{"as_of":"2026-08-16T15:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e5d6590f1885ca8e82cac1efdef74b4e111187738e041d674d463afdbdbb839c","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T22:26:58.411597Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2501.01844/citation-record","integrity":"/paper/2501.01844/integrity","json":"/paper/2501.01844/citation-record.json","paper":"/paper/2501.01844"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:26:59.078788Z","title":"A survey on data collection for ma- chine learning: a big data-ai integration perspective,","venue":null,"work_id":"7e194f85-3620-4d74-9807-053cd4de68d3","year":null},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.187784Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:6205781aee1297d8c776281d22b7ed6cf3af11175f44fdd63e5cd92a25e1395c","observation_id":"90362a7d-391e-4274-9c7c-9ed474eb3c8f","resolution":{"observed_at":"2026-08-10T22:26:59.082683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:59.067989Z","title":"Crowdsourced data management: A survey,","venue":null,"work_id":"f6e006b6-9305-4f0f-bbd8-ea2a2f62eeaa","year":2016},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.192445Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:fbe896df7d7654fbe9744c66958bed976df0e9fbade50288c21aa7c391c83e11","observation_id":"178d4f20-1f92-456d-9d13-221c8b438485","resolution":{"observed_at":"2026-08-10T22:26:59.071980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:59.057294Z","title":"Learning from crowdsourced labeled data: a survey,","venue":null,"work_id":"2517dba7-ef4a-418d-9c7d-6beb7df3d4c3","year":2016},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.196435Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:918c0bba161a2972e762fa83f0118ccc6dc5e354335435974eae42ba5c64fc60","observation_id":"c668ea93-c2fa-4d9c-a4f6-cc3c2324bdd4","resolution":{"observed_at":"2026-08-10T22:26:59.060955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:59.046592Z","title":"Learning from multiple annotators with varying expertise,","venue":null,"work_id":"00c8bcf8-1807-4596-9ce6-4733e5f59294","year":2014},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.200358Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:d8fe2e68fd6ec09f2355f70a29eb25cff9695d43a6e63a998f3ed831a136cb81","observation_id":"c347e476-b047-4a97-b6d2-fa6c1b01ae93","resolution":{"observed_at":"2026-08-10T22:26:59.050440Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:59.037460Z","title":"Learning from noisy large-scale datasets with minimal supervision,","venue":null,"work_id":"337eb805-295c-4462-a1c4-a8a197ecaeb3","year":2017},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.206094Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:c9e7cbb12e858622fd6294982215c1559dffb29f5d94ba17dde5d8bab0352127","observation_id":"88294b31-165c-4212-98e4-f7b416e243cc","resolution":{"observed_at":"2026-08-10T22:26:59.040603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:59.027879Z","title":"Evaluating machine accuracy on imagenet,","venue":null,"work_id":"eef724e6-eb9f-4c74-b50d-7f9c257b5a0d","year":2020},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.210454Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:9bd86aa29e458b28cb38d2bd175968fe443b53798d804ae83b5331d0823511c4","observation_id":"ad9629c7-7508-4aca-b05e-ffd5fe0b01a8","resolution":{"observed_at":"2026-08-10T22:26:59.031387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:59.017070Z","title":"Learning with noisy labels revisited: A study using real-world human annotations,","venue":null,"work_id":"cef51653-1787-4ef6-90e2-665b9aba3a52","year":null},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.215661Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:a612901d0f876a6cbc489e62e9a4eb7e04931e0799489b12c46d14baf9af9eaf","observation_id":"88ea76c9-a30c-4803-ab74-84e1d80d925e","resolution":{"observed_at":"2026-08-10T22:26:59.020921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:59.006428Z","title":"Pervasive label errors in test sets destabilize machine learning benchmarks,","venue":null,"work_id":"0dcb904f-2fa8-4745-880c-072ae4826dd6","year":2021},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.220264Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:b5152f9a5ebbc5e0f060acfe150bd3ce439e6758e4f3836fded20f03a6257526","observation_id":"a7109247-e224-4017-af9a-6195ef5ba6aa","resolution":{"observed_at":"2026-08-10T22:26:59.010277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.995209Z","title":"Deep label distribution learning with label ambiguity,","venue":null,"work_id":"73caba65-8185-42fa-b410-f380e29b6657","year":2017},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.225004Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:510755aa0c5b42540637374937c5b7782fae3fbb9a5d71ce31eeba10a967a1dc","observation_id":"af5f2d18-b5f1-4809-add8-920c0a35dd6f","resolution":{"observed_at":"2026-08-10T22:26:58.998953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.09496","last_updated":"2020-09-20T18:42:13Z","snapshot_observed_at":"2026-08-15T17:35:10.950484Z","submitted_at":"2020-09-20T18:42:13Z","title":"Learning Soft Labels via Meta Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.09496","snapshot_observed_at":"2026-08-10T22:26:58.230327Z","title":"Learning soft labels via meta learning,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.230327Z"},"links":{"cited_paper":"/paper/2009.09496","citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:bddb6ae9fae212359db9886f7af36e04620983f8c08ccc98b9102e654ac56585","observation_id":"65afd91c-660c-41a2-b6fb-73ef5ab8bd57","resolution":{"observed_at":"2026-08-10T22:26:58.230327Z","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":"2026-08-10T22:26:58.985166Z","title":"Human uncertainty makes classification more robust,","venue":null,"work_id":"a8603667-cdee-4c4f-af0c-149151cfa31d","year":2019},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.234115Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:63003717554a1be5d5511c33a9be1ba98a35a2bdd423a80894864049f72f1f57","observation_id":"99a22f18-3269-4b4f-9558-55eb466c7a6f","resolution":{"observed_at":"2026-08-10T22:26:58.988629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.974406Z","title":"Re-labeling imagenet: from single to multi-labels, from global to localized labels,","venue":null,"work_id":"e8c1ab63-9e0b-4d97-b3e4-8839c11803c2","year":2021},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.237603Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:d4a52d836a8c69c60aa88693166583fdcebc704545ed0a5228c6c1d49bdbacbb","observation_id":"d15449aa-11fe-487c-ad73-3d50f9de13d0","resolution":{"observed_at":"2026-08-10T22:26:58.978317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.962743Z","title":"Artificial neural variability for deep learning: On overfitting, noise memorization, and catastrophic forgetting,","venue":null,"work_id":"68360119-0fd9-4add-8414-32fc5e77e26a","year":2021},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.241063Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:4fba5e14b6ece6e7ea7b49560426e0bbe0d308c17867364f9185f38a498ede31","observation_id":"1ccf8fbf-57e3-4536-b2d1-1409505b2b20","resolution":{"observed_at":"2026-08-10T22:26:58.967154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.951734Z","title":"Positive-negative momen- tum: Manipulating stochastic gradient noise to improve generalization,","venue":null,"work_id":"f9c0cd23-5109-435a-81c2-f483942da3e7","year":2021},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.244413Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:012bff8dc5d55f7e6500b31897cc2fc2babed8de380572476bfe4256a786cc0f","observation_id":"2de81406-2841-4596-bebe-8944160f217f","resolution":{"observed_at":"2026-08-10T22:26:58.955678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.06224","last_updated":"2022-10-06T08:22:10Z","snapshot_observed_at":"2026-08-13T15:04:54.165538Z","submitted_at":"2022-07-13T14:25:30Z","title":"Beyond Hard Labels: Investigating data label distributions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.06224","snapshot_observed_at":"2026-08-10T22:26:58.247443Z","title":"Beyond hard labels: Investi- gating data label distributions,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.247443Z"},"links":{"cited_paper":"/paper/2207.06224","citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:cac3a0fb78dbe39cc6c1a58f6fef48798b54add29a1d5622267af0c15f1d2215","observation_id":"95881082-9cb2-41e8-a5f4-e39c0b6ec12a","resolution":{"observed_at":"2026-08-10T22:26:58.247443Z","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":"2026-08-10T22:26:58.940935Z","title":"Sparse double descent: Where network pruning aggravates overfitting,","venue":null,"work_id":"de29fe76-da72-4ec3-9cb6-238db364afda","year":2022},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.251460Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:56c87c5db901db40dec731056752284c58dd43a5332fd5b1283fde306119c6a2","observation_id":"63d05169-aa64-4f71-b0eb-dce27d65fe1f","resolution":{"observed_at":"2026-08-10T22:26:58.944831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.04406","last_updated":"2021-02-20T07:28:12Z","snapshot_observed_at":"2026-08-15T21:03:24.408746Z","submitted_at":"2020-11-09T13:16:02Z","title":"A Survey of Label-noise Representation Learning: Past, Present and Future","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.04406","snapshot_observed_at":"2026-08-10T22:26:58.254954Z","title":"A survey of label-noise representation learning: Past, present and future,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.254954Z"},"links":{"cited_paper":"/paper/2011.04406","citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:cb0710f3c2f5c5666a16c01220c2f1e7310880f4445ecf77afb9c5dc1aac6799","observation_id":"5e96410f-c717-47bc-ba45-0749c1d873c3","resolution":{"observed_at":"2026-08-10T22:26:58.254954Z","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":"2026-08-10T22:26:58.930220Z","title":"Analysis of learning from positive and unlabeled data,","venue":null,"work_id":"8cb46e3c-e7ea-4d58-b869-345e7d5d4158","year":2014},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.259412Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:a920eaa67f7c5ecc5ea868b105770345a37369a62cab05c21d959b1380e25700","observation_id":"5c69136d-8bbb-4875-a20d-3bf790ef3059","resolution":{"observed_at":"2026-08-10T22:26:58.934038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.919501Z","title":"Convex formulation for learning from positive and unlabeled data,","venue":null,"work_id":"88434f54-27b8-4f5b-aca1-21e3778254f0","year":2015},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.263031Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:f70ed9130f6684038db6d867f79b3539a9009f98719a18ddcb7558eea1f7958e","observation_id":"8849afa8-5b4d-409b-90a3-d5946c260f7e","resolution":{"observed_at":"2026-08-10T22:26:58.923252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.908809Z","title":"Positive- unlabeled learning with non-negative risk estimator,","venue":null,"work_id":"d7c7a6c7-3393-41a2-8f7b-8735010c5da1","year":2017},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.266617Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:faf1e8f4e9aa98c147df07ca24a135430cccef5e1f2e8ba4dc78de5b84c11bc2","observation_id":"12329261-0bb5-433c-a812-0265c4e464e2","resolution":{"observed_at":"2026-08-10T22:26:58.912455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.899071Z","title":"Theoreti- cal comparisons of positive-unlabeled learning against positive-negative learning,","venue":null,"work_id":"e4d0de33-29ba-4a7f-b2bb-86ceab3eda16","year":null},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.271356Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:49bc4a774b1984b2b077e1d13d8c168fe2208640385ef030632e91fe896cc96b","observation_id":"331980ed-2e2e-434c-8552-7259cf8591ab","resolution":{"observed_at":"2026-08-10T22:26:58.902540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.887368Z","title":"Learning from corrupted binary labels via class-probability estimation,","venue":null,"work_id":"785f324b-051e-4163-a25f-819bcb14ded7","year":2015},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.275097Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:ea2bd3249d8530ba23775664a538ed0f1ac14d77030ebf0f250f385c5a270419","observation_id":"932fb47b-4c1f-49ad-8f4e-d27ad8d418f5","resolution":{"observed_at":"2026-08-10T22:26:58.891375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.876328Z","title":"Estimating the class prior and posterior from noisy positives and unlabeled data,","venue":null,"work_id":"9fd8ebd1-286b-4bf2-8e05-7fd9a8a5de6f","year":2016},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.278663Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:5833d3bcecb0bb6e515104d00be35269df8779722eb724125416e0f866c70c91","observation_id":"332b6562-3507-4231-8623-41aea96d4f10","resolution":{"observed_at":"2026-08-10T22:26:58.880096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.865664Z","title":"Class-prior estimation for learning from positive and unlabeled data,","venue":null,"work_id":"092b450a-a39a-4ff5-974e-0715e5280138","year":2016},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.282316Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:f373d4e1159010f9c2b57f93adde7e80724cf57d64ec170c34691e7c97b90907","observation_id":"f6d16479-b954-43a0-81fb-4ef636c85841","resolution":{"observed_at":"2026-08-10T22:26:58.869829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.855050Z","title":"Rethinking class-prior estimation for positive-unlabeled learning,","venue":null,"work_id":"db348ed6-2b91-440d-bfea-6934f25e4ef7","year":2021},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.285758Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:4c241a9b447d5a255e277e6d2b04d2546ec5b968ede0ec00d4db30f3272db5d1","observation_id":"56944038-d87b-4468-9268-596a07a67b6c","resolution":{"observed_at":"2026-08-10T22:26:58.858756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.843975Z","title":"Generalized jensen-shannon divergence loss for learning with noisy labels,","venue":null,"work_id":"3e88d552-74ec-4e64-aeb6-dd138796db2c","year":2021},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.290404Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:5847c7ff28b24fd1321ae642da51743020fbffdd06c24f3452de92c54e4ed7a5","observation_id":"bd99160e-dc77-479d-97d7-c8132f74e51c","resolution":{"observed_at":"2026-08-10T22:26:58.848010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.833261Z","title":"mixup: Beyond empirical risk minimization,","venue":null,"work_id":"1cccf90b-c04e-46f1-b620-8dad9d6fcb39","year":2018},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.294133Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:eea2c3a6e8e5b866085692262f4aa75f84e35ff2725007ce91bb61dc80416ca6","observation_id":"cad82bbe-7519-449c-b5e1-fd0a2c05e312","resolution":{"observed_at":"2026-08-10T22:26:58.837166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.812923Z","title":"Cutmix: Reg- ularization strategy to train strong classifiers with localizable features,","venue":null,"work_id":"9e0dbd9c-8579-408e-b0bc-fc6978dba41c","year":2019},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.301896Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:5fb88d8e4626a2a6c633b43f66ee845a43adbc1570bf2b84fd95d6a5c7e2e30d","observation_id":"c6578fda-c743-4288-a3b3-5ffbaa0cd353","resolution":{"observed_at":"2026-08-10T22:26:58.816009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.803133Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":"803db61b-3118-4e3c-acc8-7baa07b51faf","year":2016},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.306798Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:186e7fe6e2efd9e4e7c47d237c5fa7b13f06553666fcbe91b85015151c554394","observation_id":"826ac8f9-51b1-4e78-bc9e-beb16aa0f012","resolution":{"observed_at":"2026-08-10T22:26:58.806837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6596","last_updated":"2015-04-15T19:48:37Z","snapshot_observed_at":"2026-08-14T23:06:40.806094Z","submitted_at":"2014-12-20T04:11:33Z","title":"Training Deep Neural Networks on Noisy Labels with Bootstrapping","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6596","snapshot_observed_at":"2026-08-10T22:26:58.310538Z","title":"Training deep neural networks on noisy labels with bootstrapping,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.310538Z"},"links":{"cited_paper":"/paper/1412.6596","citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:f04854aae8854010cf5c6b0b36fa6bc669af3d9023c6ab5736b7c7cb9f7da007","observation_id":"69b2dfa8-b0fb-4c8d-9cbe-c09c56dce18e","resolution":{"observed_at":"2026-08-10T22:26:58.310538Z","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":"2026-08-10T22:26:58.791478Z","title":"Generalized cross entropy loss for training deep neural networks with noisy labels,","venue":null,"work_id":"7fc21b11-ede0-497d-82f9-85f4daad20bd","year":2018},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.314417Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:9d4af7241fac77dd4324667362d05134835956d2160e91cca667b78eb6364510","observation_id":"51b52c4f-4a41-4e4b-a30c-2481fe3db80f","resolution":{"observed_at":"2026-08-10T22:26:58.795297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.780927Z","title":"Symmetric cross entropy for robust learning with noisy labels,","venue":null,"work_id":"8618d928-492f-478a-be27-08383a76513c","year":2019},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.317923Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:be2df1db4c1ad48c5c877a1ba520baf00f6d3feaf3e1a53c2fc8bcfcc5827259","observation_id":"5ef40cd5-e4f8-42f2-9a90-261039906c2b","resolution":{"observed_at":"2026-08-10T22:26:58.784703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.770042Z","title":"L dmi: A novel information- theoretic loss function for training deep nets robust to label noise,","venue":null,"work_id":"e961dd59-2652-4cf1-81e7-c11ec13f0990","year":2019},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.321722Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:74ebb5c5bc01fdf1f84fa0975e22e7883a7c3e8ca5b4ef40fccc7d4ac1d0117d","observation_id":"bd8909ad-ff08-4e64-92f2-4a75f62ff695","resolution":{"observed_at":"2026-08-10T22:26:58.774186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.759697Z","title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels,","venue":null,"work_id":"b550605c-ece4-416f-b4e2-8b7bfbf3804a","year":2018},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.325452Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:1ab9d412355254da7415aec11cece9ae337fa77ea2d1161ffba231f8e9a7ddf5","observation_id":"2a5d5f73-2ac7-4047-86d1-07f17da2cdb8","resolution":{"observed_at":"2026-08-10T22:26:58.763271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.748523Z","title":"How does disagreement help generalization against label corruption?","venue":null,"work_id":"68d8d5d9-b26e-4859-a10d-6b4e675f8518","year":2019},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.329127Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:227028c317561facd94d7beb9f205201e14d4dce4082acae4fe31a48fe30d66e","observation_id":"f00879b4-3c22-49b6-b0b4-f6c4c4273361","resolution":{"observed_at":"2026-08-10T22:26:58.752639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.738445Z","title":"Robust early-learning: Hindering the memorization of noisy labels,","venue":null,"work_id":"1ca9458b-bae4-4eac-b140-2da614f66a68","year":2020},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.332927Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:26166a348008e235cf4774d7ad98b3f67fbfab6d6bd8705344277079f924c1cd","observation_id":"e60fa32f-4f05-4ff3-88fe-bff9612dd9e8","resolution":{"observed_at":"2026-08-10T22:26:58.741606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.728229Z","title":"Early- learning regularization prevents memorization of noisy labels,","venue":null,"work_id":"ef2f0ea1-fc6c-4051-9768-e40be0aa1e55","year":null},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.336557Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:264a9209f6b749a899ed4ba485164fe2281521ce748207d1920eb2b7a780e27f","observation_id":"5b1a8df6-18fb-4c1b-a6eb-1521bb13f12a","resolution":{"observed_at":"2026-08-10T22:26:58.731527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.717747Z","title":"Dividemix: Learning with noisy labels as semi-supervised learning,","venue":null,"work_id":"b145e291-fdfd-48ed-8c26-7aea7b49a386","year":2020},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.340400Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:ec1a4103a31be3a23e3dd1c24d394402f9beeb25295871fefb30683658b90170","observation_id":"66d2ca1e-ab97-4a18-bc15-c097fb16e180","resolution":{"observed_at":"2026-08-10T22:26:58.721764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.705176Z","title":"Understanding and improving early stopping for learning with noisy labels,","venue":null,"work_id":"41275b35-cba7-4ec2-beab-98bc4b4c6c4f","year":null},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.344058Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:9e0cffbe61368d34500ae0a2f1b0372df7c248a919104b52bf239c7aa486ba48","observation_id":"68a85159-27cd-4470-a0f1-3d17d8788a8d","resolution":{"observed_at":"2026-08-10T22:26:58.709744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.693852Z","title":"Fixmatch: Simplifying semi- supervised learning with consistency and confidence,","venue":null,"work_id":"6d061340-5951-4d5e-846f-e7c9495ebf91","year":2020},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.348162Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:8a7cbfb22afaea6c028eb6f7cc70b57b5c4fb13acd53df6075e7e9ab1ab1b47c","observation_id":"cb5777ac-42fb-4dac-b3c2-035d2280dfa3","resolution":{"observed_at":"2026-08-10T22:26:58.697539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.682916Z","title":"Exploiting spatial dimen- sions of latent in gan for real-time image editing,","venue":null,"work_id":"0be300b8-5d35-4515-a1ea-926480fae115","year":2021},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.351919Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:8ffba32b671af1c8432d3d871d5f40e1075898946e1d75ff2507d5900dc559e5","observation_id":"7b1377c9-cd00-41dc-972f-f9f668446d15","resolution":{"observed_at":"2026-08-10T22:26:58.686858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.672201Z","title":"Stargan v2: Diverse image synthesis for multiple domains,","venue":null,"work_id":"f59cfa89-de1c-438f-9651-7b96b57b2121","year":2020},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.355523Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:f68a28dca8444cedceceabc76fde74f2a6ec8ad5209c81d4df24fd7f4dc5e495","observation_id":"0f8ebfdc-aee7-4863-99a4-c9ab7a104b35","resolution":{"observed_at":"2026-08-10T22:26:58.676077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.661727Z","title":"Variational label enhancement,","venue":null,"work_id":"e3244dcf-7dc4-4a9c-85b7-1e9372d17def","year":2020},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.359192Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:f05fa96927681edd1f73ecb136ac0214b1669bbdae56279205e201b381f6ce25","observation_id":"3560d9c4-0c8d-4496-a607-84277cfd9ca1","resolution":{"observed_at":"2026-08-10T22:26:58.665193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.07159","last_updated":"2020-06-12T13:17:25Z","snapshot_observed_at":"2026-08-15T10:22:52.364884Z","submitted_at":"2020-06-12T13:17:25Z","title":"Are we done with ImageNet?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.07159","snapshot_observed_at":"2026-08-10T22:26:58.363303Z","title":"Are we done with imagenet?","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.363303Z"},"links":{"cited_paper":"/paper/2006.07159","citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:11315f35d110d13e91e553335c1ca5ccad548855ef503518b34d4fa725765209","observation_id":"26115eca-d13d-4b77-a579-f19d226b6155","resolution":{"observed_at":"2026-08-10T22:26:58.363303Z","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":"2026-08-10T22:26:58.650293Z","title":"From imagenet to image classification: Contextualizing progress on bench- marks,","venue":null,"work_id":"82d41820-c74a-4419-ae08-4d594eccccbf","year":2020},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.367107Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:0d0789654eb56da10008901a28b4cfd597e96af83b88d74afc4aad3d9f1477e7","observation_id":"0ab5f321-bcec-4a24-a5f7-b183a2fdf09e","resolution":{"observed_at":"2026-08-10T22:26:58.654097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.640215Z","title":"A data-centric approach for improving ambiguous labels with combined semi-supervised classifica- tion and clustering,","venue":null,"work_id":"f5283ae8-08fb-458b-aef7-5b91a4d4d1b3","year":2021},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.370819Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:001fe0f773748c472a3427e7266e5bc40766d7ba6b2c5bc7b3ea73d04b286016","observation_id":"f241f3ef-45dc-4dca-b1d0-4fe5484e45c6","resolution":{"observed_at":"2026-08-10T22:26:58.643548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.628761Z","title":"Binary classification with ambiguous training data,","venue":null,"work_id":"d513c7fb-a48a-4ce3-95e3-e7778f0370d9","year":2020},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.373981Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:a9031229d4f545f7a38c4c553e9f9b1c6edb06f89340860d5f110857b4118ca4","observation_id":"86437d81-3398-4db7-b6b5-517537a58458","resolution":{"observed_at":"2026-08-10T22:26:58.633292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.616228Z","title":"Learning from partial labels,","venue":null,"work_id":"99ee3d97-0040-4182-a353-8f0c45c3ebf0","year":2011},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.377030Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:84d6f71d20335fe5047cb381ce23b195394af09a9e79642932fe0abbf331d17c","observation_id":"9ecf7304-4c80-4d73-8e5a-0a2b76c93742","resolution":{"observed_at":"2026-08-10T22:26:58.620760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.602811Z","title":"Solving the partial label learning problem: An instance-based approach,","venue":null,"work_id":"46a9c13e-ef62-479b-a00a-6ef7f4e9ace3","year":2015},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.380136Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:12249136ba0d9e0db24a8d302a7db4eaf5c343f433afd2da7134713d7dac079d","observation_id":"4908635b-3474-4bda-90f9-fb10312e1776","resolution":{"observed_at":"2026-08-10T22:26:58.607422Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.590117Z","title":"Disambiguation-free partial label learning,","venue":null,"work_id":"9f4c4245-972c-4204-a046-b2ea8a8e6c27","year":2017},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.383139Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:cfb4d63f3bca638e002d27aaafa88e53a88e6549d2e716b74f1ae4f64dabb2ff","observation_id":"4dc8ad0e-80df-4fdc-8676-6f27791b46ec","resolution":{"observed_at":"2026-08-10T22:26:58.594580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02347","last_updated":"2021-03-22T22:01:05Z","snapshot_observed_at":"2026-08-14T13:49:34.933744Z","submitted_at":"2020-10-05T21:44:09Z","title":"Learning with Instance-Dependent Label Noise: A Sample Sieve Approach","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02347","snapshot_observed_at":"2026-08-10T22:26:58.386101Z","title":"Learning with instance-dependent label noise: A sample sieve approach,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.386101Z"},"links":{"cited_paper":"/paper/2010.02347","citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:739a3a030a28599ad04defc00a01a93b1e027475ddc9cd945e1941dcafdd3e08","observation_id":"005dbaf3-c932-4d83-8bf1-e899fea599c3","resolution":{"observed_at":"2026-08-10T22:26:58.386101Z","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":"2026-08-10T22:26:58.578232Z","title":"Part-dependent label noise: Towards instance-dependent label noise,","venue":null,"work_id":"9cdd2f3d-b927-4b44-8145-37c2e9088198","year":2020},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.391158Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:c6cc56a06a288ccf62036bce21f1e5363ded30e5eb5a218586a805f8f97a8726","observation_id":"d6f47e53-c059-4e73-a2c7-bdde2c215ab6","resolution":{"observed_at":"2026-08-10T22:26:58.582243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.566131Z","title":"Label distribution learning,","venue":null,"work_id":"d5250d57-bb4f-4d4e-b5e9-6b805e1a58b7","year":2016},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.394754Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:320b56ff1fc05db1c39fa672263ef7717cfd40c7e96ab60847efe7b3229e1405","observation_id":"5e0d2f99-0157-4cc9-ba28-dd091d19ff02","resolution":{"observed_at":"2026-08-10T22:26:58.570312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.553595Z","title":"When does label smoothing help?","venue":null,"work_id":"041a1fc8-4110-4a44-845c-5d31b1fdc92d","year":null},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.398626Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:4bd559445d3ee04a5ae37079ba891afbc238fddb666d1c100a6ac611021f21f2","observation_id":"cbbec5ce-26c2-4a1c-b2ce-623ea92d5e77","resolution":{"observed_at":"2026-08-10T22:26:58.557735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.04819","last_updated":"2021-03-17T19:43:43Z","snapshot_observed_at":"2026-08-14T21:57:46.879117Z","submitted_at":"2020-10-09T21:38:14Z","title":"How Does Mixup Help With Robustness and Generalization?","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.04819","snapshot_observed_at":"2026-08-10T22:26:58.402963Z","title":"How does mixup help with robustness and generalization?","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.402963Z"},"links":{"cited_paper":"/paper/2010.04819","citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:10c4fdcd522e66338dfd1186696e13d5b673eb4b72906f7abb5ddf43b1d254bd","observation_id":"74eb7099-9611-419f-8565-558fd20666d8","resolution":{"observed_at":"2026-08-10T22:26:58.402963Z","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":"2026-08-10T22:26:58.541063Z","title":"Each animal category in the dataset has its own distinct visual style, and the images were carefully curated and labeled to ensure high standards","venue":null,"work_id":"cc1fe8a0-6db4-4add-942e-f6d935115f82","year":null},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.407851Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:611ec4d37f824fe9835b1d16520420f65c932a302eb37136ac4e8aeeecd4124d","observation_id":"716bb8df-cfad-405a-8fdb-1497d6f1dc93","resolution":{"observed_at":"2026-08-10T22:26:58.545422Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.526053Z","title":"To perform local editing on AFHQ, we randomly pair images from the training set and select half-and-half masks that divide them equally into horizontal and vertical halves (see Fig","venue":null,"work_id":"a5d2c1fe-62dc-4c42-a7a8-f98bf2c90bcf","year":null},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.411597Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:85fb5aee67072ce838bb27a360cd77ac11c299dd0b5243757e84e5d31c240129","observation_id":"8d67d964-7f86-4cc5-b5f0-99219675faa4","resolution":{"observed_at":"2026-08-10T22:26:58.532005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-10T22:26:58.822467Z","title":"Available: https://openreview.net/forum?id=r1Ddp1-Rb 3","venue":null,"work_id":"24987568-e309-44be-ace2-9b57afcd510d","year":null},"citing_paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-10T22:26:58.297741Z"},"links":{"citing_paper":"/paper/2501.01844"},"observation_digest":"sha256:9d13b7a8c9f607b912c9468cf15106b5540ec26975700f4ac97e2c631a724457","observation_id":"9d3e0804-3cec-429f-98fa-7cf510883d83","resolution":{"observed_at":"2026-08-10T22:26:58.826078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.01844","last_updated":"2025-01-08T14:10:15Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T01:37:28.473630Z","submitted_at":"2025-01-03T14:54:49Z","title":"Learning from Ambiguous Data with Hard Labels"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":0,"verified_fuzzy":51},"total_outbound_references":58},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 0 inbound Pith citation observations for arXiv:2501.01844."}