{"as_of":"2026-08-10T17:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0fb8128a35de7c8637cdc7983019a3330f8c9f469ff5e9d477b272d1dc70e24e","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T01:41:47.188111Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.14607/citation-record","integrity":"/paper/2607.14607/integrity","json":"/paper/2607.14607/citation-record.json","paper":"/paper/2607.14607"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:42.441567Z","title":"Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:42.441567Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:be7067cd7b44b03c07b2642f98cbe859a239bd75f841e09e8476d5034228c9d0","observation_id":"2a645162-f59b-4456-9c02-f57f26179ef7","resolution":{"observed_at":"2026-08-02T01:41:42.441567Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:42.515087Z","title":"A reductions approach to fair classification","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:42.515087Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:b47b0fc86015d93907bc04c225c612a829dcc4b9c8615b14fca025ffdd4f04e6","observation_id":"8e4dfac0-2099-4361-96ae-f9852bc36eb7","resolution":{"observed_at":"2026-08-02T01:41:42.515087Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:42.547512Z","title":"Aithal and R","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:42.547512Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:e9a2df21ad044f267bdd84015d5a8333996b7e2814f0998ed42410b7888fd504","observation_id":"5dffd72c-46f6-460f-a638-649ed7529926","resolution":{"observed_at":"2026-08-02T01:41:42.547512Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:42.619525Z","title":"Evaluating marketing campaigns of banking using neural networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:42.619525Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:514c1ae7b8068b970650f4cda624f6fb63eaf3f728b33b74a01805a67972951d","observation_id":"9521c666-32c9-46b2-9a8a-81cee98cf28e","resolution":{"observed_at":"2026-08-02T01:41:42.619525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:42.750632Z","title":"Differential privacy has disparate impact on model accuracy","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:42.750632Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:3ff2a8fdb1c0b18261a1bd6395b0321a4efbcd416daaccc333c53b8947b01130","observation_id":"3fe57218-5dfe-41bb-b08b-2d5d6cb64230","resolution":{"observed_at":"2026-08-02T01:41:42.750632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:42.910404Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:42.910404Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:7041a32c2987a7f11aed23e8327a96a5f3cf20df9b09c64763abb363dd51d079","observation_id":"56312e5d-88eb-41d8-907d-6f2389f4b5a1","resolution":{"observed_at":"2026-08-02T01:41:42.910404Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.04321","last_updated":"2022-06-20T14:50:35Z","snapshot_observed_at":"2026-08-09T14:27:02.673281Z","submitted_at":"2022-05-09T14:25:24Z","title":"Evaluating the Fairness Impact of Differentially Private Synthetic Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.04321","snapshot_observed_at":"2026-08-02T01:41:43.037631Z","title":"Evaluating the fairness impact of differentially private synthetic data","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:43.037631Z"},"links":{"cited_paper":"/paper/2205.04321","citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:007d77ce3897a48bd12855394875854b2f7cd5bb1189182a816a8b25b4b19a18","observation_id":"e9271a22-e714-42d6-9109-0f60c2954a3b","resolution":{"observed_at":"2026-08-02T01:41:43.037631Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:43.143636Z","title":"Membership inference attacks from first principles","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:43.143636Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:f2829946b5476914f0acebe3a04d617c93c8bc66fe7d8c16264f868c4d3b181e","observation_id":"ed86f7bc-337d-4a25-8bb0-6b6621ad5aae","resolution":{"observed_at":"2026-08-02T01:41:43.143636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.03731","last_updated":"2021-04-07T05:43:22Z","snapshot_observed_at":"2026-08-04T12:30:44.028783Z","submitted_at":"2020-11-07T09:15:31Z","title":"On the Privacy Risks of Algorithmic Fairness","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.03731","snapshot_observed_at":"2026-08-02T01:41:43.264582Z","title":"On the privacy risks of algorithmic fairness","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:43.264582Z"},"links":{"cited_paper":"/paper/2011.03731","citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:76a57b4c5b1b83c013d019754b5be7477d3d713dc5b436f8a8092345384bcb9a","observation_id":"0adc0b74-03b7-49f8-99c1-d127bef59143","resolution":{"observed_at":"2026-08-02T01:41:43.264582Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:43.398936Z","title":"Chawla, Kevin W","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:43.398936Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:9bc95495ef14119cd9f449f904ce3a561822b8144a503601e19ee0e6f0879f06","observation_id":"7edf9aa8-cc6d-4b7b-9f9d-babd017d5d4f","resolution":{"observed_at":"2026-08-02T01:41:43.398936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:43.479450Z","title":"Residuals and influence in regression","venue":null,"work_id":null,"year":1982},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:43.479450Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:8007f4c0dbdbe3ee98f7e3b17a9d10c28aa9e84d262b63a125ce5e407abe4137","observation_id":"57a8027d-4ce1-47c8-8961-fe8249102841","resolution":{"observed_at":"2026-08-02T01:41:43.479450Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:43.576995Z","title":"The accuracy, fairness, and limits of predicting recidivism","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:43.576995Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:5d2a9caacd8b485959014a080d63da496afc754689fd7e6350acc9239c3f91fa","observation_id":"96f0abf6-ac50-40b8-97db-ec7551c4124d","resolution":{"observed_at":"2026-08-02T01:41:43.576995Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.12674","last_updated":"2021-10-27T05:33:38Z","snapshot_observed_at":"2026-08-08T16:02:43.512030Z","submitted_at":"2021-06-23T22:26:29Z","title":"Fairness via Representation Neutralization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.12674","snapshot_observed_at":"2026-08-02T01:41:43.644209Z","title":"Fairness via representation neutralization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:43.644209Z"},"links":{"cited_paper":"/paper/2106.12674","citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:275b222bddda05d5bace123371c5ad1447b64731b520b70b45bf47a29e9b3168","observation_id":"9895a2de-92ad-457b-b145-874c45381a54","resolution":{"observed_at":"2026-08-02T01:41:43.644209Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:43.735028Z","title":"Friedler, John Moeller, Carlos Scheidegger, and Suresh Venkatasubramanian","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:43.735028Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:7048adda9975e60485074c88c20e36a5ecf4a04ddcd1d5b0ed48861feb9839a8","observation_id":"04c5ec61-3eab-4099-b87c-82153dcb2828","resolution":{"observed_at":"2026-08-02T01:41:43.735028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:43.875153Z","title":"Does learning require memorization? a short tale about a long tail, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:43.875153Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:b1b7b4644b68dda154a4b5b59942de1e8ca69c5db47971965195e60a5ac6f6d1","observation_id":"4bf43eea-9901-4d22-83a9-9ccee3d468db","resolution":{"observed_at":"2026-08-02T01:41:43.875153Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:44.043551Z","title":"Whatneuralnetworks memorize and why: Discovering the long tail via influence estimation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:44.043551Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:856e1710c3e2f17ffd6b6db1b99cd19acab14f5e6b373c86f82efbb72385fe91","observation_id":"e2d4cab6-86cf-4a12-800d-62fd9da41d54","resolution":{"observed_at":"2026-08-02T01:41:44.043551Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:44.474166Z","title":"Differential privacy and fairness in deci- sions and learning tasks: A survey","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:44.474166Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:35c53f6ec151d4f380d5c0b31a5c9c33d33ed020d205fe8cc332c1a961273b1e","observation_id":"376a3656-c61c-4bc4-ac44-809a58d2cd5e","resolution":{"observed_at":"2026-08-02T01:41:44.474166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:44.646712Z","title":"Decision making with differential privacy under a fairness lens, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:44.646712Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:a667ba005bfedbce77996035905f08587fc2dd3c9e1ba84acbcf1e9bc2b105ee","observation_id":"24747e6f-cc29-45da-abc3-cb4ce8722340","resolution":{"observed_at":"2026-08-02T01:41:44.646712Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:44.869019Z","title":"Why do tree-based models still outperform deep learning on typical tabular data? In Advances in Neural Information Processing Systems, volume 35, pages 507–520, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:44.869019Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:2d6527a744a2afa4e41340396258eca7d14adc3b7bb2419e0a961805a6a3482c","observation_id":"081d9885-fe65-4c11-9ddc-f609a5376b73","resolution":{"observed_at":"2026-08-02T01:41:44.869019Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:45.043925Z","title":"Robuststatistics:theapproachbased on influence functions","venue":null,"work_id":null,"year":1986},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:45.043925Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:d9a73d8442c2850b1284e1382136f12ecc72336c2c1a363f5651741abe555f8b","observation_id":"fab21cf2-5e6c-48f4-9239-edda4176b22a","resolution":{"observed_at":"2026-08-02T01:41:45.043925Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:45.213060Z","title":"The impact of differential privacy on group disparity mitigation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:45.213060Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:6aad6c9d53f4e218a9d8e8fe5253e4a857d58785fd3301213a9a57a6a404cc3e","observation_id":"02820d12-bf72-4ccd-93a8-801b2e010cfb","resolution":{"observed_at":"2026-08-02T01:41:45.213060Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.02444","last_updated":"2019-07-04T15:08:38Z","snapshot_observed_at":"2026-08-03T01:28:19.280367Z","submitted_at":"2019-07-04T15:08:38Z","title":"Diffprivlib: The IBM Differential Privacy Library","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.02444","snapshot_observed_at":"2026-08-02T01:41:45.392505Z","title":"Diffprivlib: The ibm differential privacy library","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:45.392505Z"},"links":{"cited_paper":"/paper/1907.02444","citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:68ae59ddc88f1216a535bbb1f4e598b19326012b29cfbc03934a8fbf2bef6004","observation_id":"2a404d6d-2cb3-4b2a-a179-a099b285ce3e","resolution":{"observed_at":"2026-08-02T01:41:45.392505Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:45.539222Z","title":"Differentially private fair learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:45.539222Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:c2c97ebd527d3b6ed476eb32f10b1ac1cdeb7fe00f1a8137e5bb5e257fa93565","observation_id":"44469d99-a8f8-45f3-b171-714e059ab731","resolution":{"observed_at":"2026-08-02T01:41:45.539222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:45.597576Z","title":"Datapreprocessingtech- niques for classification without discrimination","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:45.597576Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:f6036f2c01edb1ccd556da0c85f28a0ea787579c14f7d485fd7317dd1cbef2af","observation_id":"5b6c2f5b-6b1f-4565-a36e-c78291a30b2b","resolution":{"observed_at":"2026-08-02T01:41:45.597576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:45.676475Z","title":"Understanding black- box predictions via influence functions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:45.676475Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:9638cb7bb90fb0f9e72fe05111c5a84b893009a75b002cf9f08a15410e6f9981","observation_id":"a83e6ca8-8a35-4374-9328-967aef063488","resolution":{"observed_at":"2026-08-02T01:41:45.676475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:45.779829Z","title":"Disparate vulnerability to membership inference attacks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:45.779829Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:35197708c0be86abc264afb56d7b4d39bd6c7ce5ce068a5c2621f83646b60ea7","observation_id":"61888f5c-4863-49b3-b948-5ddd0502b5bb","resolution":{"observed_at":"2026-08-02T01:41:45.779829Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:45.796125Z","title":"Arcolezi, and Catuscia Palamidessi","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:45.796125Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:8c58e8640b7f29f28d8c25ac20d0629195386177ae4e9011a0afa83da4bdebe2","observation_id":"448356cb-0c8b-4812-b4b1-1c285ab03bde","resolution":{"observed_at":"2026-08-02T01:41:45.796125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:45.861101Z","title":"Differential privacy has bounded impact on fairness in classification, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:45.861101Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:4de45d5f751fd114558d1c58619e9c60a136f595ed279d74aaddb97f03de62c9","observation_id":"e41c4d78-70ec-476e-ab0f-963e530bb33b","resolution":{"observed_at":"2026-08-02T01:41:45.861101Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.09339","last_updated":"2020-07-18T06:21:35Z","snapshot_observed_at":"2026-08-09T16:12:30.056905Z","submitted_at":"2020-07-18T06:21:35Z","title":"ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.09339","snapshot_observed_at":"2026-08-02T01:41:45.999306Z","title":"Ml pri- vacy meter: Aiding regulatory compliance by quantifying the privacy risks of machine learning","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:45.999306Z"},"links":{"cited_paper":"/paper/2007.09339","citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:96eb83876736ca05dae2ca5fe13378fc39bbda2e21f76b56fb5786a6cd961896","observation_id":"ecd1ff98-2e9b-41f3-9730-1ff843bf2942","resolution":{"observed_at":"2026-08-02T01:41:45.999306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:46.104586Z","title":"Increasing the views and reducing the depth in random forest","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:46.104586Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:cac3990bd71b2c0c4e348c67fa9f32482bb6ddcd12ccc767e7de74d821500203","observation_id":"0136a617-be9e-4b44-ac5a-e49942883f4a","resolution":{"observed_at":"2026-08-02T01:41:46.104586Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:46.215458Z","title":"A comprehensive sustainable framework for machine learning and artificial intelligence, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:46.215458Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:7761120f2a9c029e88d6617a504df6d268a9976e46a7450ae373cb41985a25d0","observation_id":"f6393eeb-7d44-4826-befc-ac6a9047f417","resolution":{"observed_at":"2026-08-02T01:41:46.215458Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:46.361478Z","title":"Weinberger","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:46.361478Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:acd9deb328aa1725e1ff844223d7ad3bdd3852c500c1980fb7bb81eebc55ea3d","observation_id":"0a50ebf8-d591-44e6-b6ac-39aaa27234db","resolution":{"observed_at":"2026-08-02T01:41:46.361478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:46.454536Z","title":"Understanding MachineLearning:FromTheorytoAlgorithms","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:46.454536Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:2992b946385b03a8888003324d539ff6bdbc5e965fbb56f36208f0e8b74f68b6","observation_id":"18429d41-7a43-4a7a-8f6e-5630df5a3fb1","resolution":{"observed_at":"2026-08-02T01:41:46.454536Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:46.576364Z","title":"When fairness meets pri- vacy: Exploring privacy threats in fair binary classifiers via membership inference attacks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:46.576364Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:894a2a9cca65552223a2ba1981fce1a87bdb8dec90bbac337c640ea9a6960e2b","observation_id":"7ef5218d-41be-46c1-a972-f7819ccce87b","resolution":{"observed_at":"2026-08-02T01:41:46.576364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:46.674550Z","title":"Dinh, and Ferdinando Fioretto","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:46.674550Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:b2b2bd0dbc2e20ebfc06d5c90359d82eef62a5d293bb69b3d4b327f1ba57d03e","observation_id":"df87a2a1-503b-423c-9ba1-c206e5e04be4","resolution":{"observed_at":"2026-08-02T01:41:46.674550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:46.778039Z","title":"Effectsofdifferentialprivacyanddataskewness on membership inference vulnerability","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:46.778039Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:d916a9874fb243c5c9a9c38008a7dbcccaf83cff9376fd0ffa8db7b6f8008b44","observation_id":"e514350c-6c8d-4262-b309-674080710ca8","resolution":{"observed_at":"2026-08-02T01:41:46.778039Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.00389","last_updated":"2021-09-16T19:21:39Z","snapshot_observed_at":"2026-08-09T07:34:31.417065Z","submitted_at":"2019-06-02T11:37:00Z","title":"Disparate Vulnerability to Membership Inference Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.00389","snapshot_observed_at":"2026-08-02T01:41:46.890920Z","title":"Disparate vulnerability: on the unfairness of privacy attacks against machine learning","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:46.890920Z"},"links":{"cited_paper":"/paper/1906.00389","citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:6ba02ec106d7523b3e152b946c543bc80fa0294786a9ff2e1ae3ebcdc46ea2b2","observation_id":"2505cd46-c9bc-4dfc-a75b-77daf1f31b2a","resolution":{"observed_at":"2026-08-02T01:41:46.890920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:46.973926Z","title":"Privacy risk in machine learning: Analyzing the connection to overfitting","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:46.973926Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:5cd1c366fa046fdd78d7fd700a7210efaf5f54077491bd154d1f67bfca823e0f","observation_id":"f998a0fa-13fc-40b8-b8dc-af9caebf2e5d","resolution":{"observed_at":"2026-08-02T01:41:46.973926Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:47.078229Z","title":"Understanding disparate effects of membership inference attacks and their countermeasures","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:47.078229Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:11ff2fa805d6e0ab364c5728f5d2698da898a7375d74fb319db2ad33687a640e","observation_id":"19d4da5f-0b2d-4529-a4c9-d58a63af72cf","resolution":{"observed_at":"2026-08-02T01:41:47.078229Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:47.188111Z","title":"On Improving Fairness of AI Models with Synthetic Minority Oversampling Techniques, pages 874–882","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:47.188111Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:06998dc11930e0f3aa124cf7e0980ac9e733d40c9bee68832b4f93c809b95c37","observation_id":"f0070d5c-e82a-425a-822c-a773080ab165","resolution":{"observed_at":"2026-08-02T01:41:47.188111Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:41:44.264022Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms","version":1},"reference_index":2891,"source":"pdf_text","source_observed_at":"2026-08-02T01:41:44.264022Z"},"links":{"citing_paper":"/paper/2607.14607"},"observation_digest":"sha256:841462c2beaca291987d447400f667d51ebe40a71cae0d99011b17d6cb1b16c3","observation_id":"4f4f9422-e7fb-4578-abd5-06952390e9d5","resolution":{"observed_at":"2026-08-02T01:41:44.264022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.14607","last_updated":"2026-07-16T06:10:42Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-02T01:41:40.688435Z","submitted_at":"2026-07-16T06:10:42Z","title":"Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":40,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":41},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2607.14607."}