40.184593Z","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":"2026-08-15T18:38:41.322366Z","title":"Automated flower classification over a large number of classes","venue":null,"work_id":"ea44216a-9c14-4d38-b1b7-43e747fdab4d","year":2008},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.188921Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:c153da86a482a1fa1a67dbf2a4ff43377426ef1108c9d59f463486b49dec9116","observation_id":"203ce021-3d8c-4248-8eb8-621ffabcf6b7","resolution":{"observed_at":"2026-08-15T18:38:41.325213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.312275Z","title":"O'Connor, and Kevin McGuinness","venue":null,"work_id":"385954ab-e77d-4153-a4bc-fd9a20d583a7","year":2021},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.193421Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:9ad8163524fd925147d550533a78c6443c4d3b3200c11f7a09b83e713a71e7e4","observation_id":"e4f5fdc1-70bd-4ddd-8509-ad51818520d6","resolution":{"observed_at":"2026-08-15T18:38:41.315495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.303078Z","title":"Parkhi, Andrea Vedaldi, Andrew Zisserman, and C","venue":null,"work_id":"b679b1c3-4299-4b47-a51e-536453355095","year":2012},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.195767Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:78aacc91339c2c5266b7048d8cad862501cef381c18b35e7e1783634231735d0","observation_id":"82c1e774-217d-41cc-8ab8-bfecf25791f7","resolution":{"observed_at":"2026-08-15T18:38:41.306289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.287663Z","title":"Learn, unlearn and relearn: An online learning paradigm for deep neural networks","venue":null,"work_id":"0545b885-9d5d-430d-af32-a7f0d7c721ed","year":2023},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.199659Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:5b1229eef030e5b145b56fc20a0b154ac974ceac71b6861cae8cc7c828c0a92e","observation_id":"9ac9c35b-92ce-4f79-8905-48f97f7796fa","resolution":{"observed_at":"2026-08-15T18:38:41.296426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.169370Z","title":"Forgetting as a form of adaptive engram cell plasticity","venue":null,"work_id":"4e5ad32d-d000-48fb-a624-e3b6a42358be","year":2022},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.230818Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:a99dc9eb59f6652ba13e8c8cebe8c5b1800fc96f38e80cdd6cf494a100c000c6","observation_id":"5dfdcbea-3c7f-4777-9da7-bb9ccd634b04","resolution":{"observed_at":"2026-08-15T18:38:41.200526Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.070585Z","title":"Noisy concurrent training for efficient learning under label noise","venue":null,"work_id":"2b2b58a0-888c-454f-aab5-1f0ec7a585e1","year":2021},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.301319Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:86d870416e88ebfab97ef623d028ddfc03deb686600464bf409d07a066772488","observation_id":"7e3594ab-4472-4316-beb3-887817ee952f","resolution":{"observed_at":"2026-08-15T18:38:41.101127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.20620","last_updated":"2024-05-31T05:10:30Z","snapshot_observed_at":"2026-08-21T02:25:27.147043Z","submitted_at":"2024-05-31T05:10:30Z","title":"\"Forgetting\" in Machine Learning and Beyond: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.20620","snapshot_observed_at":"2026-08-15T18:38:40.376418Z","title":"forgetting","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.376418Z"},"links":{"cited_paper":"/paper/2405.20620","citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:82380b7683e6a9873a0cfee56c2142ce58db00935602097b8b1d8997e5634781","observation_id":"688ee668-e074-479e-9af3-3a99f86ff91d","resolution":{"observed_at":"2026-08-15T18:38:40.376418Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:38:40.381316Z","title":"Rethinking the inception architecture for computer vision","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.381316Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:5b9e518fa507467e882a4babdb9b5d7d245385472b7a795edae02c412fd9bc81","observation_id":"9db986dd-865b-4b8d-a32f-6a66869d3e62","resolution":{"observed_at":"2026-08-15T18:38:40.381316Z","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":"2026-08-15T18:38:41.060448Z","title":"Efficientnet: Rethinking model scaling for convolutional neural networks","venue":null,"work_id":"d029ef55-ceab-48f0-aaba-e776046f82d5","year":2019},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.384523Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:69f6ee12e75817e7858f5f4064149ff8f5c41793308171a503a815bd23b98eca","observation_id":"502afbe1-33e2-4838-bb74-ec875d4eefd0","resolution":{"observed_at":"2026-08-15T18:38:41.062384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.053050Z","title":"Symmetric cross entropy for robust learning with noisy labels","venue":null,"work_id":"b9a85ff9-d299-4aa2-bee7-ca86c8b87628","year":2019},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.389429Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:0c4380670fc04c27157fff5413ac9007cc63192aa743e7782945ee6c9f8cc25a","observation_id":"439acb88-06e6-4ecf-a6d5-52996df1b1b8","resolution":{"observed_at":"2026-08-15T18:38:41.055672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.11577","last_updated":"2023-08-07T12:33:20Z","snapshot_observed_at":"2026-08-18T17:58:08.799481Z","submitted_at":"2021-08-26T04:42:24Z","title":"Machine Unlearning of Features and Labels","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.11577","snapshot_observed_at":"2026-08-15T18:38:40.393128Z","title":"Machine unlearning of features and labels","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.393128Z"},"links":{"cited_paper":"/paper/2108.11577","citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:eed6f6733e8044d7877485ccbd7814bf67a3e0002c470ce09213c34db3342e03","observation_id":"3b0fbd1d-6c58-45ab-bb44-90c25eed3d5a","resolution":{"observed_at":"2026-08-15T18:38:40.393128Z","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":"2026-08-15T18:38:41.046124Z","title":"Combating noisy labels by agreement: A joint training method with co-regularization","venue":null,"work_id":"3bbba415-06fd-4cc0-bb69-c6a3baabf322","year":2020},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.396098Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:27ebcc57bd454027335f1129539a1367bdf07c9eee19d2b9d19fec4d8076a06e","observation_id":"5be8a921-025f-4117-9c29-572b3f97041f","resolution":{"observed_at":"2026-08-15T18:38:41.049265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.038319Z","title":"To smooth or not? when label smoothing meets noisy labels","venue":null,"work_id":"a05621dd-7d0d-4c21-af23-aa68717a9da8","year":2022},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.399665Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:272216f6aa39d71e1c4be998f8afd9250318e48dfb90a490bb8cc043dba0b704","observation_id":"d730baf1-5ce9-404a-b0cc-00df44a52134","resolution":{"observed_at":"2026-08-15T18:38:41.041411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.031867Z","title":"L \\_ dmi: A novel information-theoretic loss function for training deep nets robust to label noise","venue":null,"work_id":"95e89d84-3043-4cd0-b60e-cecf759967bc","year":2019},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.402340Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:f8893654a2410f0967ad787da8c79059583a3a35e4f75fb3c3dd3e30a0b22013","observation_id":"a0bef616-a2dc-4f91-831d-939921eb2d2b","resolution":{"observed_at":"2026-08-15T18:38:41.034363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.025169Z","title":null,"venue":null,"work_id":"29907e4c-a699-43e8-a80f-f9bdfc3a1bd8","year":2023},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.434221Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:113ca166fa909e53cd3bce7f151c0207f451db5542639b12a7e626c08daa3265","observation_id":"50fb3933-e63d-468d-9eca-f938fb697d9c","resolution":{"observed_at":"2026-08-15T18:38:41.027653Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.019391Z","title":"Probabilistic end-to-end noise correction for learning with noisy labels","venue":null,"work_id":"6d565c6c-8a7d-4806-ab9b-f1c492f32d40","year":2019},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.508067Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:276b220303cee858dad3841cbb41c2d2f9df00e5ba28761b3f0aeb6d00e52e99","observation_id":"fcfdac15-d76d-4ec9-92ec-c88beae234e9","resolution":{"observed_at":"2026-08-15T18:38:41.021603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:41.008744Z","title":"Tsang, and Masashi Sugiyama","venue":null,"work_id":"d0320bc3-4729-4ab6-9d11-dfe9833e9728","year":2019},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.574554Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:6995726e1b8d3aedb14f28ac44a2c35c98289a904f7bcc959ec099adb9eab6c6","observation_id":"8ff5dce6-42e9-4fa5-94c8-4291351504d1","resolution":{"observed_at":"2026-08-15T18:38:41.013135Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:40.903612Z","title":"Wide residual networks","venue":null,"work_id":"d116f93f-e409-4804-abc5-39f3d6c45138","year":2016},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.614192Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:7c539739c0571d690361f2a25d8a9992dea902e8eb790af456d8e11c6c265484","observation_id":"e25e5791-e8db-4e33-9da4-be174b40638a","resolution":{"observed_at":"2026-08-15T18:38:40.943772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:40.763124Z","title":null,"venue":null,"work_id":"96e7dce3-dd3d-4e33-997e-73c5559ed472","year":2018},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.617173Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:e74ef9a7c9546bf0e478bbde3b456530890ac06e914863019c7526ad2c2383ee","observation_id":"8c43f612-e01b-4063-b79e-03b061242e35","resolution":{"observed_at":"2026-08-15T18:38:40.814316Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:40.709032Z","title":"Dauphin, and David Lopez-Paz","venue":null,"work_id":"dd78b3b9-f9a3-41d7-b2ea-2072a2b3f024","year":2018},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.619912Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:39eccc599c7f26944c03be63250e9a3a23e10494764fc8653d127a5f1ee1dc9e","observation_id":"895880c2-4837-42b2-8e81-7d629e6dda20","resolution":{"observed_at":"2026-08-15T18:38:40.722032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:40.700053Z","title":"Tripartite collaborative filtering with observability and selection for debiasing rating estimation on missing-not-at-random data","venue":null,"work_id":"a7d48f1e-717e-40b8-ad36-12e07186baf6","year":2021},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.622094Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:558c2f8626c1a73d5d9f9ca5c9b2af957f7463416b773840904cfc1da975c812","observation_id":"a13f6626-cfa4-41d0-a88d-11abf92d74c2","resolution":{"observed_at":"2026-08-15T18:38:40.702610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:40.692338Z","title":"Learning with feature-dependent label noise: A progressive approach","venue":null,"work_id":"fcf9d861-8418-4ea1-a135-cd3d2d780bc9","year":2021},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.624580Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:e081a5368ebe353016a94b2186f03a99587141c0fde9f807e6ca228edbe63074","observation_id":"0786f50c-5aed-415a-9874-7e823896fcd0","resolution":{"observed_at":"2026-08-15T18:38:40.694833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:40.681472Z","title":"Learning with noisy labels via sparse regularization","venue":null,"work_id":"9accacca-e364-45fe-8a9e-fd8e60922af1","year":2021},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.627301Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:411a98c1a3e4be67d156eda8835f6fba053abd370e077bf02ec2e2dccfa87e19","observation_id":"edeb1628-5366-42e6-ba89-2f115d21b11c","resolution":{"observed_at":"2026-08-15T18:38:40.686513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T18:38:40.630417Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-15T18:38:40.630417Z"},"links":{"citing_paper":"/paper/2506.19496"},"observation_digest":"sha256:2f8ea97c973657d88918ef591e9fe885946f9db27b3ed0dac42398928bc2c4c8","observation_id":"4c997425-8ff5-46b4-b14f-d0f02a8bd24f","resolution":{"observed_at":"2026-08-15T18:38:40.630417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.19496","last_updated":"2025-06-24T10:33:48Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T18:04:09.671141Z","submitted_at":"2025-06-24T10:33:48Z","title":"COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement"},"reference_resolution":{"displayed":55,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":44},"total_outbound_references":55},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2506.19496."}