{"as_of":"2026-08-13T00:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3297d2129b9655eb637e6c6ae1becdb68c7308c667b723deb72a4a52ba9ca6e4","coverage":[{"denominator":75,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":75,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T12:36:43.370579Z","state":"measured"},{"denominator":75,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":75,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2411.17113/citation-record","integrity":"/paper/2411.17113/integrity","json":"/paper/2411.17113/citation-record.json","paper":"/paper/2411.17113"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T12:36:43.008024Z","title":"Deep Learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.008024Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:70e31c683ba9be21b950924fa1a21a79da5194a97a6dfc536391dedb5e6f3788","observation_id":"f7c3de22-67c6-43d5-b281-ccd0c949298b","resolution":{"observed_at":"2026-08-12T12:36:43.008024Z","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":"2026-08-12T12:36:44.555591Z","title":"Deep learning in neural networks: An overview","venue":null,"work_id":"3d1a0752-3bf1-48d5-aca1-2212ec6db34f","year":2015},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.013956Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:a78c47316f90017231c6a9ab0575f97d1859bae6ff144becbded0ebb22b6c67b","observation_id":"f9ab43ce-edd6-43f3-ae92-08b630611916","resolution":{"observed_at":"2026-08-12T12:36:44.560393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.540305Z","title":"A closer look at memorization in deep networks","venue":null,"work_id":"0c272dfd-bf6b-44c7-8130-f99484a236be","year":2017},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.019267Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:a5e78c67f2a448ffdc60cec7ebc04933d1671fcd7e8c4f35350b298e6468edae","observation_id":"00ba77ce-aef4-4276-95da-c4fb8b22b572","resolution":{"observed_at":"2026-08-12T12:36:44.545114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.524736Z","title":"Measurement Error in Nonlinear Models: A Modern Perspective","venue":null,"work_id":"4a34012c-0c0c-4f72-86f9-728caf566a30","year":2006},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.024919Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:1b1d926833c1fc2e5133a1730fc584919d61129ab47fdc247868af938808c1f3","observation_id":"3e71e8a1-a9ae-4b50-9e93-7ee89add3cce","resolution":{"observed_at":"2026-08-12T12:36:44.529700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.509552Z","title":"Statistical Analysis with Measurement Error or Misclassification","venue":null,"work_id":"f2258dfa-69cb-4fe2-9861-4810883c4af9","year":2017},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.030555Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:901cc0611144ea4a703fb89bd9ceb3a76d0e704c47ffae38bb9cb2baf4126fa5","observation_id":"f1ca2b8f-bb9d-4744-96ee-c36237d3042d","resolution":{"observed_at":"2026-08-12T12:36:44.514191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.494245Z","title":"Handbook of Measurement Error Models","venue":null,"work_id":"1a6015bd-8f47-4381-90e7-48fc7c3b23ce","year":2021},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.036035Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:e4524825ee491b11f9fdb6433b2df1502473a12a71d09c79299dc1a7077220b6","observation_id":"d86d63e5-0433-4834-92e0-f9dde196d0b1","resolution":{"observed_at":"2026-08-12T12:36:44.499046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.478675Z","title":"Maximum likelihood estimation of observer error-rates using the em algorithm","venue":null,"work_id":"9d6bc539-6bf0-4a12-916b-40595a026a73","year":1979},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.041696Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:9ee406f0f74a085082646adab3c8b66823d220ac5ffdc90ef5f8de7aec5cfc72","observation_id":"1aad2638-8b25-440e-82c9-2acb6ca661c0","resolution":{"observed_at":"2026-08-12T12:36:44.484074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.463625Z","title":"Whose vote should count more: Optimal integration of labels from labelers of unknown expertise","venue":null,"work_id":"e723f7b7-dacf-4eb6-96a1-ac71d6596d75","year":2009},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.046690Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:fd637a1ea381f611d20c5cfda87544f947d5edda68ed586ae33c8394ad061e57","observation_id":"dfe9ed69-e26c-4017-8701-adb88f46a3e0","resolution":{"observed_at":"2026-08-12T12:36:44.468557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.04577","last_updated":"2018-05-20T06:17:50Z","snapshot_observed_at":"2026-07-06T06:14:05.253482Z","submitted_at":"2017-12-13T00:23:10Z","title":"Learning From Noisy Singly-labeled Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.04577","snapshot_observed_at":"2026-08-12T12:36:43.051682Z","title":"Learning from noisy singly-labeled data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.051682Z"},"links":{"cited_paper":"/paper/1712.04577","citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:3febb1b301c9a378d20b295467bb7e939b3c9b45cdd82f43a1880924b718f1a9","observation_id":"1d3bbc64-9819-4b39-92ea-3c85d8737f0e","resolution":{"observed_at":"2026-08-12T12:36:43.051682Z","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":"2026-08-12T12:36:44.447517Z","title":"Label correction of crowdsourced noisy annotations with an instance-dependent noise transition model","venue":null,"work_id":"da760b70-fb98-48a9-a757-ce39f1d3a8cb","year":2023},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.056976Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:61cdffcb18288958293603f1d1572bf71cb3e439a67c17eb779936be2b221eca","observation_id":"035448a4-033d-4e1c-93a6-86dfa331eb8c","resolution":{"observed_at":"2026-08-12T12:36:44.452582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.13436","last_updated":"2019-05-31T06:32:18Z","snapshot_observed_at":"2026-07-06T07:56:56.876626Z","submitted_at":"2019-05-31T06:32:18Z","title":"Max-MIG: an Information Theoretic Approach for Joint Learning from Crowds","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.13436","snapshot_observed_at":"2026-08-12T12:36:43.061927Z","title":"Max-mig: an information theoretic approach for joint learning from crowds","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.061927Z"},"links":{"cited_paper":"/paper/1905.13436","citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:d25bf2ae06f1928a4be3535b79a8cb76a2ab67f3c558d1e7802ff4fd76620af5","observation_id":"a561e655-1412-4e5c-9b77-81814a15d976","resolution":{"observed_at":"2026-08-12T12:36:43.061927Z","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":"2026-08-12T12:36:44.431243Z","title":"Learning from noisy labels by regularized estimation of annotator confusion","venue":null,"work_id":"2315c9de-b684-4cf0-acf8-4b7e6d449b51","year":2019},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.067273Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:18ba62c3a9ada63691fe2b885e5db8639fda69f8ffcfcc6abda9d36329f0f339","observation_id":"ee921e7b-39c6-4a57-ac63-b8325d54b62f","resolution":{"observed_at":"2026-08-12T12:36:44.436353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.414750Z","title":"Pre-train your loss: Easy bayesian transfer learning with informative priors","venue":null,"work_id":"b379be9d-66b8-4d20-a54a-bfe3c3f4ded0","year":2022},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.071989Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:9843a222052e5fe84d8c1a521763eb4edb2073bfb53899380244c5c6419955db","observation_id":"1fc8d8f1-0690-4d6f-a821-f78eb4d7f269","resolution":{"observed_at":"2026-08-12T12:36:44.419886Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.398306Z","title":"Are anchor points really indispensable in label-noise learning? In Advances in Neural Information Processing Systems, volume 32, pages 6838–6849, 2019","venue":null,"work_id":"336e7608-40c2-4d14-809a-40ae2aaee23e","year":2019},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.076614Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:c6a6440c1af1a85a1abb32dcf080e59eabfed3947b29fa7e1a70cdb733434b09","observation_id":"3addde19-3687-424c-8bc0-bfbe925e8df2","resolution":{"observed_at":"2026-08-12T12:36:44.403678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.380594Z","title":"Adversarial interpretation of bayesian inference","venue":null,"work_id":"c61dae93-4902-4dbb-b319-006a243821d8","year":2022},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.081292Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:8a4868677389176a55406cea7596ec4f70f5c2f47a56dc1a2819bd9794deaf71","observation_id":"efe44f47-cc35-45c2-a2f9-2f4edd9fe938","resolution":{"observed_at":"2026-08-12T12:36:44.386587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.363847Z","title":"Conditional distributionally robust functionals","venue":null,"work_id":"3106ff46-5c63-447c-ab79-1ac7e7e65c6d","year":2023},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.085654Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:52f1a8a47f0cfece6c9299f3a19ca00343547e327e3abf4678632c67407beac9","observation_id":"77dcc4a0-c8f5-45d0-bb40-73c0cc10d674","resolution":{"observed_at":"2026-08-12T12:36:44.368825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.348196Z","title":"Quantifying distributional model risk via optimal transport","venue":null,"work_id":"c9e0e795-3b2c-4355-bdac-801883b7de2f","year":2019},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.090332Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:8906d9d3a496525671ec6679986a24ced8b91471d4456ea5dfef068833bdd6d0","observation_id":"e7f49ee3-e985-4dc6-aa85-ac599dd8c110","resolution":{"observed_at":"2026-08-12T12:36:44.353357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.331665Z","title":"Distributionally robust stochastic optimization with Wasserstein distance","venue":null,"work_id":"225afd76-2e06-4f96-9cf4-68da0f10776b","year":2023},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.095004Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:2ac2f213f2fb20e9906b63d6e754dc987ee9eb445b313c2b885ce71db83d7366","observation_id":"7aca7dd3-17cc-4367-8e75-77ec534e4bb4","resolution":{"observed_at":"2026-08-12T12:36:44.337179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.314983Z","title":"Joint optimization framework for learning with noisy labels","venue":null,"work_id":"4dee4174-dfde-4a5d-9530-e293ec0b069e","year":2018},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.100098Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:3bc6652e489d3efe83060f8f60d52c47a06c9b268b81a6984085f1ee8e453c9d","observation_id":"8e1033f3-9e96-4205-a4bb-54154f760650","resolution":{"observed_at":"2026-08-12T12:36:44.320160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.298880Z","title":"Cover and Joy A","venue":null,"work_id":"2af07d65-cb18-4f97-8c56-1838990098a6","year":2006},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.105075Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:65723c751d2e0e8447ae344874a69578cd6fca49d4093e80df3f12a13c1e7036","observation_id":"72837a2b-d826-4ba8-853f-6b710b84ea50","resolution":{"observed_at":"2026-08-12T12:36:44.303858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.109928Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.109928Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:1ce595408ea597561e0fca7abc6668ba7e13df22e47a457a945c62385500b4a1","observation_id":"38f7c8f0-bd21-4ff5-80d7-d9b0e18f0793","resolution":{"observed_at":"2026-08-12T12:36:43.109928Z","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":"2026-08-12T12:36:43.114788Z","title":"Learning with noisy labels revisited: A study using real-world human annotations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.114788Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:52ba993f224d0479f31b2500d7a21e4d6461cf6d025f547ff6ff6a925eb08815","observation_id":"acb4a0ff-e832-4ce9-ac1f-9f77a42d0580","resolution":{"observed_at":"2026-08-12T12:36:43.114788Z","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":"2026-08-12T12:36:44.262809Z","title":"Learning supervised topic models for classification and regression from crowds","venue":null,"work_id":"30a1928c-7b87-4ada-84b6-440c79e2f454","year":2017},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.119453Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:6ee9351862fc86c12b6bee9a59a8210842941c0ed78f713044db49308d07bfc1","observation_id":"bd0f33bb-2251-4340-8742-022cea837915","resolution":{"observed_at":"2026-08-12T12:36:44.267902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.246851Z","title":"Russell, and Jenny Yuen","venue":null,"work_id":"a3e3b45b-db68-4465-8714-95b509448683","year":2010},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.124013Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:915140f5435ee87d6bb4897255a959e00eada67dc3150caf09fc2994942844d6","observation_id":"a46c7d7d-48f8-426f-ac49-7513771f1b4c","resolution":{"observed_at":"2026-08-12T12:36:44.251921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.230081Z","title":"SELFIE: Refurbishing unclean samples for robust deep learning","venue":null,"work_id":"e1c3105c-87f9-416a-b4e5-67e16d7b1d0f","year":2019},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.128579Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:0e780e9e810c9a5557bed65c8d25454a3876ac1d64fc07dfabb5a1c8ddf67aee","observation_id":"4297eb63-c12d-410a-9e9c-74cff6036db1","resolution":{"observed_at":"2026-08-12T12:36:44.235683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.133247Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.133247Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:3374b67283eba2aadb3b9897104721379f4971696415bfb8adea2dfb331e4532","observation_id":"11c19521-1348-459f-b8df-27d738e0e54b","resolution":{"observed_at":"2026-08-12T12:36:43.133247Z","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":"2026-08-12T12:36:44.202267Z","title":"Deep learning from crowds","venue":null,"work_id":"e4271445-656c-4436-863c-df2a96dfacc1","year":2018},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.137955Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:7d0251c75262ad3ef4b94d91701ef7935e25d6350e1e3c5f5f4aab1ac5ccab4f","observation_id":"635c833d-2429-47e3-8c62-9167c6c03a66","resolution":{"observed_at":"2026-08-12T12:36:44.207120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.186160Z","title":"Very deep convolutional networks for large-scale image recogni- tion","venue":null,"work_id":"7c83f3bb-7e6b-439d-bbe3-3c68a9166081","year":2015},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.142913Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:0387e922a1a8d5b280d8b56a1079e7612231ba0d856b3ee4857fc7b9170a7e39","observation_id":"2f1f8ec1-aee5-45e9-bbc5-1b8c3f083e61","resolution":{"observed_at":"2026-08-12T12:36:44.191303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.170151Z","title":"Part-dependent label noise: Towards instance-dependent label noise","venue":null,"work_id":"feb58f2f-b4f3-4d29-ae11-ea2538694b71","year":2020},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.147741Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:c6bca50373fedc73b86d2fd54143bd2f02cc589ad532565e94ce195584af4180","observation_id":"3c10003e-5a41-46bc-9ae8-32f95eb3a742","resolution":{"observed_at":"2026-08-12T12:36:44.175162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.154143Z","title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","venue":null,"work_id":"07c65b67-c592-4fe9-b148-68cd72926b45","year":2018},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.152569Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:77178af0439f27b2543b6660bfdb39bd244c593f8137fb695ab98f800c8b503c","observation_id":"ace529b6-e812-494f-ae1e-e753a81d379e","resolution":{"observed_at":"2026-08-12T12:36:44.159440Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.137387Z","title":"How does disagreement help generalization against label corruption? In Proceedings of the 36th International Conference on Machine Learning, volume 97, pages 7164–7173, 2019","venue":null,"work_id":"96c5c131-ca72-403f-b6b6-df2c5e0c4197","year":2019},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.157099Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:db4f3749cd9846770f760359782742424c578abdaf2cabc0946e121ae47837ad","observation_id":"730daaa3-f45b-423b-9998-4bfe6753cadb","resolution":{"observed_at":"2026-08-12T12:36:44.142738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.161729Z","title":"Combating noisy labels with sample selection by mining high-discrepancy examples","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.161729Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:522fdd1edff3859e6a7904d96c36518a62d932a692e793ee89194988ed098aec","observation_id":"d1b7d3bd-b710-4c99-9513-60656b6c9339","resolution":{"observed_at":"2026-08-12T12:36:43.161729Z","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":"2026-08-12T12:36:44.108800Z","title":"Mitigating memorization of noisy labels by clipping the model prediction","venue":null,"work_id":"89393d9a-4bb3-4ba5-b09a-2f1d7dda0599","year":2023},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.166323Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:fd7fcbbe2206fa99aa592ad757f491adf83e448c8e5c01c73a8f47b4059a92f7","observation_id":"6de47dd0-a581-4e17-adae-f88cf1e3e644","resolution":{"observed_at":"2026-08-12T12:36:44.114823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.091757Z","title":"Who said what: Modeling individual labelers improves classification","venue":null,"work_id":"654a7ec5-dd1f-45ef-a9cf-203c3f36ff5e","year":2018},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.170785Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:bb2b7d845f6e872efdef57a9b4c1a0753e70fc69dbe9741f7fe3ae76b930cb29","observation_id":"b944b11e-4896-4088-bcd1-0a2698c1cf91","resolution":{"observed_at":"2026-08-12T12:36:44.096694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.075634Z","title":"Learning from crowds by modeling common confusions","venue":null,"work_id":"dbf45488-66db-4af6-93c9-a3c7ccd94baf","year":2021},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.175457Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:375d9cb4432c9d5f572e78ca5862d0c2d8b27f833e4fb27c5e0845836de95ae1","observation_id":"b878c5df-09eb-416d-ae4a-9aac342eee35","resolution":{"observed_at":"2026-08-12T12:36:44.080570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.058969Z","title":"Coupled confusion correction: Learning from crowds with sparse annotations","venue":null,"work_id":"72d0552c-b65c-4477-8370-7ba9331b1eb5","year":2024},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.180484Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:3be2ceae2a03d0d81f1f8127103153b723d6125b47b6dbd055e7a936a334bc58","observation_id":"fa02f2f2-8f36-4a5d-9d92-19abd1d3c2b8","resolution":{"observed_at":"2026-08-12T12:36:44.064140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.042507Z","title":"Linear and Nonlinear Programming, volume 2","venue":null,"work_id":"56d5876c-69dc-4279-a2b1-2364e7585117","year":1984},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.185334Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:f75b7900b14412b2a2866c29927d4818a43c7861e23ae4ff87239abc0c2f1b65","observation_id":"9d52874a-1f25-4e2d-856e-763749fa12d3","resolution":{"observed_at":"2026-08-12T12:36:44.047696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:44.026210Z","title":"Applied Mathematical Programming","venue":null,"work_id":"88f94fbe-5197-4588-876d-75b9695f1c6f","year":1977},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.190144Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:ff21442cc9dd5e0160e88b6b61bbafc58555570df759569031cc588adb859dfa","observation_id":"dbc2ae1d-61e3-495c-900b-1c456cdc83fd","resolution":{"observed_at":"2026-08-12T12:36:44.031328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.194737Z","title":"High-Dimensional Statistics: A Non-Asymptotic Viewpoint","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.194737Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:045c80c4a9f10a4b29b5a42907def0ec429e8a826275267c8f6fe79f2181c927","observation_id":"319ac0e6-d234-4660-b00e-a47cb8999711","resolution":{"observed_at":"2026-08-12T12:36:43.194737Z","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":"2026-08-12T12:36:43.998841Z","title":"Minimax statistical learning with wasserstein distances","venue":null,"work_id":"05309083-c1c5-406e-9a7a-95b7228b2548","year":2018},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.199356Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:8bb7c4aee1c376692f325166324233bb74011f3295707c172bb9c3a34e1d0250","observation_id":"75d18708-c3b6-44f3-81ff-67fcdc1168c3","resolution":{"observed_at":"2026-08-12T12:36:44.004044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.982858Z","title":"The supremum and infimum","venue":null,"work_id":"484e0374-ff6c-4a5e-847d-e58b15d53a66","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.204053Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:ddac2935c0f48a52948a00aac4ea7787e1c8cb4ca31b08a91a2137096ec1be28","observation_id":"083632ad-5982-48e5-b7bf-b8e1e8d957ec","resolution":{"observed_at":"2026-08-12T12:36:43.988142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.967294Z","title":"Foundations of Machine Learning","venue":null,"work_id":"932d1952-41c3-48e4-9075-83edde507d56","year":2018},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.208766Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:0683a07bca5454571673602adb7962b83c3c84e854eac0bd97591421e308f836","observation_id":"d62459f9-86b9-452f-8c7a-d209aa37d64d","resolution":{"observed_at":"2026-08-12T12:36:43.972264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-12T12:36:43.213563Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.213563Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:e8c667d9031d19544f7263396fb54193fc659748249e8783891d05c8c1440a31","observation_id":"71a90fad-e565-4581-b60c-55d9e551eeba","resolution":{"observed_at":"2026-08-12T12:36:43.213563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1411.4086","last_updated":"2014-11-15T00:02:34Z","snapshot_observed_at":"2026-08-01T16:02:07.874066Z","submitted_at":"2014-11-15T00:02:34Z","title":"Error Rate Bounds and Iterative Weighted Majority Voting for Crowdsourcing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1411.4086","snapshot_observed_at":"2026-08-12T12:36:43.219079Z","title":"Error rate bounds and iterative weighted majority voting for crowdsourcing","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.219079Z"},"links":{"cited_paper":"/paper/1411.4086","citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:6ed6d413880bff4ec6720217b6b86512558308c55b82b376ca65e7a8fe11ee78","observation_id":"0af6173a-9cce-4df8-92bc-facbe39f883a","resolution":{"observed_at":"2026-08-12T12:36:43.219079Z","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":"2026-08-12T12:36:43.951573Z","title":"Leverag- ing inter-rater agreement for classification in the presence of noisy labels","venue":null,"work_id":"e3091a3b-8e2d-472a-9877-3f2811403cb3","year":2023},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.224110Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:bb78a7af1593779d1f1dc518aeca68515618116b647df287a680e94c820b6a19","observation_id":"e4f35b72-9b36-4cd1-b92a-b06b7ca1588e","resolution":{"observed_at":"2026-08-12T12:36:43.956696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.935414Z","title":"Error-bounded correction of noisy labels","venue":null,"work_id":"46921207-a2f7-4df9-b31b-20b81018d2df","year":2020},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.228806Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:a6338bf6356f6174cae79756bbe7c6f7e49c500add232f539d1693764470395e","observation_id":"ef212bb2-46df-473b-abcb-381f798b3d75","resolution":{"observed_at":"2026-08-12T12:36:43.940476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.919391Z","title":"parameter","venue":null,"work_id":"24a1cabd-fb98-4756-a63b-8ac84d385d24","year":2023},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.233406Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:9cb1038c4f79806d31323953365ca963974405c05a9896d9a3a97ba636ddb514","observation_id":"957e00d8-849d-435c-9dca-a57d41dbdaa2","resolution":{"observed_at":"2026-08-12T12:36:43.924332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.903215Z","title":"We complete the proof by considering the following two cases","venue":null,"work_id":"9e0d423b-7b69-4db9-8a99-e6ad3a82107b","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.239264Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:1ab7abe2261dfec442d9ac54121c999f8897275c81f0a4f68a0fd75aaf6e0790","observation_id":"da17719f-3f65-4743-9c83-4b6c943303ae","resolution":{"observed_at":"2026-08-12T12:36:43.908547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.887654Z","title":null,"venue":null,"work_id":"5aedc978-c6a9-4410-b272-34a0c03b0687","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.244154Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:913de69a84f7bbda457c00e97f84d2630802d9f177c642fb8d61d0689fed3d60","observation_id":"8d38e8cd-d87f-4487-b153-ad53d0a015ab","resolution":{"observed_at":"2026-08-12T12:36:43.892491Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.871890Z","title":null,"venue":null,"work_id":"3476cf20-d0cb-478c-b18c-f9b042b2c9c1","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.248974Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:f83e118f4dfb1ca2114738e702fd66bead3a4b577ce9aeba66008335461c65d9","observation_id":"e4464bd7-1184-4ca3-b56b-49cd28d3801c","resolution":{"observed_at":"2026-08-12T12:36:43.876793Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.856224Z","title":"Step 2.2: Assume T is convex","venue":null,"work_id":"6f19f5c4-abe2-43d9-b403-2380e9c39554","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.253761Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:130184265a0fbdac3707a04bb2356e51126fb09a8dd4d22b0e5cb05de72e1dfc","observation_id":"be325188-cdb4-4267-a9c3-e23998680e2d","resolution":{"observed_at":"2026-08-12T12:36:43.861220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.840666Z","title":"Thus, ψ∗ 1 = ψ⋄ 1 with γ∗ ψ∗ 1 = T (ψ⋄ 1 )−T (1−ψ⋄ 1 ) κp by (A22)","venue":null,"work_id":"84f4d658-dbec-4d80-b8ae-2647ffedd0b6","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.258684Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:c09f0c0e2c42b8cb74c2b584a7a6873310a8126e23c12841a3f58c521735bc8c","observation_id":"a2203b8a-eefd-4f6b-baff-175b46dac46a","resolution":{"observed_at":"2026-08-12T12:36:43.845605Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.824822Z","title":"25 • Step 2: If P1 ≥ ϱ(ϵ), then, by (A22), γ∗ ψ∗ 2 is set as γ∗ ψ ∗ 2 = T (ψ ∗ 2 )−T (1−ψ ∗ 2 ) κp = T (1−ψ∗ 2 )−T (ψ∗ 2 ) κp","venue":null,"work_id":"76c7fbbb-7a6a-4f12-9f07-d62545adec8c","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.264915Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:7864a9c8d8fd7caf43160d18e876cbb230d2a826f6c8383d6af90a0c1a077ac4","observation_id":"818e238e-d4b2-4d79-9433-23c6f5b247b9","resolution":{"observed_at":"2026-08-12T12:36:43.829870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.809417Z","title":"– If P1 > ϱ(ϵ) + T (0)−T (1/2) T (0)−T (1) , then ψ ∗ 2 = 0 and γ∗ ψ∗ 2 = T (0)−T (1) κp","venue":null,"work_id":"7b9fcf64-f256-42cb-b81a-7d973632c4d6","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.269614Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:4fdc95e1a36fbab4069fabc7ab1484080b573cb5b1b5aab2955768ea684f2a43","observation_id":"0095a947-f9bc-4f95-b5b2-b7c1eb735627","resolution":{"observed_at":"2026-08-12T12:36:43.814170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.793820Z","title":"• Step 2.2: Assume T is convex","venue":null,"work_id":"25e5e549-b8b7-4a79-9e52-619f143924b4","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.274261Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:405715ff9734f536421ee048ee881ec070ae88d55f56d19f5365a4c55547b8e9","observation_id":"556a500a-192b-46ec-b034-1fa68b4d6c55","resolution":{"observed_at":"2026-08-12T12:36:43.798697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.778208Z","title":"– If ϱ(ϵ) ≤ P1 ≤ ϱ(ϵ) + 1 2, then ψ ∗ 2 = 1 2 and γ∗ ψ∗ 2 = 0","venue":null,"work_id":"f6833a78-f033-406c-a433-d411c3202e9c","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.278966Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:18dfd292a95ad1c2f44a0fa1198f31bad30509dc211e929590fb741f738d16c8","observation_id":"f8a17f71-4cad-47dd-b063-f132c86142c8","resolution":{"observed_at":"2026-08-12T12:36:43.783141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.762348Z","title":null,"venue":null,"work_id":"be5a974f-1a55-4660-adb4-726dd97c6dc1","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.283779Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:8597cf861d91f7bbdb69dee1b0a67e73e764641863f97608988726df296b7ff4","observation_id":"2c558177-1974-40f2-84eb-73e093ea2ef2","resolution":{"observed_at":"2026-08-12T12:36:43.767285Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.746993Z","title":null,"venue":null,"work_id":"35880e99-a59a-469c-8956-e959a622a8e6","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.288379Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:4e910859323a6714b7a6250e58df907fc434f52bd919623a0bd5913f199e9c4e","observation_id":"58ce3f7e-5b20-40dc-ba29-f81b95d8172f","resolution":{"observed_at":"2026-08-12T12:36:43.751901Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.730743Z","title":"In summary, we present the derived results in Tables 3 and 4 for the scenarios whereT is concave and convex, respectively","venue":null,"work_id":"2dd47d41-6545-4bf1-875d-8035ab3b4df5","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.293058Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:a0187b44a271640384a434b4bfc2c817658902b05ee99b483809c3012ce06b16","observation_id":"49e278e7-34ed-4a34-a8c1-e51063bf9dbc","resolution":{"observed_at":"2026-08-12T12:36:43.736020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.714940Z","title":"Update by Disagreement","venue":null,"work_id":"983a87fc-a1f8-4d69-a88b-f68841c875c8","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.298831Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:7eb006b2c6b5fac906f47c4e42df244926681e237dc56a16cb9fba4b3cace2a4","observation_id":"71d38792-4056-4784-bdfb-156fceec2cc0","resolution":{"observed_at":"2026-08-12T12:36:43.719890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.698994Z","title":"Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper","venue":null,"work_id":"84597f6b-1b6c-476c-8e73-64395cdc22fa","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.303808Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:640314e607e9a66d574fd4126a89ef5b710e570ef8e6e772e1241cfc26c04634","observation_id":"c38e3542-0272-4512-9d85-107c40321234","resolution":{"observed_at":"2026-08-12T12:36:43.703975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.683106Z","title":"Limitations","venue":null,"work_id":"13c0686c-a82a-48e5-81ad-9e8750fd619a","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.308674Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:34526f451351b09b6799e616732f9622e465bee71f6f585ad97f1c1c8b2c2ca5","observation_id":"2823558c-eaa8-48ba-89d4-8b7314793a91","resolution":{"observed_at":"2026-08-12T12:36:43.688117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.666051Z","title":"Guidelines: • The answer NA means that the paper does not include theoretical results","venue":null,"work_id":"382f226e-3f3c-448f-b2c2-c2df7b388424","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.313243Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:587b160b2aa76e474bedfc19c30878a0028b5852728c60266c43f6bf33017526","observation_id":"67558c91-f53e-4feb-b83f-caff7bce54ee","resolution":{"observed_at":"2026-08-12T12:36:43.671723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.648701Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"08b56aba-f84b-43b5-bfd2-d9038a62bb87","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.317755Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:e2cf76c97a067321264af128adaa66810047aae6af249a4f9e68802cc682163a","observation_id":"4b051042-7e1e-436d-b6f0-d573b426b24e","resolution":{"observed_at":"2026-08-12T12:36:43.653827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.632060Z","title":"Guidelines: • The answer NA means that paper does not include experiments requiring code","venue":null,"work_id":"047251f0-019c-490c-a5ef-f930cc6faefd","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.322998Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:d59489ba27d294a1c933f7df8ec59a8918b47ae263b654960d4680e89d06a057","observation_id":"164beeeb-174e-4896-967b-91529d9a36e6","resolution":{"observed_at":"2026-08-12T12:36:43.637268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.615631Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"52788b5d-0db3-428f-b60e-6ff05268ad49","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.327720Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:2173217f0831cf85bdbabcd4ab0d706b1154d0650f617318034fb61060b51f70","observation_id":"37af4b35-7423-48a3-9e1d-991be8c2266d","resolution":{"observed_at":"2026-08-12T12:36:43.620856Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.599457Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"01f2ba6d-c96d-4aec-83e8-90519a9d05b1","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.332434Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:7970f0f4088324a97ad8cc40654b9de5f11a82dfe6cb5fe22019ebde6119f491","observation_id":"50b72063-401a-4717-a449-c597d5f38635","resolution":{"observed_at":"2026-08-12T12:36:43.604790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.583586Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"85c3dc66-34be-4fd6-bf42-09ee8d2cf824","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.337338Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:5f82aebbd44d8ccb62df3cec42e8d3228ab0c94b667814dfe93563810229743c","observation_id":"f82622fb-9724-43e7-b4c5-a50049afad74","resolution":{"observed_at":"2026-08-12T12:36:43.588490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.342093Z","title":"Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.342093Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:4ef438c5c4210227aff5734da52bbf78518905c10ab4d95982b1ab03cc665e44","observation_id":"93aef465-7657-44be-9a32-6e1d37842b0a","resolution":{"observed_at":"2026-08-12T12:36:43.342093Z","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":"2026-08-12T12:36:43.555830Z","title":"Guidelines: • The answer NA means that there is no societal impact of the work performed","venue":null,"work_id":"41fa28fd-7bf0-4381-a1eb-5091a77ae043","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.346725Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:c4db1dc90e7e91bcd408036dc4c2491171e0bdf3069ab073d573c0eb9c5e6627","observation_id":"dee5b9a0-64cb-40d1-adcb-2c86eaf6416b","resolution":{"observed_at":"2026-08-12T12:36:43.561231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.538841Z","title":"Guidelines: • The answer NA means that the paper poses no such risks","venue":null,"work_id":"5ab43603-f281-45f5-bbc1-fa3f8d00d730","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.351768Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:74ed38f2a8227e9b6b3811e815891c63deb2cb733cb3fef57c68dc03a0faee34","observation_id":"e115b4c4-67ad-4e84-90af-38176ca5191f","resolution":{"observed_at":"2026-08-12T12:36:43.543894Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.522981Z","title":"Guidelines: • The answer NA means that the paper does not use existing assets","venue":null,"work_id":"3875cad0-0f6f-4e4f-9a1f-90c543ce4de0","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.356645Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:fa1be797e8dfa878ccfb2bc32d3ca9fc67162d79cfd988ccbd386a2c42d4731c","observation_id":"d73f59fe-1881-4525-993f-548a93b51447","resolution":{"observed_at":"2026-08-12T12:36:43.527924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.506719Z","title":"Guidelines: • The answer NA means that the paper does not release new assets","venue":null,"work_id":"685bbe22-ef5d-4d6b-a145-16fec931a319","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.361376Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:e22622f1fc8c64d608c2f15e650f0ac7d12062c2e655af98893d1b8ad746429e","observation_id":"31aa51b9-f555-4bfc-b1b4-91f5381ddea9","resolution":{"observed_at":"2026-08-12T12:36:43.511640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.490750Z","title":"Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"d1cf7219-3653-460f-be08-9cf1531b8cd2","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.365952Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:ac9219d40981862fb7f1fd5a1e18f4c28ea02c426324d195abd9bdc97e6b416e","observation_id":"4cdba0a7-6124-40a8-b4bb-43fc2d7cb83a","resolution":{"observed_at":"2026-08-12T12:36:43.495794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T12:36:43.471835Z","title":"Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"2e45c2e0-70a7-409a-bff4-e67c5c124da3","year":null},"citing_paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-12T12:36:43.370579Z"},"links":{"citing_paper":"/paper/2411.17113"},"observation_digest":"sha256:158fc935acc45c88281a2e55fd2f0aabe51ad57d4495a85a8b0200a9616268a9","observation_id":"2f76ce4d-fbd8-4317-ab34-fc51b59a43a9","resolution":{"observed_at":"2026-08-12T12:36:43.479750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.17113","last_updated":"2024-11-26T05:03:26Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T12:27:55.690075Z","submitted_at":"2024-11-26T05:03:26Z","title":"Learning from Noisy Labels via Conditional Distributionally Robust Optimization"},"reference_resolution":{"displayed":75,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":14,"verified_exact":0,"verified_fuzzy":60},"total_outbound_references":75},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 0 inbound Pith citation observations for arXiv:2411.17113."}