{"as_of":"2026-08-14T00:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:43caf16238058d296b2f8a6eabaf1119b944a8f7c69f9e9a210da9d3c604fd63","coverage":[{"denominator":80,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":80,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:34:07.193449Z","state":"measured"},{"denominator":81,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":81,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-18T02:56:38.973027Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-18T03:00:48.667187Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"cited_work":{"arxiv_id":"2506.07861","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.07861","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fairness overfitting in machine learning: An information-theoretic per- spective","venue":null,"work_id":"a546aba5-b3ab-4b39-a069-a8c4d10a80e4","year":2025},"citing_paper":{"arxiv_id":"2510.26841","last_updated":"2026-04-29T15:16:42Z","snapshot_observed_at":"2026-08-12T16:18:11.693262Z","submitted_at":"2025-10-30T07:14:55Z","title":"FedPF: Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utility","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-18T02:56:38.973027Z"},"links":{"cited_paper":"/paper/2506.07861","citing_paper":"/paper/2510.26841"},"observation_digest":"sha256:c4e1dc362a3d0eba3bbeb315481af8be011621a5c14050a41cc5605d797cd53f","observation_id":"3e7b922b-83c1-496e-8973-adba57ab8a02","resolution":{"observed_at":"2026-05-18T03:00:48.669672Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.07861/citation-record","integrity":"/paper/2506.07861/integrity","json":"/paper/2506.07861/citation-record.json","paper":"/paper/2506.07861"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:34:08.459839Z","title":"A reductions approach to fair classification","venue":null,"work_id":"dec240ee-5cc2-481a-8dad-dad5dbee24e7","year":2018},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.854565Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:eb5cad2e38a93a05593c68b30965572a06b36e585d5a761ff9fa31eb0f4d2b3d","observation_id":"bc348029-597b-442f-b49f-82555e1b8edb","resolution":{"observed_at":"2026-08-07T05:34:08.464068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.446911Z","title":"Towards a unified theory of learning and information","venue":null,"work_id":"90911a03-a253-478a-84d7-4948ba8b3dad","year":2020},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.859940Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:9d7b6ac9f3ce2415fea1e739aae9141226ecd111834b3246558b77761c0608a4","observation_id":"029eeee9-15d3-4bd8-bfbc-f7e664edf157","resolution":{"observed_at":"2026-08-07T05:34:08.451375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.433615Z","title":"Beyond adult and compas: Fair multi-class prediction via information projection","venue":null,"work_id":"31f0658b-1c66-47c7-9c96-2eb03ea5dabd","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.864199Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:bc35d3c0fc517c1a7f3a5274f4766058239b1bbec69bb0170fec2b0936fec42d","observation_id":"35f63c7d-e409-451d-b693-e76ba7254895","resolution":{"observed_at":"2026-08-07T05:34:08.437924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.420724Z","title":"An exact characterization of the generalization error for the gibbs algorithm","venue":null,"work_id":"d5eba74b-39cd-4a78-a977-8253cce4ae4a","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.868357Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:1cf5ecb46aef10a62e99fdc3d5977c04784e4878a0e303258c40a32567663089","observation_id":"971215d3-da6b-4af5-8cfe-5dadb27ba837","resolution":{"observed_at":"2026-08-07T05:34:08.425073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.407852Z","title":"R 'enyi fair inference","venue":null,"work_id":"c0422c4a-3e48-49ef-991c-6a6759e9b04d","year":2020},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.872558Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:a8cfa39472d93db00cece30d10e1e6f5a6df9ccc15c0a190d1b347e48827fe63","observation_id":"ef1ad9a3-02d7-403c-a3b4-39cb2c47f6f5","resolution":{"observed_at":"2026-08-07T05:34:08.412060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.394505Z","title":"Fairness and machine learning","venue":null,"work_id":"b52f78f9-027e-4813-bc02-412f83064f96","year":2019},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.876877Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:74ee3746fe7442043dac5787e081395e4703c37261ba6d4fde4df0916200306d","observation_id":"e5bf7e93-777f-4bf4-9dbb-dc338eab5278","resolution":{"observed_at":"2026-08-07T05:34:08.398699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.381118Z","title":"and Mukherjee, S","venue":null,"work_id":"9cd35aa7-cac3-4487-88b6-473df38ecf58","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.881507Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:a1908bc58d52c5f887f775fbec6924dd4b26a58cced3ef555fd0ae5b670af558","observation_id":"67265029-3107-49ed-8f9b-68218c23d977","resolution":{"observed_at":"2026-08-07T05:34:08.385457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:06.885763Z","title":"Concentration Inequalities: A Nonasymptotic Theory of Independence","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.885763Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:534d160017e88c15f3e9cda62aa038ee1f7e60728f0db5ecbfc5a1febeec9a64","observation_id":"44ed69b7-55a4-4099-a6c2-d9977205bd81","resolution":{"observed_at":"2026-08-07T05:34:06.885763Z","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":"2026-08-07T05:34:08.368289Z","title":null,"venue":null,"work_id":"f1a5d588-8039-4b78-a4ba-637a99d2b8a0","year":2020},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.889613Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:455f9148ae5a7d3d5766cec7679513fcc2d1534df279d51e77cc0f1b92ab0db9","observation_id":"d84be9a5-29cd-4cd2-b2ef-7424e2820b4f","resolution":{"observed_at":"2026-08-07T05:34:08.372671Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.354807Z","title":null,"venue":null,"work_id":"5e64a41c-7bd3-4435-9cda-8176c44a9882","year":2017},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.893797Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:ca2d12881ef721707ba45f05791a2ddf59695fa502064953287019028b20d561","observation_id":"ecebbad2-66a9-47cf-90d3-00c013ff1e24","resolution":{"observed_at":"2026-08-07T05:34:08.359302Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.342048Z","title":"Generalization bounds for meta-learning: An information-theoretic analysis","venue":null,"work_id":"00072c9c-5dd8-4c8f-8b1a-1d5503d7ae1e","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.898018Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:a8e7af38fd210390dc67a905bcae105497cea54b8afb2d782d787da684dbf98f","observation_id":"df2f4d9b-7d0f-4360-8dfc-f4b7f641754a","resolution":{"observed_at":"2026-08-07T05:34:08.346297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.329227Z","title":"Fairness transferability subject to bounded distribution shift","venue":null,"work_id":"0f8c5cbc-e7df-4762-a616-ca95e60a68e5","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.902271Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:db6edb9a23b26f3e6296d95edc7746a43ec8e8ae213430619159109f2a46d711","observation_id":"788fa7ee-53f4-4475-9b39-807c48bebffe","resolution":{"observed_at":"2026-08-07T05:34:08.333392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.316725Z","title":"Fair prediction with disparate impact: A study of bias in recidivism prediction instruments","venue":null,"work_id":"5b303de1-dd51-46e7-9c6b-7449aafcd4e1","year":2017},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.906993Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:aff5f81b1c9a98106f42092f69832f693c05655c505f54efe57345561a839801","observation_id":"d294859b-8c9b-477a-a5e2-86e24059d87e","resolution":{"observed_at":"2026-08-07T05:34:08.320916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.303776Z","title":"Algorithmic decision making and the cost of fairness","venue":null,"work_id":"474c3887-8308-4d9f-8738-609c69823675","year":2017},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.912457Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:5bd218a3a3d33c770f3f18181ef2cfb73f0377a8a72ea0443ef44c658c563e07","observation_id":"407b4d68-9fd6-4469-b443-cf0c0575f19a","resolution":{"observed_at":"2026-08-07T05:34:08.308138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.291008Z","title":"N., Wei, D., Varshney, K","venue":null,"work_id":"55d71bd9-05e8-44b9-ac34-795558efe371","year":2019},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.916455Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:78cc558fd0d91add68d404bb68eb332e61d7572495442a5350b9e66ed8e810a5","observation_id":"95d0e56a-ea07-4262-b139-cbd76d0ac8e1","resolution":{"observed_at":"2026-08-07T05:34:08.295118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.278389Z","title":null,"venue":null,"work_id":"548aadbc-7c3e-4e61-ad73-50a84d995ff5","year":1999},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.920455Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:8f3f189aa796d8c10b4b63893884687d08ff2db48baf8a4140f239331bca6a40","observation_id":"21884f29-73bf-4bed-b139-301e8a0372b5","resolution":{"observed_at":"2026-08-07T05:34:08.282562Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.13642","last_updated":"2023-03-10T10:41:14Z","snapshot_observed_at":"2026-08-13T18:03:40.754750Z","submitted_at":"2021-09-28T12:00:26Z","title":"Fairness guarantee in multi-class classification","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.13642","snapshot_observed_at":"2026-08-07T05:34:06.924365Z","title":"Fairness guarantee in multi-class classification","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.924365Z"},"links":{"cited_paper":"/paper/2109.13642","citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:cb80052b579835dfbf67ebc03be74f6f1778771d7bd33ed62fcc24f2d641ad2e","observation_id":"0d75729d-7998-4bfa-8bfe-ffd6d5b1827e","resolution":{"observed_at":"2026-08-07T05:34:06.924365Z","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":"2026-08-07T05:34:08.264896Z","title":"Towards generalization beyond pointwise learning: A unified information-theoretic perspective","venue":null,"work_id":"cfb78048-65a8-4cf4-9f41-bf40a7f36245","year":2024},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.929047Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:248a3490fcbaef403a811ec044d16bd31d73cc3ce107725d6abcd2d9cec9817c","observation_id":"61566b88-a651-4362-a5e3-dac905965dc5","resolution":{"observed_at":"2026-08-07T05:34:08.269600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.251907Z","title":null,"venue":null,"work_id":"32ce5e02-0ba4-4adf-9d09-5429a2938268","year":1940},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.933007Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:a60f9cf0fecf12160b0db543fe90c4236f892daaf43939ffa45872e2b9cd7703","observation_id":"2aa5476b-bc36-48ad-bc5e-6881dac3c4d8","resolution":{"observed_at":"2026-08-07T05:34:08.256121Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.238515Z","title":"Fairness through awareness","venue":null,"work_id":"af439ce0-4d8d-49b4-90d8-dd91329a90e0","year":2012},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.937729Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:458ce6a655f217bab86de820d6fe1711376a4b6d1b976e5a40ddde46c4013d55","observation_id":"d8e9fa4d-7d0d-43ec-a959-8bb40d62abee","resolution":{"observed_at":"2026-08-07T05:34:08.242727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.225041Z","title":"Estimating mutual information for discrete-continuous mixtures","venue":null,"work_id":"56e9d687-e599-4ea2-8f8f-782bbfd192be","year":2017},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.941568Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:ddffc785f9b84819370c200fd0e69e80f8ca9090a419b3949ba53dc6d81029fa","observation_id":"c18c5f42-6641-4db7-8fa2-72158bd6d1fa","resolution":{"observed_at":"2026-08-07T05:34:08.229457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.211947Z","title":"C., Thomas, P","venue":null,"work_id":"1c6cc9ea-ce30-486c-b034-fba6a64ad138","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.945404Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:2c4f39cd294b8760d02911f6e2adf28623b64ee7ea9476075491ba492c26681f","observation_id":"b8911a41-cd51-41ed-9deb-def8c3fac5f4","resolution":{"observed_at":"2026-08-07T05:34:08.216222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.198662Z","title":"Learning fair representations via distance correlation minimization","venue":null,"work_id":"9c4fa462-ccb1-4017-a0d3-e2ffa1f6644b","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.949237Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:84fc9f67cc05b5c816b8c17931240fb7daebd38661d3c9cbe0b702bf0f946d51","observation_id":"3ad6a005-5e8e-4c82-a103-839ddbdb781a","resolution":{"observed_at":"2026-08-07T05:34:08.203287Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.04108","last_updated":"2021-06-03T17:21:06Z","snapshot_observed_at":"2026-08-10T22:52:07.700915Z","submitted_at":"2021-01-11T18:57:33Z","title":"Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation","version":3},"cited_work":{"arxiv_id":"2101.04108","doi":null,"metadata_source":"pith","pith_arxiv_id":"2101.04108","snapshot_observed_at":"2026-08-07T05:34:07.499875Z","title":"Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation","venue":"cs.LG","work_id":"31736bcb-a1fc-4e20-87a4-98ac86ffc958","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.953281Z"},"links":{"cited_paper":"/paper/2101.04108","citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:67b27fe1926229e0d6b39d7174e431b9ed319d276a6f00ef8216d81cc4172df3","observation_id":"3258d6a3-9448-4dfa-adb9-771002a15faa","resolution":{"observed_at":"2026-08-07T05:34:07.504683Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.185020Z","title":"Ffb: A fair fairness benchmark for in-processing group fairness methods","venue":null,"work_id":"c0640aca-c647-4cf5-9511-c36fe9d688e8","year":2024},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.957669Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:f07e57db783ede2f5535897c180e385400f1af181f84ab793b78876721b38692","observation_id":"e06b30eb-9f72-4ceb-b63c-48d7bb9e291d","resolution":{"observed_at":"2026-08-07T05:34:08.189539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.172127Z","title":"Equality of opportunity in supervised learning","venue":null,"work_id":"f658ae79-1a19-4ef9-a64c-36fb9bbb400d","year":2016},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.961640Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:588dcfb8bd07af53a2a53eaec46593f9bb1161ed330e3b875f9b134ba66bbd78","observation_id":"1f3aaa73-70fc-4b98-a212-6786cb60444d","resolution":{"observed_at":"2026-08-07T05:34:08.176369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.158677Z","title":"Information-theoretic generalization bounds for black-box learning algorithms","venue":null,"work_id":"34663318-190b-4b9d-b5db-22c2e1d2d847","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.969052Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:7cd007703fe9639e103c9978260e47a0f4944459c9fada320257b14b950c13a8","observation_id":"4ae3f9bb-ab99-4e44-bff9-b4d47545c9cb","resolution":{"observed_at":"2026-08-07T05:34:08.163449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.145266Z","title":"Nearly-tight vc-dimension bounds for piecewise linear neural networks","venue":null,"work_id":"cfc3d420-446d-4a67-b37c-3e896885317c","year":2017},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.973625Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:2bdabdb0a4119fbdc7170e1da9e175ca9dde5e2eed0972f20ac02d6196640960","observation_id":"e9e1067f-df42-41ee-b708-ece6d2d0ebac","resolution":{"observed_at":"2026-08-07T05:34:08.149655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.132346Z","title":"and Durisi, G","venue":null,"work_id":"6148518b-ecd3-4e76-969a-4959c4609c3f","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.977915Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:36add82d0befe25a1aba76bbb3e2b99f038021f464b8943391b19b6683a18180","observation_id":"773d1f46-a954-407d-a366-89319c039bc5","resolution":{"observed_at":"2026-08-07T05:34:08.136401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2412.00720","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:34:07.476265Z","title":"and Liu, H","venue":null,"work_id":"d82c4eff-705d-4aee-899f-b7658c579776","year":2024},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.982435Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:3f763761dae90917c6d3b5fd1afb6e43a11896d5868b619c0a0a9114f973cd1c","observation_id":"018f47ab-73c0-4b86-85fc-2fbb48c306a3","resolution":{"observed_at":"2026-08-07T05:34:07.483299Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.119369Z","title":"Wasserstein fair classification","venue":null,"work_id":"abfa38fe-cd28-4e47-9887-e693ba423719","year":2020},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.986740Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:d582bb60f9f169917d198b0b49217dd9ce77b5e3ddf663cd5183645603187508","observation_id":"94306bab-82ee-4168-a861-bb4485362534","resolution":{"observed_at":"2026-08-07T05:34:08.123478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.106542Z","title":null,"venue":null,"work_id":"fc6e6f27-2fb1-449c-bf52-1c073ece586a","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.990639Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:9222d6c09f1f7f316dca75b9d3f73110c5f97641e3ee7459a7a34514fd72a517","observation_id":"80bcc68f-2419-41cc-9875-9f23a471db75","resolution":{"observed_at":"2026-08-07T05:34:08.110575Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.093991Z","title":"and Calders, T","venue":null,"work_id":"1bdb2c60-749a-4a84-bbb3-885f03781b2b","year":2012},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.994681Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:5b5387106c635a996bec38258c71d604dc277480735fcbefccb7be3a3137318d","observation_id":"7e1d737c-bba2-4215-8f5c-227d08a3a5ef","resolution":{"observed_at":"2026-08-07T05:34:08.097891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.081347Z","title":"Fairness-aware classifier with prejudice remover regularizer","venue":null,"work_id":"3b015cac-3736-452e-9adc-c8232ff00097","year":2012},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:06.998868Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:19b517f2e65db3012371263b49d1384faec3dbb2f28c8d7516f0c9b7e5c5cb56","observation_id":"0afd6823-63f7-437c-88c8-3750b60b19ac","resolution":{"observed_at":"2026-08-07T05:34:08.085594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.05807","last_updated":"2016-11-17T16:41:21Z","snapshot_observed_at":"2026-08-07T03:32:58.857419Z","submitted_at":"2016-09-19T16:08:51Z","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.05807","snapshot_observed_at":"2026-08-07T05:34:07.003165Z","title":"Inherent trade-offs in the fair determination of risk scores","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.003165Z"},"links":{"cited_paper":"/paper/1609.05807","citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:97f2b580696f2c9e1bf64c49bcd6f47c6284a0afb63200def4b36376a71ed414","observation_id":"99e4f09a-84f5-48b2-a4ef-0451042646f0","resolution":{"observed_at":"2026-08-07T05:34:07.003165Z","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":"2026-08-07T05:34:08.068781Z","title":"and Becker, B","venue":null,"work_id":"790bdbea-fc4d-4791-95be-0a224b1e75b6","year":1996},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.008074Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:fb695b8ca989dd737e7df33034f934a80e9685928954175b223a0cdb6fc529ee","observation_id":"5d5d58f1-b439-4dfc-b6cd-1bc0ffc9bd62","resolution":{"observed_at":"2026-08-07T05:34:08.072699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.056010Z","title":"Estimating mutual information","venue":null,"work_id":"839fff84-8e28-4150-a02b-307ccd2099f7","year":2004},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.012115Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:4e4020a074327821868ed6300782375798128a315daed1f260a99131622e3fe6","observation_id":"aadacc58-3a04-43d4-8f63-545dd5fbb3e8","resolution":{"observed_at":"2026-08-07T05:34:08.060290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02904","last_updated":"2024-01-05T17:05:14Z","snapshot_observed_at":"2026-08-13T04:48:20.932870Z","submitted_at":"2024-01-05T17:05:14Z","title":"Class-wise Generalization Error: an Information-Theoretic Analysis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02904","snapshot_observed_at":"2026-08-07T05:34:07.016254Z","title":"Class-wise generalization error: an information-theoretic analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.016254Z"},"links":{"cited_paper":"/paper/2401.02904","citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:561046079a498141c81aa6917c978e5a3500693105864035d285116053d13c6c","observation_id":"8b282bce-84c0-402c-a0a4-2cf895af7b75","resolution":{"observed_at":"2026-08-07T05:34:07.016254Z","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":"2026-08-07T05:34:08.043296Z","title":"Propublica compas analysis—data and analysis for ‘machine bias.’","venue":null,"work_id":"6c58d4e7-3481-427a-8294-682d5483aa63","year":2016},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.020722Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:050171664ce3d39c80cc1e5970474ba3096aec165d119102cd87042fdcf32736","observation_id":"c4f09883-0fb3-4e52-9d79-bd9a617f32ab","resolution":{"observed_at":"2026-08-07T05:34:08.047513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.030436Z","title":"A maximal correlation approach to imposing fairness in machine learning","venue":null,"work_id":"e14618ed-d403-492c-ab58-5d96c6e90a54","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.024534Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:cacd5ddc033debecb7ed6f5b042dfa754046478b604ef33292d3e8cb81c4f8c1","observation_id":"55e22f3d-503c-4232-9a77-29385c85235a","resolution":{"observed_at":"2026-08-07T05:34:08.034723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.017172Z","title":"K., Bu, Y., Rajan, D., Sattigeri, P., Panda, R., Das, S., and Wornell, G","venue":null,"work_id":"1774c55a-f9ec-413f-af26-bfaa4737cc8f","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.028680Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:7918aec8010785146ad5ab9d02a83ab6519e9351d44d804894180bdfb6cc625d","observation_id":"ee377fd1-4a61-4dcc-9d46-ecd2f4828f45","resolution":{"observed_at":"2026-08-07T05:34:08.021273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:08.004469Z","title":"and Liu, H","venue":null,"work_id":"9bb71978-b51e-40cc-bd7c-d87b8e5c6d14","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.032779Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:2584e2d303112204af9bbc61fd11ca2bad7d3ef65c5902cc64545249c17300d0","observation_id":"b9540544-3a9b-439b-99fd-524420bc0b8e","resolution":{"observed_at":"2026-08-07T05:34:08.008644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.991191Z","title":"Kernel dependence regularizers and gaussian processes with applications to algorithmic fairness","venue":null,"work_id":"39328b87-8fdd-4cda-85bd-12a7cead3416","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.036663Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:e0ca5f4eea1a1d221ac38b4bcf9a93a631cf68c101b5280daa36653526b5b560","observation_id":"2e3e6642-53e5-4ca7-8d25-c34277309df4","resolution":{"observed_at":"2026-08-07T05:34:07.995534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.06309","last_updated":"2018-10-22T17:01:59Z","snapshot_observed_at":"2026-08-07T11:41:01.652912Z","submitted_at":"2018-02-17T23:38:29Z","title":"Learning Adversarially Fair and Transferable Representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.06309","snapshot_observed_at":"2026-08-07T05:34:07.040557Z","title":"Learning adversarially fair and transferable representations, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.040557Z"},"links":{"cited_paper":"/paper/1802.06309","citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:ecbf0702a8539a2d22f268455d8cbfe863e30c63897a8477a88ebb16f0efe762","observation_id":"297d6d3d-39a9-4ce7-9ed9-1e9c308df587","resolution":{"observed_at":"2026-08-07T05:34:07.040557Z","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":"2026-08-07T05:34:07.978064Z","title":"A survey on bias and fairness in machine learning","venue":null,"work_id":"3df47c78-a088-44a2-b5e6-68edf2f94add","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.044836Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:dfdc0bc85300f32355479016902a58d5c30c960f4dfffbb7406fadc85645b47e","observation_id":"51fa8acd-7173-481a-9d9c-8788a7640b1e","resolution":{"observed_at":"2026-08-07T05:34:07.982313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.964619Z","title":"and Vishnoi, N","venue":null,"work_id":"daefd1b1-5738-4d87-a239-fd2685546ebf","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.048890Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:c83782beb113be265f4405ce1d9ca8ec676b352f6b67689ba6b00bc48ee009b3","observation_id":"04e78758-bc08-40da-acfd-1987812562d6","resolution":{"observed_at":"2026-08-07T05:34:07.969071Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.951111Z","title":null,"venue":null,"work_id":"9794675b-b168-4f4a-bfef-f5873ea3be39","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.052854Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:1a2c4bd93bb22b87b71be68a34c74d0bcd11b2bba6211dd3b0b64a522bedbf9f","observation_id":"6e3b4cd7-a6e4-4706-912e-d98127089355","resolution":{"observed_at":"2026-08-07T05:34:07.955371Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.938758Z","title":null,"venue":null,"work_id":"c586f8c0-e9b4-43bc-a833-b7934777b286","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.056987Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:20b20c5f0db481ca69356e844f0ff936b7750c7a14ecf5f9c9b36ae24d4927a7","observation_id":"3f3ce011-0ced-4eb3-bae5-ebf34165d9e3","resolution":{"observed_at":"2026-08-07T05:34:07.942818Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.925322Z","title":"K., Haghifam, M., and Roy, D","venue":null,"work_id":"4cc7879f-8fc4-4a86-85e2-e064b2df812d","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.060780Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:ebfc1969d9a4fd788c9457313498fda4ae2a4835a2a177c726b6f06c80b1d90c","observation_id":"740c63a7-a9d3-40bb-98cd-a2e3355209db","resolution":{"observed_at":"2026-08-07T05:34:07.929571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.912279Z","title":"Learning fair and transferable representations with theoretical guarantees","venue":null,"work_id":"62ab87c6-5d57-43a4-ac17-9bf4146229d1","year":2020},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.064869Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:71dc792bba80fa0ab88317c78cd7074a264d5680ea8ce91d6ed69a9283052700","observation_id":"dcd67343-3d43-41f2-8c68-27365e99c2f9","resolution":{"observed_at":"2026-08-07T05:34:07.916367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.899153Z","title":"Randomized learning and generalization of fair and private classifiers: From pac-bayes to stability and differential privacy","venue":null,"work_id":"145dbe46-9811-4476-90f2-47b5a661e164","year":2020},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.068968Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:6588f662909416883f03e33179bf5b4014e5e9dc4a8027f199019b4d87538ce0","observation_id":"d432a6fb-77ca-4860-848a-69ede2d8e997","resolution":{"observed_at":"2026-08-07T05:34:07.903680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.886815Z","title":"and Shmueli, E","venue":null,"work_id":"4e745062-741e-44de-8b1e-1c4f48bed824","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.073140Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:298d5bdab7015a93e978821fac9d1a6b079b9495ffb2c2a880b02f4002381f3d","observation_id":"4d28b3ca-86bc-4390-8bda-21c4df5ba070","resolution":{"observed_at":"2026-08-07T05:34:07.890699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.873855Z","title":"Fairness and accuracy under domain generalization","venue":null,"work_id":"ed6b7783-8041-4149-8cbc-ad44a93ec09e","year":2023},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.077123Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:0b99785edfb731496b7bffb377c1ef5669830727678c4d210b358d0f8e452f3c","observation_id":"0be3f7d0-5774-4bfb-a0f2-30d5f5c46920","resolution":{"observed_at":"2026-08-07T05:34:07.878080Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.860866Z","title":null,"venue":null,"work_id":"98f735bf-3891-4c9c-8905-9186dea14f29","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.081175Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:3519b98a193ac5eb4d70f8c09ff4de8d607377331bff7e8a22ad1cf9f5122061","observation_id":"d5bb5fc0-9bc9-49ff-9502-231d86a7ae28","resolution":{"observed_at":"2026-08-07T05:34:07.865011Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.847660Z","title":"T., Durisi, G., and Simeone, O","venue":null,"work_id":"c9a20363-6a2a-4530-8bc7-75419c58527b","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.085203Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:f848678063594117817c4eb4821358216da6d4dd8456197bbb168c981d886cd5","observation_id":"299ef964-3a88-4b49-8b77-9539834ed3b5","resolution":{"observed_at":"2026-08-07T05:34:07.852182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.835008Z","title":"Tighter expected generalization error bounds via wasserstein distance","venue":null,"work_id":"051e7d44-9e59-43b3-981f-d6a38e71bde1","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.089432Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:74ac5350affb61e64189e64cc178987d078028122b76089b9b606a41525b8fd6","observation_id":"fb3a6599-d56f-4beb-967f-0b6312e6b056","resolution":{"observed_at":"2026-08-07T05:34:07.839188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.822310Z","title":null,"venue":null,"work_id":"1a6bc3f6-2c0b-4704-bc5a-5353cdb0036c","year":2014},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.093362Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:1ca7329d28580e8066fd0a6ae13721fd9a75601453ee113abf5df8c23a727889","observation_id":"dca845e4-bd8e-4d42-aa09-30deee395d8a","resolution":{"observed_at":"2026-08-07T05:34:07.826225Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.809689Z","title":"M., Pugnana, A., Turini, F., et al","venue":null,"work_id":"832c6800-c2c0-4abe-bee7-b63ee2db1d58","year":2023},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.097836Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:bba60b59758369e7871ce1018fc9eac98c8231899c87d1a7d7534b1279df3afe","observation_id":"05c85676-095f-491b-83e6-d2d551cc256d","resolution":{"observed_at":"2026-08-07T05:34:07.813713Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.09688","last_updated":"2019-11-14T21:50:20Z","snapshot_observed_at":"2026-08-08T16:57:08.917394Z","submitted_at":"2019-06-24T01:55:09Z","title":"Transfer of Machine Learning Fairness across Domains","version":3},"cited_work":{"arxiv_id":"1906.09688","doi":null,"metadata_source":"pith","pith_arxiv_id":"1906.09688","snapshot_observed_at":"2026-08-07T05:34:07.310522Z","title":"Transfer of Machine Learning Fairness across Domains","venue":"cs.LG","work_id":"7151b5bb-2223-4ba9-b8c7-ae988c51a26b","year":2019},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.101868Z"},"links":{"cited_paper":"/paper/1906.09688","citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:aaa094759ff142a3c954b35997ae57edc942f2cbb099127ff8ee055c3ec03264","observation_id":"0f4b0f5a-bad9-4fed-ab47-d67dc24102e1","resolution":{"observed_at":"2026-08-07T05:34:07.315379Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.797015Z","title":"K., Das, S., Panda, R., Sattigeri, P., and Wornell, G","venue":null,"work_id":"99560c76-2b39-4f42-beca-f5ca2b874501","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.106371Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:ac65d99e80ca8f42bc50dbe3a0cbc960fe341a2f976ca8b83e93878d317ee550","observation_id":"7b83fdf7-80b0-41eb-b5a1-6eff16243c8a","resolution":{"observed_at":"2026-08-07T05:34:07.801308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.783515Z","title":"Average individual fairness: Algorithms, generalization and experiments","venue":null,"work_id":"996fdb4f-673c-4224-a011-bf66b7046638","year":2019},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.110388Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:81f562ca1669c38ea7b2e6b324dcc050222206d6893df02f19f57e39e646b400","observation_id":"ee3f4243-5f33-43ce-ae2b-f40d1a485035","resolution":{"observed_at":"2026-08-07T05:34:07.788045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.15567","last_updated":"2020-07-30T16:19:59Z","snapshot_observed_at":"2026-08-09T07:50:46.596749Z","submitted_at":"2020-07-30T16:19:59Z","title":"Beyond $\\mathcal{H}$-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence","version":1},"cited_work":{"arxiv_id":"2007.15567","doi":null,"metadata_source":"pith","pith_arxiv_id":"2007.15567","snapshot_observed_at":"2026-08-07T05:34:07.291518Z","title":"Beyond $\\mathcal{H}$-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence","venue":"cs.LG","work_id":"60c83a73-ab6b-45c1-8e08-780661fb39f7","year":2020},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.114450Z"},"links":{"cited_paper":"/paper/2007.15567","citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:c596eb82e18cd2b45dd9cecaf1fb53c9c1ed446de6d9b3d44b633565be3f377f","observation_id":"5395e111-6261-4c4b-98a1-b704362b7d7f","resolution":{"observed_at":"2026-08-07T05:34:07.296344Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.770376Z","title":"X., Arbel, T., Wang, B., and Gagn \\'e , C","venue":null,"work_id":"242d6a36-e144-43a7-bc23-eab57969286c","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.118578Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:0ceb488fb8e388d868bddfe2d128df3e29d7f03588b84e34d0494f12ccaf259a","observation_id":"9e5f349e-279e-405c-9aee-755944982898","resolution":{"observed_at":"2026-08-07T05:34:07.774620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.757283Z","title":"Fairness violations and mitigation under covariate shift","venue":null,"work_id":"a52cb789-4814-48c8-950b-119a32a7a418","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.122771Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:d4f537e6f4b047a87f1cee1573f0c899a5654a04bfc25b16eaa0437d59bb56bd","observation_id":"1428c9e7-4a9d-4a44-a39a-949d8573f0d1","resolution":{"observed_at":"2026-08-07T05:34:07.761500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.744015Z","title":null,"venue":null,"work_id":"2faf262d-350b-46ac-8a62-c5a866cbf90a","year":1998},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.126705Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:181a34b3fd3a1488081c459d7ac80a8dd771ad4d881996d400bff3443fc5bfcf","observation_id":"78306ead-7542-4f6b-9bb3-1b97aee12324","resolution":{"observed_at":"2026-08-07T05:34:07.748345Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.729866Z","title":"and Zakynthinou, L","venue":null,"work_id":"765dd333-8cae-42d0-9c52-e68a1aa47099","year":2020},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.133264Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:1d4ff25db44bcf2f096c37609b87771274cd1bbe554986579126fb61c4d39289","observation_id":"cc08b785-b684-42d9-8a23-0b7a84603206","resolution":{"observed_at":"2026-08-07T05:34:07.734490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.716174Z","title":"and Zhang, K","venue":null,"work_id":"2a3541df-d4c7-4eb0-9318-0910fc729877","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.137374Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:5ed15c9466c40f17e3724f259413e22e536b3d1a46615421cf531e800d91ba5c","observation_id":"a5a48f48-fd50-4f4e-a71a-75c5608016cc","resolution":{"observed_at":"2026-08-07T05:34:07.720173Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.702473Z","title":null,"venue":null,"work_id":"e6a7c5b4-6712-43a5-99f2-65be9eb6b0ae","year":2023},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.141798Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:ff73fc5391b2d8fa46d4278b4507aa782543d13de8c6d6024c2a17d72d003bf9","observation_id":"4306e78f-d98f-4082-a6ca-5ce344ed0fff","resolution":{"observed_at":"2026-08-07T05:34:07.706446Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.03128","last_updated":"2022-03-19T15:11:05Z","snapshot_observed_at":"2026-08-09T10:13:58.086549Z","submitted_at":"2021-10-07T00:53:33Z","title":"On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications","version":2},"cited_work":{"arxiv_id":"2110.03128","doi":null,"metadata_source":"pith","pith_arxiv_id":"2110.03128","snapshot_observed_at":"2026-08-07T05:34:07.272255Z","title":"On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications","venue":"cs.LG","work_id":"6170cb14-051d-473a-a417-df44eaa2b85f","year":2021},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.145929Z"},"links":{"cited_paper":"/paper/2110.03128","citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:fefab89aa004c12a4d6e989e5d981fed01710d47e01ac38fc648afb1812f8da6","observation_id":"26b62803-5ad4-47d4-b176-711a628ac94e","resolution":{"observed_at":"2026-08-07T05:34:07.277171Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.02432","last_updated":"2023-06-15T05:46:14Z","snapshot_observed_at":"2026-08-13T12:50:38.362096Z","submitted_at":"2023-02-05T17:06:27Z","title":"Tighter Information-Theoretic Generalization Bounds from Supersamples","version":3},"cited_work":{"arxiv_id":"2302.02432","doi":null,"metadata_source":"pith","pith_arxiv_id":"2302.02432","snapshot_observed_at":"2026-08-07T05:34:07.252922Z","title":"Tighter Information-Theoretic Generalization Bounds from Supersamples","venue":"stat.ML","work_id":"b9a7c0d0-b6c0-4262-8a93-7acce201f062","year":2023},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.150255Z"},"links":{"cited_paper":"/paper/2302.02432","citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:fb718545f236feb0c69ba8ce2f9814e6d12892761092ffb9ec65d2ccfe09c049","observation_id":"dc115f9a-e853-41b8-b659-a7211a7bbcde","resolution":{"observed_at":"2026-08-07T05:34:07.257647Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.688769Z","title":"I., and Srebro, N","venue":null,"work_id":"751f36cc-e39d-4cbf-b2f6-99374ba5148b","year":1920},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.155970Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:1f5e611bd84f7fff30a9cb10f54e4b1485d47158eaf50e37ac48f70c374f563e","observation_id":"29b2360f-ea53-4033-a3a5-1a4fca4a7b11","resolution":{"observed_at":"2026-08-07T05:34:07.693378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.674528Z","title":"H., Aickelin, U., and Zhu, J","venue":null,"work_id":"52ad2371-fb20-48c0-babd-c42ac8e22ea8","year":2020},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.160141Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:0d24eaf850596a21c66c00256614e57d957406156be244c528981fce8c6df2cd","observation_id":"aca4c720-69a3-4a2e-b3d7-66f890ede65b","resolution":{"observed_at":"2026-08-07T05:34:07.679049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.660386Z","title":"H., Aickelin, U., and Zhu, J","venue":null,"work_id":"cdbe8908-274d-41c3-98e7-d096dde0d2ce","year":2024},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.164090Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:6dcf30731673f42e5edf0dc7eae2fc5de36362321c2d4b7adde7c0a0c5234be7","observation_id":"5c43352a-3827-4f6e-8650-b1e13a2e616a","resolution":{"observed_at":"2026-08-07T05:34:07.664636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.168601Z","title":"and Raginsky, M","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.168601Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:65f4753e693bb36abd62dea090049ddc10e17ad39099a00a24ee0ba16d4c7305","observation_id":"acb13403-24ed-4de2-a00d-91ff52c18ce5","resolution":{"observed_at":"2026-08-07T05:34:07.168601Z","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":"2026-08-07T05:34:07.637498Z","title":"Joint transfer of model knowledge and fairness over domains using wasserstein distance","venue":null,"work_id":"90221877-75e3-43e6-858d-f203539d404f","year":2020},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.172799Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:567bf4a6dab1d0e03d79979ecf43f7cea2d4ec99300c04dea03c7326a2be7ff9","observation_id":"21662b4a-129d-4eb1-9215-08e60b1b6eb1","resolution":{"observed_at":"2026-08-07T05:34:07.642463Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.624449Z","title":"B., Valera, I., Rogriguez, M","venue":null,"work_id":"6d370260-c5ee-4f99-a5d6-7797360cc453","year":2017},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.176880Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:7563b83c10d3d94082859d93b8a2d77d058a4176c23c4bb396551a4a925ca8d5","observation_id":"ee0f74ce-6425-4070-a8d2-ffa40edb8c85","resolution":{"observed_at":"2026-08-07T05:34:07.628631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.610646Z","title":"Learning fair representations","venue":null,"work_id":"f7d81ce6-287f-452c-92a3-c64b0966dfcb","year":2013},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.181018Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:1a2c0fbd330d5012e4adea9e33f0f795ba8146cafd77368e8e5632f3ede22e0b","observation_id":"37464eb4-6783-49a5-8c55-387f0ddd1a73","resolution":{"observed_at":"2026-08-07T05:34:07.615259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.595991Z","title":"Individually conditional individual mutual information bound on generalization error","venue":null,"work_id":"5c33d874-3f24-41e9-abcd-259773ccc270","year":2022},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.185071Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:6625809e4b08587b29479c489629e70fe008711ccdd5db6a0d8e3ab4dddddc70","observation_id":"8ded4634-5a3c-4e39-ab43-ce8db658a1c0","resolution":{"observed_at":"2026-08-07T05:34:07.600609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.00876","last_updated":"2023-11-13T04:40:26Z","snapshot_observed_at":"2026-08-13T11:51:58.680673Z","submitted_at":"2023-05-01T15:22:58Z","title":"Exactly Tight Information-Theoretic Generalization Error Bound for the Quadratic Gaussian Problem","version":2},"cited_work":{"arxiv_id":"2305.00876","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.00876","snapshot_observed_at":"2026-08-07T05:34:07.230964Z","title":"Exactly Tight Information-Theoretic Generalization Error Bound for the Quadratic Gaussian Problem","venue":"cs.IT","work_id":"1c4b8fe1-6f77-4064-9c51-255f4082cffc","year":2023},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.189316Z"},"links":{"cited_paper":"/paper/2305.00876","citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:ef27ba6a8ddef721e13309af1e15eaa4d9f996c6b912802c2294598be7af4eaf","observation_id":"3b6248b8-4172-47b3-a803-c2401ed9670f","resolution":{"observed_at":"2026-08-07T05:34:07.237565Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T05:34:07.193449Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-07T05:34:07.193449Z"},"links":{"citing_paper":"/paper/2506.07861"},"observation_digest":"sha256:19453447a723d5a96cf8e729feaa56f5984e48e9a162fdddbca16249a1a3ef97","observation_id":"07d14fd9-db4a-4f96-a6b7-3092e799ed0f","resolution":{"observed_at":"2026-08-07T05:34:07.193449Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.07861","last_updated":"2025-06-09T15:24:56Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T11:41:37.841338Z","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective"},"reference_resolution":{"displayed":80,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":18,"verified_exact":6,"verified_fuzzy":55},"total_outbound_references":80},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 80 of 80 outbound references and 1 inbound Pith citation observation for arXiv:2506.07861."}