{"as_of":"2026-08-18T07:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3b0be1a3af410a8bfd47ec3906d5a940d33f14e13076efd9779e067486a2a187","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:18:57.978573Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2505.13342/citation-record","integrity":"/paper/2505.13342/integrity","json":"/paper/2505.13342/citation-record.json","paper":"/paper/2505.13342"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:18:58.553272Z","title":"Image clas- sification with deep learning in the presence of noisy labels: A survey","venue":null,"work_id":"19400a5c-47e8-4c21-b702-cc176c0efb5f","year":2021},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.082239Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:71fe244f8a6aeef76cdbcdba1317dc36a1759d9d8d31b4b2f853ac3f38a06995","observation_id":"384c6d87-b39d-4fd2-a86d-dded2bbefaca","resolution":{"observed_at":"2026-08-15T20:18:58.556700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.545137Z","title":"Learning from noisy examples","venue":null,"work_id":"8e10cb88-956f-4c4a-8916-01f0288d513d","year":1988},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.121078Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:25453b49787de49ca248df1b8463e54a1b13279a5d9f93e19ddb150a882ad37c","observation_id":"4905a96c-3e41-44cf-80d4-f87ad02bc896","resolution":{"observed_at":"2026-08-15T20:18:58.547900Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.535570Z","title":"A Simple Framework for Contrastive Learning of Visual Representations","venue":null,"work_id":"393d3cb6-f7a3-44a6-9495-092fdd7f4084","year":null},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.124175Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:740dbe55f516d9873d42c2d923ed4b4c0459a0b673a619253b285b5fdf92f340","observation_id":"2011abd4-5540-4aed-9f2c-7c9a3a2e77d3","resolution":{"observed_at":"2026-08-15T20:18:58.539021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.13719","last_updated":"2019-11-14T04:51:03Z","snapshot_observed_at":"2026-08-16T23:08:17.551042Z","submitted_at":"2019-09-30T14:05:14Z","title":"RandAugment: Practical automated data augmentation with a reduced search space","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.13719","snapshot_observed_at":"2026-08-15T20:18:57.132658Z","title":"Cubuk et al","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.132658Z"},"links":{"cited_paper":"/paper/1909.13719","citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:bba3b26cb4c3733e63a57805ac53b101b66e7d26a837db70e4d5d5c48c73f069","observation_id":"5ae7a602-63bb-464c-8d1d-fffb83f467f0","resolution":{"observed_at":"2026-08-15T20:18:57.132658Z","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":"2026-08-15T20:18:58.525076Z","title":"Maximum likelihood from incomplete data via the EM algorithm","venue":null,"work_id":"02f2e77a-a2f9-4e8b-b0b2-66c6eace88fe","year":1977},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.136383Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:f538862eb665bacec94193d8d13e781fea96967ad3e573522676805be6e4b414","observation_id":"53f276a3-ff1f-4d0b-a77f-6e1eb65c4384","resolution":{"observed_at":"2026-08-15T20:18:58.528707Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.512944Z","title":"COPER: Correlation-based Permutations for Multi-View Clustering","venue":null,"work_id":"61fc7799-1140-4dd3-99ff-367da3c0c4ca","year":null},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.140249Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:44ffba3203128813925f032824f408f590ed08c1e58f38d30c130b27c7b9ac24","observation_id":"f89f7ca7-c4a9-451f-a58f-1cfa7e322657","resolution":{"observed_at":"2026-08-15T20:18:58.517699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.503378Z","title":"Joint probabilistic modeling of single-cell multi-omic data with totalVI","venue":null,"work_id":"71b5f0dc-d588-4add-8173-942147b6b9d7","year":2021},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.143132Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:ffd085bc99d88e33e20a096a474f8f5aee25cefd0afe8c7314d60f67e00932f5","observation_id":"6f8f1b65-7446-4db5-b709-7d83164f1d45","resolution":{"observed_at":"2026-08-15T20:18:58.506382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.494351Z","title":"Co-teaching: Ro- bust training of deep neural networks with ex- tremely noisy labels","venue":null,"work_id":"3711cda2-0d38-4829-8a8e-bd1153d2e2ec","year":2018},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.146709Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:e62a2ed7c840efaa0b84046884c5035ac5777a6bc650600f567d348cc94c34fa","observation_id":"b3e1e996-b16b-476d-a6d8-6f977d4e68e5","resolution":{"observed_at":"2026-08-15T20:18:58.497730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.484533Z","title":"Deep self-learning from noisy labels","venue":null,"work_id":"94a6faae-3b92-49a3-8f11-976da9bca23b","year":2019},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.149684Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:71d75f8a86cb691591b950ed390529498076ef62d1561061e2a754861880ac6c","observation_id":"15672cf3-08f8-4beb-bd7b-5767d4b2b933","resolution":{"observed_at":"2026-08-15T20:18:58.487883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:57.205065Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.205065Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:e249f3e5d16dd469ee43284e38e0fbe1b02bf929d729a861222f518757b6ee37","observation_id":"1c64c2d2-4d9b-4f32-94c5-61cdbd9902fc","resolution":{"observed_at":"2026-08-15T20:18:57.205065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.06377","last_updated":"2021-12-19T19:23:25Z","snapshot_observed_at":"2026-08-17T17:58:26.288570Z","submitted_at":"2021-11-11T18:46:40Z","title":"Masked Autoencoders Are Scalable Vision Learners","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.06377","snapshot_observed_at":"2026-08-15T20:18:57.293121Z","title":"Masked Autoencoders Are Scalable Vision Learners","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.293121Z"},"links":{"cited_paper":"/paper/2111.06377","citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:fcfd08806f22c72d3a6ff99d33c70b8a902fd53448c188689337a23823637e6e","observation_id":"1bbf10cc-1faa-4b7c-98cb-f8e4e4990aa5","resolution":{"observed_at":"2026-08-15T20:18:57.293121Z","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":"2026-08-15T20:18:58.470021Z","title":"A systematic evaluation of single-cell RNA-sequencing imputation methods","venue":null,"work_id":"37941424-de51-41b5-8981-3942c840ba9b","year":2020},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.297046Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:6f3b7aeb8cc30818aa2e6aea091f9747f46d1129ce24097fb2a9f424f9bc9163","observation_id":"cc797e38-abd3-4c8c-b745-27304df01520","resolution":{"observed_at":"2026-08-15T20:18:58.473432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.461464Z","title":"O2U-Net: A Simple Noisy Label Detection Approach for Deep Neural Networks","venue":null,"work_id":"52782b75-c247-4acd-82d0-c009b73b45d7","year":2019},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.300606Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:665212c0d1c3fbe91fabc2ee064cbd007090a16218868963cb3d4769188a3516","observation_id":"d6cbb4e2-9bfc-48c3-9c57-aa393b6a6b70","resolution":{"observed_at":"2026-08-15T20:18:58.464146Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.452763Z","title":"MentorNet: Learning data-driven curriculum for very deep neural networks on cor- rupted labels","venue":null,"work_id":"4bb6cdcd-88b6-4c11-9e5d-ec42da0b4e45","year":2018},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.304374Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:296e15851ef3dfc3f2124061e3c2684ead7fb45c4433c9f354a8b8abc85bff88","observation_id":"b08d0c40-2c91-4001-a82b-6501b1d1fa99","resolution":{"observed_at":"2026-08-15T20:18:58.456292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.442967Z","title":"Learning Multiple Layers of Features from Tiny Images","venue":null,"work_id":"ca5802e7-6c62-4987-89eb-40d8d52cc0dd","year":2009},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.308823Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:f81f14687ef6a9097e0990c6c517e72af3956f466bf71561b69e7adecb38ff4f","observation_id":"8e6893f4-9521-49ea-84f8-0af117a0cefe","resolution":{"observed_at":"2026-08-15T20:18:58.446673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.432127Z","title":"Gradient- based learning applied to document recogni- tion","venue":null,"work_id":"c8fc212b-ca53-408a-8e89-4feedce208f3","year":1998},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.316655Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:23a9b2c311e5e693ef6773d4b8f4c4d267ccec6dd5ba16396c5b4bf24de2d933","observation_id":"31d2dc76-7812-4260-a4b1-31bdfe05091f","resolution":{"observed_at":"2026-08-15T20:18:58.435693Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.421602Z","title":"Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks","venue":null,"work_id":"7eda4e23-5aa0-4c06-8adf-31805c85db47","year":2013},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.465774Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:9fc8c27fa4e43455f382ea65db7f54da35e18ace48739e5e0597337aeca8e7ac","observation_id":"b985f4df-619c-4aa8-9658-c93ec16a319f","resolution":{"observed_at":"2026-08-15T20:18:58.425503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.412538Z","title":null,"venue":null,"work_id":"17738841-2c87-4854-95fe-587dfec90dfe","year":2020},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.551579Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:817f022c74555094345c7e6493af27890a5ae676fba559ba4f52daa4efed04e8","observation_id":"37d6e5dd-29bf-49fc-ad81-47386731a04e","resolution":{"observed_at":"2026-08-15T20:18:58.415816Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.402483Z","title":"When Speaker Recognition Meets Noisy Labels: Optimizations for Front-Ends and Back- Ends","venue":null,"work_id":"127ac651-ec42-4be0-8211-6a074bba0d20","year":2022},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.555237Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:a2002efedfbe989685d41e42b68b6057e770b974e2e00122db1f13b67629e03f","observation_id":"c0181bd0-aa58-479d-b45c-99715968be2a","resolution":{"observed_at":"2026-08-15T20:18:58.406806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.392055Z","title":"In: Advances in Neural Information Processing Systems (NeurIPS)","venue":null,"work_id":"be60b608-863b-4b98-9057-da1407d0810e","year":2022},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.558647Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:e9cdcca1e6ab044be1a3534a31bfd35700c3e9969c33e190de2ca4f21d50a4a0","observation_id":"b23c3c27-0b1f-43c2-82f6-dceefe585b74","resolution":{"observed_at":"2026-08-15T20:18:58.395944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.380382Z","title":"Provably End-to-end Label- Noise Learning without Anchor Points","venue":null,"work_id":"44d4c1fe-658c-4c85-bb80-c3a17c16073f","year":2021},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.563394Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:16a2ca1aec01fa49e17a54ffe4c9552a5b5f0ee81a7e6073f24481630d5fd934","observation_id":"a48d7f77-da97-40c2-bfd1-8edaaaaab6ee","resolution":{"observed_at":"2026-08-15T20:18:58.384986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.370526Z","title":"Transductive and inductive outlier de- tection with robust autoencoders","venue":null,"work_id":"ea12b4a4-6c50-4dbd-8fda-1ffeb5233327","year":2024},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.566457Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:c352e7328f2dc63d0cd0516457f6c2d7d4681c08a4c7708d9835df05d87544a5","observation_id":"ead57efc-0186-4942-9fac-71eee5dad34b","resolution":{"observed_at":"2026-08-15T20:18:58.374327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.359901Z","title":"Learning coupled embedding using multiview diffusion maps","venue":null,"work_id":"bcbc1eff-2c77-4a55-b8ca-96a9464c591d","year":2015},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.569997Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:1abe05376a73b880c39cd47d414a3e58085d43e82935c8648779936f50dac6f7","observation_id":"7359d0bc-e30a-4238-8733-4bc5daeb27c2","resolution":{"observed_at":"2026-08-15T20:18:58.363127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.350875Z","title":"Multi-channel fusion for seismic event detection and classification","venue":null,"work_id":"a25b9860-9495-48d4-ae14-ad666f7441e4","year":2016},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.573382Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:3b0cc20729e6dc745cae7fe78c73495cd7fb89b0293e06a2c30b2c875076921b","observation_id":"5555a5e5-7889-45b1-8b9e-525331325d37","resolution":{"observed_at":"2026-08-15T20:18:58.354157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.341566Z","title":"Iden- tifiability of Label Noise Transition Matrix","venue":null,"work_id":"4aa1edcb-5500-42b5-881a-dd1be51ef1b9","year":2023},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.638469Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:802ee9343a29439169fa3dddfab997b213e49d5bca92af1588c91e076bd7ab97","observation_id":"1c9771bf-e355-420e-b54d-d4fca41e5adc","resolution":{"observed_at":"2026-08-15T20:18:58.344963Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.331159Z","title":"Decou- pling","venue":null,"work_id":"8e97eaec-0c05-474a-b845-c34b28a3809a","year":2017},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.677421Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:6ef725aa4f17018c92e328dd598bf9e812ae664c8eb8687b85f29d620e6d5bae","observation_id":"537d8d5e-931f-4b8f-9d22-fd7ee5cdd557","resolution":{"observed_at":"2026-08-15T20:18:58.335096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.321605Z","title":"Integrated analysis of multimodal single-cell data","venue":null,"work_id":"9292b14f-84ae-4f22-ba78-7e5956e4bb4c","year":2020},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.681226Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:69dd245e6e20b3b7905f5b96326fa537025d9ec55e1c2a9272eb5c373f95a50d","observation_id":"dcf96049-2f36-44e8-895f-da66c304cbb6","resolution":{"observed_at":"2026-08-15T20:18:58.325118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.311612Z","title":"Finite mixture modeling with mixture outcomes using the EM algorithm","venue":null,"work_id":"8b9c89ec-8a6d-402f-bd89-e814ec13423d","year":1999},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.684654Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:9b6c8e8facba382d7634d846a3f87eb5a1c293208fbb5363b8a35aeeb9006dc5","observation_id":"dbc0cd6a-0e8f-409a-bcc3-3e748a1771fe","resolution":{"observed_at":"2026-08-15T20:18:58.314480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.302726Z","title":"Opti- mized threshold inference for partitioning of clones from high-throughput B cell repertoire sequencing data","venue":null,"work_id":"a108beae-6d87-4688-844c-1f1e7ffddc3d","year":2018},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.688509Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:a175db1b46f5a89a2679a25521cdc1151365f5406808524b9f9bffe263429e7d","observation_id":"5df9a43c-6c55-4343-895d-d983e1006baa","resolution":{"observed_at":"2026-08-15T20:18:58.306104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.292953Z","title":"Making deep neural net- works robust to label noise: A loss correction approach","venue":null,"work_id":"69ba0553-3b90-4e22-9bcf-210620be3d59","year":2017},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.692324Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:e972894e748e1551d6a8140e4b2f3b053b1efc9780ac4b747c9c4202d13e3435","observation_id":"7e78d25c-6208-4728-abdc-0464e95efe6c","resolution":{"observed_at":"2026-08-15T20:18:58.296306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.03538","last_updated":"2017-10-10T12:36:45Z","snapshot_observed_at":"2026-08-14T20:25:14.159477Z","submitted_at":"2017-10-10T12:36:45Z","title":"Contaminated speech training methods for robust DNN-HMM distant speech recognition","version":1},"cited_work":{"arxiv_id":"1710.03538","doi":null,"metadata_source":"pith","pith_arxiv_id":"1710.03538","snapshot_observed_at":"2026-08-15T20:18:58.024950Z","title":"Contaminated speech training methods for robust DNN-HMM distant speech recognition","venue":"eess.AS","work_id":"e3613824-ec66-4cde-93f8-b5b6ed7d6a80","year":2017},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.695438Z"},"links":{"cited_paper":"/paper/1710.03538","citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:e3876b22f8d56f8e2a27151f5859c45e051a63459cc3f6e9e8e3882a6f49d85b","observation_id":"c1cae3d6-71b8-4cf3-ac33-1c294d1a8b7c","resolution":{"observed_at":"2026-08-15T20:18:58.112696Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.282792Z","title":"Gaussian mix- ture models","venue":null,"work_id":"b998dcb5-1d83-416e-8d59-aa6c2160431c","year":2009},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.788623Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:1a4ce227301def526ebf2456443403e681f24391cd28b1ca053fc71294f61bbb","observation_id":"4ef113af-514d-4109-926a-26a15d39cc0e","resolution":{"observed_at":"2026-08-15T20:18:58.287139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.272586Z","title":"Anomaly Detection with Variance Stabilized Density Estimation","venue":null,"work_id":"0ee93511-945f-4f71-96ac-799c8e294373","year":2024},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.828972Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:81375696d9a940d784968b764e2dcd2fa7edd1e0abf28becbf9f85570d8953b3","observation_id":"4e063443-6211-4803-a78c-3cf09fb77334","resolution":{"observed_at":"2026-08-15T20:18:58.276375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.262217Z","title":"Domain-Generalizable Multiple-Domain Clustering","venue":null,"work_id":"02617471-7c03-4002-914d-df7dbf853b23","year":null},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.832603Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:7d6705a00e5ea15f851155b78f3b1d91fa4e397cff70a589b158180669517718","observation_id":"373f6581-6822-4448-91d0-744d6cfa36e9","resolution":{"observed_at":"2026-08-15T20:18:58.266616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.253474Z","title":"Cyclical learning rates for training neural networks","venue":null,"work_id":"c7288438-f5bc-4d6a-b5fe-5426cd0ff72c","year":2017},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.836344Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:591e8db601af9c721db293f846cfcaa66c35d090318478daaa0676d5dd4135c1","observation_id":"e3805746-ae20-4942-87eb-2a4dbff577bb","resolution":{"observed_at":"2026-08-15T20:18:58.256333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.243265Z","title":"Learning from noisy labels with deep neural networks: A survey","venue":null,"work_id":"ac07eeeb-219d-4171-98ef-4ce933ddc19d","year":2022},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.840440Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:dbeae492a28110ed4a2b3eba055c62d1c2b5dabaaf78013db96bcb504b7b5386","observation_id":"91d647f9-7f45-4aab-b54f-cda949e45aec","resolution":{"observed_at":"2026-08-15T20:18:58.247007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.232501Z","title":"Symmetric cross entropy for robust learning with noisy labels","venue":null,"work_id":"ccb11207-5147-4a1a-9069-b9ca11c3e45a","year":2019},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.900668Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:b4df4f0e96ae440927a680bddf5d4e48b33aec690b23e774a81d4d993bf1165d","observation_id":"9d4af767-63b2-4961-ba86-6965dac5b7b9","resolution":{"observed_at":"2026-08-15T20:18:58.236528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.12088","last_updated":"2022-03-27T06:51:57Z","snapshot_observed_at":"2026-08-16T20:37:56.916414Z","submitted_at":"2021-10-22T22:42:11Z","title":"Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.12088","snapshot_observed_at":"2026-08-15T20:18:57.922171Z","title":"Learning with noisy labels revisited: A study using real-world human an- notations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.922171Z"},"links":{"cited_paper":"/paper/2110.12088","citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:0dbff7a9d9a26ef8015ad6d2182ba50644a6c85f318437e732dd94c0d2ceffd3","observation_id":"aae85c75-3f0c-4875-a881-2f91a5a06488","resolution":{"observed_at":"2026-08-15T20:18:57.922171Z","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":"2026-08-15T20:18:58.221792Z","title":"Learning to teach with dynamic loss functions","venue":null,"work_id":"41a936a5-8bd9-4f43-8474-1bf445762c0c","year":2018},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.927119Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:7d535e05ce21aa12589663c03aab6db2b0a3fd50db0ca1adfdcd4fbb040d3256","observation_id":"8c376445-5ce8-4c91-9394-332ca9b835cd","resolution":{"observed_at":"2026-08-15T20:18:58.225909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.211344Z","title":"NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing","venue":null,"work_id":"08adad3c-5daa-41e2-bd65-5403b0aa688c","year":2023},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.931248Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:8552fa6c9005e67cad687f0fc183da5da286214e0567a364143e16ebba8c649a","observation_id":"b4a66d24-1203-4ea5-a496-388a6023beac","resolution":{"observed_at":"2026-08-15T20:18:58.214767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.201422Z","title":"Are Anchor Points Really Indispensable in Label-Noise Learning? 2019","venue":null,"work_id":"c6c891c2-1892-4c41-8e43-2a19900d7004","year":2019},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.935113Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:264d4ca2b47b6e31749f9f2599a3f87d8871b28b501748da6aeb2e80492bcf94","observation_id":"39a0bf96-b70d-4021-b275-779d185947e5","resolution":{"observed_at":"2026-08-15T20:18:58.204743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.190467Z","title":"L_dmi: A novel information- theoretic loss function for training deep nets ro- bust to label noise","venue":null,"work_id":"33c0bdcf-7c98-4156-99d9-935fdb162c64","year":2019},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.960130Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:9eee9dfd7c84dd0c537ffe07cb43d452762406b26cd3a823df0fca84135c3ccb","observation_id":"a0365dfb-19f2-4fd1-982a-a01e98313ecb","resolution":{"observed_at":"2026-08-15T20:18:58.194317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.178962Z","title":"Dual t: Reducing estimation error for transition matrix in label-noise learning","venue":null,"work_id":"d6428a76-6509-4762-8e81-c116786d8158","year":2020},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.967367Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:1031e8d96a5ff88f09374693d0ed741193a09d41093f7e3a579bfc36cba0784b","observation_id":"8023a7cb-6d5c-4328-8722-bbf877d15e90","resolution":{"observed_at":"2026-08-15T20:18:58.183378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.169291Z","title":"Probabilistic end-to- end noise correction for learning with noisy la- bels","venue":null,"work_id":"8f2f1bc7-bda6-4828-93ef-dec966486a22","year":2019},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.970547Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:e5baaad3c1e28e067628ed7827d29e3a4f48ed9f371fb269971b59c46ac6b70c","observation_id":"a9c02466-af0a-4851-82bd-7cbebd9bb5dd","resolution":{"observed_at":"2026-08-15T20:18:58.172470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:18:58.148208Z","title":"Challenges and emerg- ing directions in single-cell analysis","venue":null,"work_id":"4479b132-3c69-449f-ab3b-a33ba7cb2099","year":2017},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.974314Z"},"links":{"citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:17c370c7fb0799d4fba003308a79ffcf3fbbfce7b7534cf2b6c554b6e3818637","observation_id":"e80f0cef-6499-430c-be9e-a3d1311daafb","resolution":{"observed_at":"2026-08-15T20:18:58.162755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.09412","last_updated":"2018-04-27T21:39:25Z","snapshot_observed_at":"2026-08-08T10:28:19.597631Z","submitted_at":"2017-10-25T18:30:49Z","title":"mixup: Beyond Empirical Risk Minimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.09412","snapshot_observed_at":"2026-08-15T20:18:57.978573Z","title":"mixup: Beyond Empirical Risk Minimization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.978573Z"},"links":{"cited_paper":"/paper/1710.09412","citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:5ed53237f5b16f2ede46271c4f419ccd1bcee11e79e2cf2ef9687c9b4d200c91","observation_id":"d011f249-9404-43b0-9454-127b51c270b6","resolution":{"observed_at":"2026-08-15T20:18:57.978573Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05709","last_updated":"2020-07-01T00:09:08Z","snapshot_observed_at":"2026-08-15T20:49:51.676387Z","submitted_at":"2020-02-13T18:50:45Z","title":"A Simple Framework for Contrastive Learning of Visual Representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05709","snapshot_observed_at":"2026-08-15T20:18:57.127090Z","title":"05709 [cs.LG]","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T20:18:57.127090Z"},"links":{"cited_paper":"/paper/2002.05709","citing_paper":"/paper/2505.13342"},"observation_digest":"sha256:9b6c48f88bb5c60a3e272883607c545212625574d2dcddd057a46113d19a6c99","observation_id":"54d0747d-a870-4473-84a2-d251b7a80dae","resolution":{"observed_at":"2026-08-15T20:18:57.127090Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.13342","last_updated":"2025-05-19T16:49:27Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T20:13:04.824359Z","submitted_at":"2025-05-19T16:49:27Z","title":"Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":1,"verified_fuzzy":39},"total_outbound_references":47},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2505.13342."}