{"as_of":"2026-08-10T02:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f7bc7264faa7fbc7895d783028b5679d270fa262220840eb5acb9031968020d5","coverage":[{"denominator":62,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":62,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T13:48:02.197292Z","state":"measured"},{"denominator":62,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":62,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2507.20284/citation-record","integrity":"/paper/2507.20284/integrity","json":"/paper/2507.20284/citation-record.json","paper":"/paper/2507.20284"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:48:10.421508Z","title":"A closer look at memorization in deep networks","venue":null,"work_id":"77270304-cbed-4045-b469-aac420e87bb8","year":null},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:56.570126Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:e6c9616710d147413e707d8fc53fff457d99d437e333fb6b745b3df6c0fe336e","observation_id":"7ca0e176-66f5-4191-b116-4fb90e56ae75","resolution":{"observed_at":"2026-08-06T13:48:10.593971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:10.278812Z","title":"Learning de-biased representations with biased representations","venue":null,"work_id":"45c1de15-d9ad-4adc-8dc5-a8f58c929856","year":2020},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:56.632188Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:d085ee6d90b62d8924c4912d6269160e5b8de367231c0dfe11f8d0b59a220807","observation_id":"7c2ef82a-cac6-41c5-8190-630099dcca3a","resolution":{"observed_at":"2026-08-06T13:48:10.330401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:09.984218Z","title":"Mitigating biases in blackbox feature extractors for image classification tasks","venue":null,"work_id":"3e2b7109-858b-4f1b-a0ce-9f85543e3c61","year":2025},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:56.697611Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:d3fe6a98ad08e8769bc8a5604db166a7616474e9a99af997f5593c49f6570db5","observation_id":"00f3b86e-0bc7-442c-be97-8537ba8482be","resolution":{"observed_at":"2026-08-06T13:48:10.091631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:09.607895Z","title":"indepen- dent components","venue":null,"work_id":"ba228973-2f13-45cd-a4a1-be29c6be1602","year":1997},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:56.762448Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:b75aff0492634e4663c0cc8923a17bb79bad347a12046a9bb6404dfc95a55af4","observation_id":"f44bf4c8-f4e1-41be-b7b2-47c2522aa2b3","resolution":{"observed_at":"2026-08-06T13:48:09.781966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:09.431361Z","title":"Al- gorithms for the matrix pth root","venue":null,"work_id":"3b59dde4-bcf3-48aa-bf8f-8202ad30f2a8","year":2005},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:56.849008Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:24118029d0c7c8a51004493abdcf27994bc528096465c3a374838df9e023eecc","observation_id":"4a90e4d8-68cd-4623-a206-31f7bf82cb88","resolution":{"observed_at":"2026-08-06T13:48:09.518369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:09.223027Z","title":"Rubi: Reducing unimodal biases for visual question answering","venue":null,"work_id":"2b0fc575-f304-4761-b7c8-2932ed90af1b","year":2019},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:56.925912Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:c568bf7b5e78c7f0c211a4f03d4f6a959b51606bd4b41ff05d25e637245ecfae","observation_id":"31a8bfac-df88-4957-ab63-229d923be9d7","resolution":{"observed_at":"2026-08-06T13:48:09.345783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:09.142081Z","title":"Building classifiers with independency constraints","venue":null,"work_id":"02105694-606a-41b5-a71e-b63250c4711a","year":2009},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:56.988323Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:2d6612ac30fadb1257523f34a1533ee15f56d89c0910091fb10d5f9f9c7f62bd","observation_id":"a13f3a82-4151-415a-a459-ac1cf0918bfa","resolution":{"observed_at":"2026-08-06T13:48:09.174135Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:09.012208Z","title":"Fast model debias with machine un- learning","venue":null,"work_id":"ffcec744-928b-4067-a03d-bf1c5babc7e8","year":2023},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:57.087565Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:9b533d55eaa3e9c5d7d2da71dc4f8888f476efbd8df86a28159e0eb8bf295fe0","observation_id":"b436a414-a19e-420e-8074-e955fe21d55a","resolution":{"observed_at":"2026-08-06T13:48:09.070515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:08.868837Z","title":"Better may not be fairer: A study on subgroup discrepancy in image classification","venue":null,"work_id":"005e1c74-108a-4164-929f-9d3d04be559e","year":2023},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:57.119089Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:efd66ad12b841b53c1a3400d3707e014c0e88781d1baab51cb03b0df9a51aaae","observation_id":"5763ccda-53fb-4c35-b794-b456ec76073a","resolution":{"observed_at":"2026-08-06T13:48:08.924735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:08.654773Z","title":"Improving generalization of batch whitening by convo- lutional unit optimization","venue":null,"work_id":"2d80146f-06ba-457d-8a74-c201cf286cf6","year":2021},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:57.203019Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:5fa209c82d86736f80552b2e09dadd10517227808e8eaa53df37062c98beaf5f","observation_id":"e9ced122-6136-40ba-bdae-d4c3f2de3934","resolution":{"observed_at":"2026-08-06T13:48:08.758457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:08.488872Z","title":"Flexibly fair representation learning by disentan- glement","venue":null,"work_id":"75c21d93-193b-4150-9540-f812a20a80de","year":2019},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:57.258739Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:bb312503e48d4ae9d87ef0a15be43e9e2f819e18dad90733577e636ef73389de","observation_id":"03d8dee3-c125-4970-b437-6d2cc6f0feff","resolution":{"observed_at":"2026-08-06T13:48:08.553590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:08.297700Z","title":"Cholesky factor- ization of matrices in parallel and ranking of graphs","venue":null,"work_id":"8d24d1d8-cbe9-4506-83e8-258a6c7e4b64","year":2003},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:57.261825Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:2756ff8db71909bc2cea262804dd36259b664c42f49bd2e38ae289f30f4096f3","observation_id":"1a017e73-0420-4ea0-a337-f40ebb702d03","resolution":{"observed_at":"2026-08-06T13:48:08.398096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:08.141074Z","title":"Whitening for self-supervised representation learning","venue":null,"work_id":"659756a2-0ae0-479d-a91b-d25184a00419","year":2021},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:57.339635Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:7d823dffba77ad0c7bab514466ef261c0b96f1551c64caa62b621900ce44de47","observation_id":"d0d32d2e-d839-494a-9bd3-639351194d94","resolution":{"observed_at":"2026-08-06T13:48:08.223622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.03184","last_updated":"2018-05-28T08:22:01Z","snapshot_observed_at":"2026-07-06T06:03:20.830767Z","submitted_at":"2017-10-09T16:39:31Z","title":"On Formalizing Fairness in Prediction with Machine Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.03184","snapshot_observed_at":"2026-08-06T13:47:57.495236Z","title":"On formalizing fair- ness in prediction with machine learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:57.495236Z"},"links":{"cited_paper":"/paper/1710.03184","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:79366c343b2757023347d18bfabd8a382b35fcfab4990774c24fbfd9a7c9c1f4","observation_id":"3569ba6a-7588-491f-804f-27faf866cc36","resolution":{"observed_at":"2026-08-06T13:47:57.495236Z","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":"2026-08-06T13:48:07.983217Z","title":"Equality of op- portunity in supervised learning","venue":null,"work_id":"b619817a-58bc-4b44-a8b0-5f0616bed2b4","year":2016},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:57.604990Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:938a25d2c7b1d0bd1b6873903db26e41160e753fe90bed48e54dd6ce4d39e9c5","observation_id":"3f29c7af-8648-44f2-8d61-68ffbcfb6069","resolution":{"observed_at":"2026-08-06T13:48:08.071643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:47:57.684759Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:57.684759Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:89d6f63f9a952de830cd670797504ff71fea1effc3aaebb9b1095f8d44635cbe","observation_id":"170877d0-c2d0-4c57-9c72-210aaea70f5b","resolution":{"observed_at":"2026-08-06T13:47:57.684759Z","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":"2026-08-06T13:48:07.814411Z","title":"Newton’s method for the matrix square root","venue":null,"work_id":"0887a1f2-4b4e-46c9-839b-fc03090a9202","year":1986},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:57.744029Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:4a273fc0ee346e1fef432d26ce3060cdc70700cf756b083cc4e02224417855a4","observation_id":"af8e3cc8-31bf-420d-91ba-722b445228ec","resolution":{"observed_at":"2026-08-06T13:48:07.889845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:07.694757Z","title":"Functions of matrices: theory and com- putation","venue":null,"work_id":"99115c33-ecd0-4e10-8bed-7ddb41fe6537","year":2008},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:57.840344Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:d09b5b2cfcb44f5eece7975d712e7243de1527db94daaa5aa640c70b16780386","observation_id":"8d933792-fbc1-4bb6-8823-55c11d82dfac","resolution":{"observed_at":"2026-08-06T13:48:07.740671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:07.581108Z","title":"Decorre- lated batch normalization","venue":null,"work_id":"b60e6294-b6de-4650-ba87-7b1560c26a33","year":2018},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:57.979977Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:63cc52c19d7d8d6afa37a4af3df9071c925f622e1d183b3f8ee597344c91db16","observation_id":"93c7eb69-98f2-446c-93f7-0ba3f2dd8cc4","resolution":{"observed_at":"2026-08-06T13:48:07.624832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:07.411728Z","title":"It- erative normalization: Beyond standardization towards ef- ficient whitening","venue":null,"work_id":"d5591848-766a-4d80-9573-81702b498adc","year":2019},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:58.056909Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:8b5c14bf01c51525817037c952e690846df511d8b74618e06b0d34f5f1187ccc","observation_id":"dcfe7250-89a0-4d99-9c49-2b0661720892","resolution":{"observed_at":"2026-08-06T13:48:07.483665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:07.290968Z","title":"An investigation into the stochasticity of batch whiten- ing","venue":null,"work_id":"fa39ac28-e365-40c0-8968-6d99769d2250","year":null},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:58.140797Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:acd6f502a3df7b6169ccc6c420f0a42c9232d188ecd633fc2cbe5cd6d4aae653","observation_id":"af316b58-3a08-4bd9-a46d-dbc7a741f723","resolution":{"observed_at":"2026-08-06T13:48:07.336848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:07.112172Z","title":"Selecmix: Debiased learning by mixing up contradicting pairs","venue":null,"work_id":"01534d79-4cad-464c-8c55-1c9ea44ee702","year":2022},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:58.208602Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:145aefe7340c5f196c25ae4506e05f06f5e4d8c6cd9f8d8b326034dc45370994","observation_id":"ebb080b4-ef96-480f-852d-017105a38416","resolution":{"observed_at":"2026-08-06T13:48:07.189770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:06.909846Z","title":"Neu- ral tangent kernel: Convergence and generalization in neural networks","venue":null,"work_id":"3c06c440-b38b-47ed-b76b-d428fdfcaaa0","year":2018},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:58.298235Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:3b55d514f07e8ecade22c2139ebc50c73becdc2b43066c02ab3d40837c4ba489","observation_id":"1eaf0b28-4be5-4ebc-a267-8ffc3207cf22","resolution":{"observed_at":"2026-08-06T13:48:07.005724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:06.760596Z","title":"Fair feature distillation for visual recognition","venue":null,"work_id":"41e26ea5-e130-4fbb-bdee-fecb8e3e3ea2","year":2021},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:58.413421Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:f612ce85702fb35ca6ba43c64bb0ab891149611515caa1543f950147d0707543","observation_id":"e6c2eacd-97a8-43c0-a686-c4c6191a8d3c","resolution":{"observed_at":"2026-08-06T13:48:06.824818Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:06.635719Z","title":"A style-based generator architecture for generative adversarial networks","venue":null,"work_id":"965f960b-3bc1-49cd-8dce-893a63f3090e","year":2019},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:58.525815Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:b0f2573d47d51ad4035b45ba42442cf41bc3f654c5d7e71e62ae8f0dfa7922d7","observation_id":"471c1acc-615a-4946-aa5c-da60f5232879","resolution":{"observed_at":"2026-08-06T13:48:06.686181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:06.491154Z","title":"Optimal whitening and decorrelation","venue":null,"work_id":"2aac9b51-30de-4f70-b16c-94c5086b877e","year":2018},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:58.599739Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:580a12958909030ef1841fe5b5d1141fcea2eb549dab5ad68261d88d34fb9f84","observation_id":"fee68d40-e92e-440d-9ecb-f51b2632e4c6","resolution":{"observed_at":"2026-08-06T13:48:06.555598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:47:58.717856Z","title":"Supervised contrastive learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:58.717856Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:bdd8f5ecfdd27c87dec44600bf811d8be587ef097cbe71c1cebd30b88b549705","observation_id":"ec68bc02-7020-4eaa-9c56-2e7b64188b21","resolution":{"observed_at":"2026-08-06T13:47:58.717856Z","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":"2026-08-06T13:48:06.316642Z","title":"Avoiding discrimination through causal reason- ing","venue":null,"work_id":"ac6fdd33-4293-4797-8f0a-7471aa55f708","year":null},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:58.832515Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:a3bfcbfa5a7048c9703f57d89095e4ab28dadfda00e7df35bcc62799950b805e","observation_id":"070284d2-829e-43c4-8170-547204fd37d1","resolution":{"observed_at":"2026-08-06T13:48:06.381147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:06.161838Z","title":"Learning not to learn: Training deep neural networks with biased data","venue":null,"work_id":"e07d376b-f6e6-4783-b18e-a66670ae16e0","year":2019},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:58.950185Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:9867ec2a39537389687c4a84987c22c912f63d087f9918f49ad1581c470d2deb","observation_id":"f23cc289-a0a4-40f5-a337-cfeaefae3a04","resolution":{"observed_at":"2026-08-06T13:48:06.247147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:06.001621Z","title":"Biaswap: Removing dataset bias with bias-tailored swapping augmen- tation","venue":null,"work_id":"633b93e0-e790-4d6b-bbe2-65206c5168ce","year":2021},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:59.073668Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:0dd55f6f31c52e966d6c0d3126ce9a28f3c1fe5db1f69bef71a2c38518996c25","observation_id":"a5a58abc-7b74-4a32-8713-b3153916817a","resolution":{"observed_at":"2026-08-06T13:48:06.064351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:05.875114Z","title":"Learning debiased classifier with biased committee","venue":null,"work_id":"354608eb-b4cd-416e-9039-fea87e6371cc","year":2022},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:59.192067Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:92df5446fd8a33c803e0710203fc3aaf609f036bfb25d8f6db7efb9acac54e08","observation_id":"7347bcb9-a624-4663-b35c-80e0616915ae","resolution":{"observed_at":"2026-08-06T13:48:05.929416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:05.736989Z","title":"Nlnl: Negative learning for noisy labels","venue":null,"work_id":"9139b815-b36d-44c9-afda-c25ea35a780e","year":2019},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:59.312494Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:fdf3b6404da2f25238fde7540e0995114a7d18d7ce6d3292e279bb8da45731a9","observation_id":"8f1fa0e3-b8a6-4cd1-898d-d36eed7bb836","resolution":{"observed_at":"2026-08-06T13:48:05.788236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.02937","last_updated":"2023-06-30T22:51:42Z","snapshot_observed_at":"2026-07-06T12:57:32.819460Z","submitted_at":"2022-04-06T16:55:41Z","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.02937","snapshot_observed_at":"2026-08-06T13:47:59.430756Z","title":"Last layer re-training is sufficient for robustness to spu- rious correlations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:59.430756Z"},"links":{"cited_paper":"/paper/2204.02937","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:d4e2d8f57d17c5123c098a67c12ebeb98bf14bbeb358fbd72746e48230abee3d","observation_id":"978a034f-fdfb-47d4-980d-96a225912dde","resolution":{"observed_at":"2026-08-06T13:47:59.430756Z","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":"2026-08-06T13:48:05.597111Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"8512532a-874a-4d66-be08-1013ad4cbbee","year":2009},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:59.560139Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:1fecfa3bf0de1103ad531ae04fea8ce3e90214392c24c220152956f4f9df5a67","observation_id":"81694c4b-e800-4cbf-a895-8c809ee1f885","resolution":{"observed_at":"2026-08-06T13:48:05.653427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.00165","last_updated":"2018-03-03T00:45:00Z","snapshot_observed_at":"2026-08-04T10:06:19.819372Z","submitted_at":"2017-11-01T02:13:25Z","title":"Deep Neural Networks as Gaussian Processes","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.00165","snapshot_observed_at":"2026-08-06T13:47:59.673166Z","title":"Deep neural networks as gaussian processes","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:59.673166Z"},"links":{"cited_paper":"/paper/1711.00165","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:65a28e0f9435e10e09bbc77da31354ecc4c5ff70b684ff12196fe333d36082f5","observation_id":"dbe9eb5f-b440-414d-8312-89e8d8f880e9","resolution":{"observed_at":"2026-08-06T13:47:59.673166Z","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":"2026-08-06T13:48:05.429225Z","title":"Learning debiased representation via disentan- gled feature augmentation","venue":null,"work_id":"eac88a2c-24fb-4142-a319-a7849c15ffd4","year":2021},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:59.794252Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:c7fc7338791a55c4c8d4139998517e3e4fb4c3e68b9eb109f4a5b0f929830f56","observation_id":"581a8e91-fc90-429b-a9db-155dc22fb61a","resolution":{"observed_at":"2026-08-06T13:48:05.507720Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:05.313016Z","title":"Just train twice: Improving group robustness without training group information","venue":null,"work_id":"9fa13e84-56f1-408c-87f8-5529d58488dc","year":2021},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T13:47:59.913895Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:e19480476ecc31802e75639f54f4c4447b57334c3e01225a002513577a615c8b","observation_id":"90bfb038-6d84-4883-9485-0c654cafd36c","resolution":{"observed_at":"2026-08-06T13:48:05.375960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:05.171695Z","title":"Deep learning face attributes in the wild","venue":null,"work_id":"6a43ef17-ad3c-4d42-90f3-6ef7bee29caf","year":2015},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:00.042703Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:d3bd0e3d514bf0bfa8b17381fc02b6cbfea52350a854030a8f4821d7790ea068","observation_id":"95458ac9-9f44-49ca-acb6-eb08a045c94f","resolution":{"observed_at":"2026-08-06T13:48:05.253730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:00.154089Z","title":"Deep learning face attributes in the wild","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:00.154089Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:ec9d006464fed27ed4182f6ef40e8c4c38c7e338ec92733595c14f83fc828631","observation_id":"e4fc013d-6bfe-46ed-be33-8375f7a198cf","resolution":{"observed_at":"2026-08-06T13:48:00.154089Z","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":"2026-08-06T13:48:05.001540Z","title":"Learning from failure: De-biasing classifier from biased classifier","venue":null,"work_id":"c5df65cc-446e-496d-b4a4-d4e6c7f4b64c","year":2020},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:00.246600Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:dbadc39734d495ff0b75b3f23d328619c3f6910b312568fbe6f9866b1af101d6","observation_id":"c1bcd991-f14e-4b01-8e8a-19ca6f9b727d","resolution":{"observed_at":"2026-08-06T13:48:05.072783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.02070","last_updated":"2022-04-05T09:08:30Z","snapshot_observed_at":"2026-07-06T12:56:53.043501Z","submitted_at":"2022-04-05T09:08:30Z","title":"Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.02070","snapshot_observed_at":"2026-08-06T13:48:00.371150Z","title":"Spread spurious attribute: Improving worst-group accu- racy with spurious attribute estimation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:00.371150Z"},"links":{"cited_paper":"/paper/2204.02070","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:fc77806da0c8e45228eec465662bc97483254a0bfe5b1fbbcafc64527603e72f","observation_id":"a8372626-5b49-4a77-a3e3-3f628cb69beb","resolution":{"observed_at":"2026-08-06T13:48:00.371150Z","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":"2026-08-06T13:48:04.872092Z","title":"Learning disentangled representation for fair facial attribute classification via fairness-aware information align- ment","venue":null,"work_id":"80d2c653-6876-48fb-81f2-bd6fb1f1446a","year":2021},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:00.452463Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:ef8d76c2d1772b9ea544718b5e41b379fa0e4c252576082adf4ded04417bfe5c","observation_id":"c2bca5f3-740e-4770-bc33-ec7a13ba188c","resolution":{"observed_at":"2026-08-06T13:48:04.940979Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:04.696505Z","title":"Fair contrastive learn- ing for facial attribute classification","venue":null,"work_id":"7a67376a-63e3-4a2b-89a7-bf6a5dcb7245","year":2022},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:00.537542Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:f03877db52bb56945d6bcc904cf7f153e716edafefc1162e4717735e5f574aa3","observation_id":"ee303cc6-02b9-483e-94b4-a912d43b2e7c","resolution":{"observed_at":"2026-08-06T13:48:04.794108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:04.501301Z","title":"Gradient reversal against discrimination: A fair neural network learning approach","venue":null,"work_id":"ad62c6b3-dccf-4a1d-9eb9-66a183310291","year":2018},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:00.638246Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:d02cd9ac72a9eff7b77e40270a7e1216b8ce618d60bc7b8fd8c40dd7de2ecdb2","observation_id":"a4027c32-b4c0-4440-8655-75e7a828a940","resolution":{"observed_at":"2026-08-06T13:48:04.610535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:04.345800Z","title":"Learning unbiased representations via mutual information backpropagation","venue":null,"work_id":"c1978e29-ff18-4e10-9a65-478dac982144","year":2021},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:00.726243Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:c9dd10c3781b1172681b7d2804c0617c6b1e7ddc059683425e6846a102627d4a","observation_id":"571b6534-4744-4459-a606-58a34c54c048","resolution":{"observed_at":"2026-08-06T13:48:04.420498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:04.112371Z","title":"why should i trust you?","venue":null,"work_id":"35af6bc2-413e-4b1f-9e59-e6f9f4f9f7d4","year":2016},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:00.819740Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:bfcd56bdeb8683e8bbe4d80fe5c5410415af6cbd21abfcfb23e147ca7d07e158","observation_id":"2201f7c2-b61a-43d3-8dcc-b23252cbd390","resolution":{"observed_at":"2026-08-06T13:48:04.223498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.01696","last_updated":"2021-06-02T14:55:19Z","snapshot_observed_at":"2026-07-06T10:20:13.545492Z","submitted_at":"2020-12-03T04:36:04Z","title":"FairBatch: Batch Selection for Model Fairness","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.01696","snapshot_observed_at":"2026-08-06T13:48:00.899803Z","title":"Fairbatch: Batch selection for model fairness","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:00.899803Z"},"links":{"cited_paper":"/paper/2012.01696","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:f83cdc6201596efa5b9d2c52a8f7eeb17c56019641e4d43d9e99a1157ac2b639","observation_id":"fadd4302-f934-447d-ae56-36a2da8b41b9","resolution":{"observed_at":"2026-08-06T13:48:00.899803Z","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":"2026-08-06T13:48:03.908052Z","title":"Unsuper- vised domain adaptation using feature-whitening and con- sensus loss","venue":null,"work_id":"c839ae58-39d4-4361-91b6-67832dc8f381","year":2019},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:00.970023Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:6c5d457c97ebb5fd3843a96876113172786b2cfbcdaa29bff344d11b2eba2949","observation_id":"70275d56-d9e6-44dc-a56a-17d5de7b408d","resolution":{"observed_at":"2026-08-06T13:48:04.008370Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.08731","last_updated":"2020-04-02T05:40:29Z","snapshot_observed_at":"2026-08-02T19:28:48.954133Z","submitted_at":"2019-11-20T06:43:41Z","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.08731","snapshot_observed_at":"2026-08-06T13:48:01.033514Z","title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst- case generalization","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:01.033514Z"},"links":{"cited_paper":"/paper/1911.08731","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:bbfadb5fed3e062c0207e1e79a674ad9b8f4b4931dff8b9731abb2fa25f6f89e","observation_id":"4f5768a1-8019-41a3-a243-8f3c319313ff","resolution":{"observed_at":"2026-08-06T13:48:01.033514Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03121","last_updated":"2022-01-10T01:19:31Z","snapshot_observed_at":"2026-08-09T20:41:41.108468Z","submitted_at":"2022-01-10T01:19:31Z","title":"Information-Theoretic Bias Reduction via Causal View of Spurious Correlation","version":1},"cited_work":{"arxiv_id":"2201.03121","doi":null,"metadata_source":"pith","pith_arxiv_id":"2201.03121","snapshot_observed_at":"2026-08-06T13:48:02.604594Z","title":"Information-Theoretic Bias Reduction via Causal View of Spurious Correlation","venue":"cs.LG","work_id":"1a5b4332-e455-4ebb-9293-2a8963fe3dec","year":2022},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:01.121547Z"},"links":{"cited_paper":"/paper/2201.03121","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:00223b5eababecb19e041caab9bc725662340ef6486e1f71e7c0dc15ba87daf6","observation_id":"210c57d0-10dc-4283-a264-e90f7de1ec61","resolution":{"observed_at":"2026-08-06T13:48:02.658792Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.00420","last_updated":"2019-02-25T23:19:40Z","snapshot_observed_at":"2026-07-06T06:42:30.989473Z","submitted_at":"2018-06-01T16:17:30Z","title":"Whitening and Coloring batch transform for GANs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00420","snapshot_observed_at":"2026-08-06T13:48:01.205273Z","title":"Whitening and coloring batch transform for gans","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:01.205273Z"},"links":{"cited_paper":"/paper/1806.00420","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:54d06b3b5bec19b23c96c7cd937d0f73ad70823c7382a2ff65ecc8e2250e4bd5","observation_id":"896755d1-894c-491f-8250-312cb5fc988e","resolution":{"observed_at":"2026-08-06T13:48:01.205273Z","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":"2026-08-06T13:48:03.652525Z","title":"End: Entangling and disentangling deep rep- resentations for bias correction","venue":null,"work_id":"a15e8c77-1534-44fe-93df-813b7bc1ef2b","year":2021},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:01.320507Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:7d4a56af9329c3c51d97de7c6bda1765921b09a11a2f36cda7f225a0f9fb0397","observation_id":"e700a0be-43c8-41c5-9212-f7138fb4d967","resolution":{"observed_at":"2026-08-06T13:48:03.758060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.06256","last_updated":"2019-03-02T00:42:03Z","snapshot_observed_at":"2026-08-07T22:06:28.029519Z","submitted_at":"2019-03-02T00:42:03Z","title":"Learning Robust Representations by Projecting Superficial Statistics Out","version":1},"cited_work":{"arxiv_id":"1903.06256","doi":null,"metadata_source":"pith","pith_arxiv_id":"1903.06256","snapshot_observed_at":"2026-08-06T13:48:02.448784Z","title":"Learning Robust Representations by Projecting Superficial Statistics Out","venue":"cs.CV","work_id":"39e5ac9c-41af-4dad-bb82-4e1be55a6900","year":2019},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:01.431289Z"},"links":{"cited_paper":"/paper/1903.06256","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:4889000758fa10d746eda2071b023032e84973800809340441eea15b6b2b64dc","observation_id":"d8005efd-ca53-4b96-ac41-2fde7a858591","resolution":{"observed_at":"2026-08-06T13:48:02.507638Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:03.496483Z","title":"Improving out-of-distribution robustness via selective augmentation","venue":null,"work_id":"acb3cf6c-9298-4b70-b0be-4637c7ee08de","year":null},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:01.535107Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:935a44a3299742f1e8e1ed5f7b46d390f7b439318b566a9733a9e7acff3586bb","observation_id":"7e289d76-7be7-4ccb-9dca-6c6700bac21d","resolution":{"observed_at":"2026-08-06T13:48:03.577841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.11926","last_updated":"2020-02-25T20:48:22Z","snapshot_observed_at":"2026-08-07T23:44:26.891400Z","submitted_at":"2019-05-28T16:38:34Z","title":"Network Deconvolution","version":4},"cited_work":{"arxiv_id":"1905.11926","doi":null,"metadata_source":"pith","pith_arxiv_id":"1905.11926","snapshot_observed_at":"2026-08-06T13:48:02.296785Z","title":"Network Deconvolution","venue":"cs.LG","work_id":"16da8447-1fe4-45dd-92cd-79d0d027c29b","year":2019},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:01.649641Z"},"links":{"cited_paper":"/paper/1905.11926","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:df6564f75a4412c802fd879eff194dce14d70bee1e911154656587ea8efb3c0a","observation_id":"c33905fe-ae21-484f-a832-02191badf8ac","resolution":{"observed_at":"2026-08-06T13:48:02.359372Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07146","last_updated":"2017-06-14T06:06:48Z","snapshot_observed_at":"2026-08-08T14:57:17.868613Z","submitted_at":"2016-05-23T19:27:13Z","title":"Wide Residual Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07146","snapshot_observed_at":"2026-08-06T13:48:01.732492Z","title":"Wide residual net- works","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:01.732492Z"},"links":{"cited_paper":"/paper/1605.07146","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:d81f5be5161bcaae5a0f8fec521537ce78b69cf7f6c66aa13ea3b6c47f3a1de0","observation_id":"d59c4ca7-4e92-4c9b-9bed-278657cf01a0","resolution":{"observed_at":"2026-08-06T13:48:01.732492Z","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":"2026-08-06T13:48:03.265456Z","title":"Mitigating unwanted biases with adversarial learning","venue":null,"work_id":"9ec00214-8045-4b5e-9442-db9adcf6fff8","year":2018},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:01.810528Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:f1a49cb6819d69a799865eb217844afee14133376b3fbab24742f0ddc3e1acae","observation_id":"35e0b98a-2f2a-4d39-91da-d4a6a4fe2a19","resolution":{"observed_at":"2026-08-06T13:48:03.396817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:03.112686Z","title":"Contrastive adapters for foundation model group robustness","venue":null,"work_id":"5dc52cfc-4cb2-4750-b1f9-96aa9c12ddc6","year":2022},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:01.854393Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:7fb9c05d5e248e8e1379a1301c540f9ee289a1e9d960789000d05f826c772b63","observation_id":"a66ce5d5-fd87-45fd-839b-eeda6facbf6e","resolution":{"observed_at":"2026-08-06T13:48:03.192680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.01517","last_updated":"2024-12-11T17:06:21Z","snapshot_observed_at":"2026-08-05T01:28:14.278352Z","submitted_at":"2022-03-03T05:03:28Z","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.01517","snapshot_observed_at":"2026-08-06T13:48:01.958398Z","title":"Correct-n-contrast: A contrastive approach for improving robustness to spurious correlations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:01.958398Z"},"links":{"cited_paper":"/paper/2203.01517","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:36ad8bda50c78f9c6d970084611cc9bcd8d96e303a40f6b2be89d0382a1afd31","observation_id":"6a9fa603-28ab-4560-ba98-7c14323759d4","resolution":{"observed_at":"2026-08-06T13:48:01.958398Z","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":"2026-08-06T13:48:02.963165Z","title":"Generalized cross entropy loss for training deep neural networks with noisy labels","venue":null,"work_id":"3c44c203-0d16-44bc-8b60-368bdc3b5bed","year":2018},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:02.053290Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:9226ccbfb4ad911d8e448d26635c9931624d8d8b6ca85e588477f93d53f0daed","observation_id":"0f282c90-806b-4a2d-8f47-7b3c96b85f8c","resolution":{"observed_at":"2026-08-06T13:48:03.021060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T13:48:02.810815Z","title":"Learning bias-invariant representation by cross-sample mutual information minimization","venue":null,"work_id":"7a45fd3a-4b42-4487-98be-a5ce7532386d","year":2021},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:02.118577Z"},"links":{"citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:0a25b22afeaffd33b836ab861ee270aedefd510b2136deaff98f4ba058fb738a","observation_id":"70a9266e-b5dd-4cca-aa49-ad8d573ed373","resolution":{"observed_at":"2026-08-06T13:48:02.854750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.06596","last_updated":"2017-05-25T18:15:06Z","snapshot_observed_at":"2026-07-06T05:19:23.158124Z","submitted_at":"2016-11-20T21:20:32Z","title":"Object Recognition with and without Objects","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.06596","snapshot_observed_at":"2026-08-06T13:48:02.197292Z","title":"Ob- ject recognition with and without objects","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T13:48:02.197292Z"},"links":{"cited_paper":"/paper/1611.06596","citing_paper":"/paper/2507.20284"},"observation_digest":"sha256:a17007fb73b99658447e3b1df9debed46b486e96adfd22b2148526820d209bde","observation_id":"3c334263-56c5-4ed9-b7b3-a55cecf4ae78","resolution":{"observed_at":"2026-08-06T13:48:02.197292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.20284","last_updated":"2025-07-27T14:01:30Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T19:48:59.211995Z","submitted_at":"2025-07-27T14:01:30Z","title":"Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation"},"reference_resolution":{"displayed":62,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":3,"verified_fuzzy":46},"total_outbound_references":62},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 0 inbound Pith citation observations for arXiv:2507.20284."}