{"as_of":"2026-08-19T04:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ee71c473ea5b7594a232a402ad1f3e91eaff06703b7b885c7c1c6fe54d9928db","coverage":[{"denominator":81,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":81,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:47:04.620273Z","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":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.10194/citation-record","integrity":"/paper/2507.10194/integrity","json":"/paper/2507.10194/citation-record.json","paper":"/paper/2507.10194"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:47:03.961275Z","title":"Deep learning with differential privacy","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:03.961275Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:ac00854d77c1f6dc6ce97994abd985a800b619286c376c2bb342589969780e98","observation_id":"a11416cd-5ce2-4f8a-bff1-ec8ff6768df4","resolution":{"observed_at":"2026-08-06T17:47:03.961275Z","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":"2026-08-06T17:47:05.790618Z","title":"Where- fore art thou r3579x?: anonymized social networks, hidden patterns, and structural steganography","venue":null,"work_id":"c4dfac09-8a17-4a1d-bb85-ca01a73224c7","year":2007},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.023205Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:146a7e7671543d45b8140aaa649783e11d0dd1e1cbda57286de4ecc88dabb0c2","observation_id":"68e20585-0fb3-40aa-a19b-9701e1228930","resolution":{"observed_at":"2026-08-06T17:47:05.795204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.777107Z","title":null,"venue":null,"work_id":"85fc2ee5-e72b-4893-96e9-796e1fc7253d","year":2014},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.055854Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:a2e8fa4706c4dca2d8753c43b1ed4d3707b68639f70ebbc6e3acdb1546f2fc7e","observation_id":"d969fa3d-cc70-4285-9dae-2515e9ec3bd6","resolution":{"observed_at":"2026-08-06T17:47:05.781142Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.763612Z","title":"Federated disentangled representation learning for unsupervised brain anomaly detection","venue":null,"work_id":"cc9b58ad-787e-4d96-ac7f-710d083f9c06","year":2022},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.121648Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:efe389113be68dfaa2a204ab520e96f1b3cca722b0acacf36d2b6244d028118f","observation_id":"b0883275-130a-4831-9293-c1e453daa44a","resolution":{"observed_at":"2026-08-06T17:47:05.768802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.750412Z","title":"Multi-level variational autoencoder: Learning disentangled representations from grouped observations","venue":null,"work_id":"e3fad0be-e102-4321-a952-679b3a964962","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.186280Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:2d5e5304ed1dc99ee901e51dcef383a5779ff9a85f210664564fcef12d50d849","observation_id":"6587968a-b459-4e0f-8f5e-7b0328dae9be","resolution":{"observed_at":"2026-08-06T17:47:05.754624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.737289Z","title":null,"venue":null,"work_id":"fe4865ba-7e01-4239-92d7-0ab68a82693d","year":2018},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.246197Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:aa325af4c034d0b1e4a1f83fe2b85b8d5b785bba223a0ddf74d1196c1845736f","observation_id":"4ae79230-2cf8-42c1-b4d9-4cc38a1f178d","resolution":{"observed_at":"2026-08-06T17:47:05.741254Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.02589","last_updated":"2019-06-06T13:56:24Z","snapshot_observed_at":"2026-08-14T16:19:49.961195Z","submitted_at":"2019-06-06T13:56:24Z","title":"Flexibly Fair Representation Learning by Disentanglement","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.02589","snapshot_observed_at":"2026-08-06T17:47:04.275357Z","title":"Flexibly fair representation learning by dis- entanglement","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.275357Z"},"links":{"cited_paper":"/paper/1906.02589","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:be9972c73cebfe00edddb3fdccec7d0219fd92397335e7e1e39697c27f0923c5","observation_id":"2b950937-b89f-4bda-8ca9-3f9886007d2c","resolution":{"observed_at":"2026-08-06T17:47:04.275357Z","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":"2026-08-06T17:47:05.724204Z","title":"Unsupervised learn- ing of disentangled representations from video","venue":null,"work_id":"86062c09-c1f4-493a-ae07-1f18e6ff1a22","year":2017},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.317596Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:acffc8820c11980a88a35ab1c74724c95e0a7634c998eb546cd49bfc7e89482d","observation_id":"1183f31c-c122-4318-9d47-b4b5e194eb7c","resolution":{"observed_at":"2026-08-06T17:47:05.728333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.710533Z","title":"Guided variational autoencoder for disentanglement learning","venue":null,"work_id":"b595616b-278b-41c2-bf4e-f2cf0754e98c","year":2020},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.333687Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:efe8a9c0ec5fedfb57ad53d38485f0542f0cae521a9f25b5cfd621fd04513d12","observation_id":"cf76f567-8934-4aa7-a561-0e0a6c42eb04","resolution":{"observed_at":"2026-08-06T17:47:05.715102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.697270Z","title":"Im- proving zero-shot learning by mitigating the hubness prob- lem, 2014","venue":null,"work_id":"5fea8433-bfcd-473d-98e3-8fc2c84a18d6","year":2014},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.337735Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:dc6e76cbfd2e5a7227c228718f094bd2fc32d19b2b35769dd14948a89a6d9038","observation_id":"d0aab52e-6a17-436b-97ae-4f3f1bb88273","resolution":{"observed_at":"2026-08-06T17:47:05.701376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.682588Z","title":"Uci machine learning reposi- tory, 2017","venue":null,"work_id":"78d69a0a-0be5-4108-8557-a1207268052e","year":2017},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.341707Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:ef806d052dc09e7900fee4b6dbd9b1a688d109f4f497198ea5e5c5cc88f28ca0","observation_id":"e2c1db39-6530-42df-841b-214ca7762ce3","resolution":{"observed_at":"2026-08-06T17:47:05.688045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.667761Z","title":"Privacy-preserving image features via adversarial affine subspace embeddings","venue":null,"work_id":"93500331-65e2-4c14-ad98-ab3bba4a2a83","year":2021},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.346151Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:acc955e9266c6f170f538b6326e2aac99b47132b232a38e9af6da7313cca8aa9","observation_id":"4da579da-81b7-46de-8dc3-1e68c9741b3b","resolution":{"observed_at":"2026-08-06T17:47:05.672383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.653784Z","title":"Differential privacy","venue":null,"work_id":"b72c0164-5c26-41d2-a16d-bcde0d7280f1","year":2006},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.350474Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:5b0389f8668497eacfc3a4c2d347c311e2860b59ad4109b18a078e71cf068f58","observation_id":"5571b180-e665-4442-83f9-eb3ec9b72549","resolution":{"observed_at":"2026-08-06T17:47:05.657976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.640540Z","title":"Exposed! a survey of attacks on private data","venue":null,"work_id":"aa9a105f-3110-42a8-a154-0157e9d37789","year":2017},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.355041Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:abdb64e530e549453c9db3f70ba11751049bc6f7d1d6257de2d401d94a7ce568","observation_id":"7ec32a53-2da5-4932-8ff7-03096c5ab7ea","resolution":{"observed_at":"2026-08-06T17:47:05.644938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.09386","last_updated":"2018-02-26T15:14:51Z","snapshot_observed_at":"2026-08-14T19:42:06.840697Z","submitted_at":"2018-02-26T15:14:51Z","title":"Learning Anonymized Representations with Adversarial Neural Networks","version":1},"cited_work":{"arxiv_id":"1802.09386","doi":null,"metadata_source":"pith","pith_arxiv_id":"1802.09386","snapshot_observed_at":"2026-08-06T17:47:04.833436Z","title":"Learning Anonymized Representations with Adversarial Neural Networks","venue":"stat.ML","work_id":"2be1ab45-4542-475a-8187-c8d13850b32f","year":2018},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.359033Z"},"links":{"cited_paper":"/paper/1802.09386","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:7e1306c8bd893e61c253a30dee77e57f4cf82c6842482f811ebb5f246165ac26","observation_id":"270da044-4564-4559-816f-92876aeccd91","resolution":{"observed_at":"2026-08-06T17:47:04.837611Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.626990Z","title":"Demystifying inter-class disentanglement","venue":null,"work_id":"856fec43-41ef-46e7-af7e-3c25b1a237b5","year":2020},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.363084Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:f5faaba3d7c07289eb54329e73f54258273f664d70de89c8f62b49324f1a18e0","observation_id":"d4ca2c66-8bb9-47c8-81c0-316084d3c9ab","resolution":{"observed_at":"2026-08-06T17:47:05.631527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.7495","last_updated":"2015-02-27T14:54:37Z","snapshot_observed_at":"2026-08-14T23:18:01.026650Z","submitted_at":"2014-09-26T08:22:21Z","title":"Unsupervised Domain Adaptation by Backpropagation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.7495","snapshot_observed_at":"2026-08-06T17:47:04.367123Z","title":"Unsupervised domain adaptation by backpropagation","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.367123Z"},"links":{"cited_paper":"/paper/1409.7495","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:a4c20ecce77fbbf431e56f0d61a83872eb7520f0498f5c487e2665fb76e1f7cd","observation_id":"3d61890e-a2fa-47e0-869c-84639bbc3f0c","resolution":{"observed_at":"2026-08-06T17:47:04.367123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1712.07557","last_updated":"2018-03-01T10:12:27Z","snapshot_observed_at":"2026-08-16T10:57:46.215293Z","submitted_at":"2017-12-20T16:28:37Z","title":"Differentially Private Federated Learning: A Client Level Perspective","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.07557","snapshot_observed_at":"2026-08-06T17:47:04.371565Z","title":"Differentially private federated learning: A client level perspective","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.371565Z"},"links":{"cited_paper":"/paper/1712.07557","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:05fd0cca26cb7093c70e7cb5fce805a5780546b54e6ad21bb2de6f15c443d841","observation_id":"ee14e768-f366-417b-9fde-256510f1806a","resolution":{"observed_at":"2026-08-06T17:47:04.371565Z","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":"2026-08-06T17:47:05.614290Z","title":"Jointly de- biasing face recognition and demographic attribute estima- tion","venue":null,"work_id":"751a1c3f-3a2d-4429-8ae0-182baaec264b","year":2020},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.376184Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:eb4c08190a1470dcf0b75f5aea486092af358efe951f1d7694967e4a568ed404","observation_id":"11678143-0199-4f70-8d95-5409a8639acf","resolution":{"observed_at":"2026-08-06T17:47:05.618607Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.600712Z","title":"Ms-celeb-1m: A dataset and benchmark for large-scale face recognition","venue":null,"work_id":"07db10be-367f-4957-89a7-01a32140360f","year":2016},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.379895Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:729511170fa1972de01c82877a841b1a9ebdddd7d55182c5ca70739b97f922e8","observation_id":"0bee20be-cb3a-4b2f-a39a-ccf129c9a6c4","resolution":{"observed_at":"2026-08-06T17:47:05.605328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.585902Z","title":"Minimax filter: Learning to preserve privacy from inference attacks","venue":null,"work_id":"a9c7a31e-e318-4c35-8beb-58e96f28dd93","year":2017},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.383950Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:d662e34e73672014ff286d921b144f15d561c5c8dd6c027b4d8237362693275d","observation_id":"6dd39ca5-7cdf-4cba-9664-926f0488f471","resolution":{"observed_at":"2026-08-06T17:47:05.590509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.572283Z","title":"Equality of op- portunity in supervised learning","venue":null,"work_id":"53b00946-c25f-46cd-b8df-2754e4ed8150","year":2016},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.387769Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:621c63f792becd74a9a89397593398121a288b23802775be73068d9d728aa651","observation_id":"8db9cb7b-0d57-437d-88ec-c6f8da5da2ff","resolution":{"observed_at":"2026-08-06T17:47:05.577010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.557936Z","title":"Disentangling factors of variation with cycle- consistent variational auto-encoders","venue":null,"work_id":"f89023c6-b34f-4907-ac11-1731e9ad16a9","year":2018},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.391650Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:0e7cea2c06d1352953e86db1e9972777bc092e5aeaccace8a518f67eb5b077d5","observation_id":"52cfd11e-0436-481f-bd2a-3d3946afba8a","resolution":{"observed_at":"2026-08-06T17:47:05.563011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.543881Z","title":"Deep Residual Learning for Image Recognition","venue":null,"work_id":"2b5ef0f5-686a-4525-8684-29de6889dfe5","year":2016},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.395418Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:8825f680c7c70ad4428652edb8c1ead8573e6b950e78c7d7800b594fef80c6a3","observation_id":"a1156aa2-6d25-4d01-9a47-c08531c3965b","resolution":{"observed_at":"2026-08-06T17:47:05.548765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.530356Z","title":"beta-V AE: Learning basic visual con- cepts with a constrained variational framework","venue":null,"work_id":"cae62be6-4729-4902-92d6-592c2b4c1306","year":2017},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.399602Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:d0aa8c81062f5d310398681fb67d1c05f661abd4c584d46c8215f7ce6db9674e","observation_id":"156b05fd-9e54-4cfc-90b4-fa9c8d1b26da","resolution":{"observed_at":"2026-08-06T17:47:05.534801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.516897Z","title":"Fades: Fair disentanglement with sensitive relevance","venue":null,"work_id":"d95db045-384f-4eeb-9124-85c1d76d3ffd","year":2024},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.403438Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:e620dcc802194e24a7c10adbb15ad926411c9fc868019c715420f91fbed4c414","observation_id":"cad214c7-6394-48a2-be43-996bb401bf35","resolution":{"observed_at":"2026-08-06T17:47:05.521239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.502992Z","title":"Noisy adversarial representation learning for effective and efficient image obfuscation","venue":null,"work_id":"eafc1351-b763-48eb-8418-3a14fb512f9d","year":2023},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.407795Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:749329debbd860bcae233aecea8674a5691f27cfefef70077916702fe1cfc3f4","observation_id":"00a97ad9-2724-46c8-9072-50ffb92f2385","resolution":{"observed_at":"2026-08-06T17:47:05.507415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.04087","last_updated":"2020-11-13T19:00:09Z","snapshot_observed_at":"2026-08-18T22:03:53.759400Z","submitted_at":"2019-09-09T18:17:10Z","title":"Privacy-Net: An Adversarial Approach for Identity-Obfuscated Segmentation of Medical Images","version":3},"cited_work":{"arxiv_id":"1909.04087","doi":null,"metadata_source":"pith","pith_arxiv_id":"1909.04087","snapshot_observed_at":"2026-08-06T17:47:04.785221Z","title":"Privacy-Net: An Adversarial Approach for Identity-Obfuscated Segmentation of Medical Images","venue":"eess.IV","work_id":"759a1bb4-3c66-4771-95ac-c9f540f77a50","year":2019},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.412066Z"},"links":{"cited_paper":"/paper/1909.04087","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:9335c6f89bc31fe80d973a925eec7e2ea079fb39a58458085e70d001659d4ffb","observation_id":"131b5ba8-2cfc-404c-8874-b202aada41ef","resolution":{"observed_at":"2026-08-06T17:47:04.789435Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-08-14T23:50:45.029465Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-06T17:47:04.416240Z","title":"Auto-encoding varia- tional bayes, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.416240Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:976eb24f36df531ed4929eba41be6d90db4fbf1be52ec4bd654f6119ff274d47","observation_id":"6deca337-ab96-4120-8e77-ec5cf9406891","resolution":{"observed_at":"2026-08-06T17:47:04.416240Z","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":"2026-08-06T17:47:05.488341Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"e97ac3b2-4d88-4798-8566-da544273df87","year":2009},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.420969Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:90503914dbb4edee3a02d1dfbc00690655c136b57795c5fc2174ce50652afca1","observation_id":"446a163f-f40c-4606-a898-a495667bd6b5","resolution":{"observed_at":"2026-08-06T17:47:05.493800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.474267Z","title":"Con- struction of an off-centered entropy for supervised learning","venue":null,"work_id":"5ac06965-ca62-4706-b893-07548f78d65e","year":2007},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.425047Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:597e3be3531c7242f3894d04c0b63360ff872c0f55becfc1d6e78b36a9e55075","observation_id":"5818c5d7-f922-41e9-a1b3-dd2c86fc1ae1","resolution":{"observed_at":"2026-08-06T17:47:05.478904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.04126","last_updated":"2021-05-06T02:46:26Z","snapshot_observed_at":"2026-08-13T00:48:46.310288Z","submitted_at":"2019-09-09T19:57:01Z","title":"DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones","version":2},"cited_work":{"arxiv_id":"1909.04126","doi":null,"metadata_source":"pith","pith_arxiv_id":"1909.04126","snapshot_observed_at":"2026-08-06T17:47:04.752354Z","title":"DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones","venue":"cs.CR","work_id":"10aefead-dc69-4aa5-add4-29e448ab3c63","year":2019},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.429405Z"},"links":{"cited_paper":"/paper/1909.04126","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:3c596a39e28c3960b3abf32cc8a5763867a300685384a1b0774e1a96fa5620e7","observation_id":"b6c23ee3-ff7f-453a-a37f-fbe5683dcccd","resolution":{"observed_at":"2026-08-06T17:47:04.756681Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.460104Z","title":"Fair representation learning: An alternative to mutual information","venue":null,"work_id":"a997488c-6bb1-4a9f-b00f-afd3d3464ab5","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.433430Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:3e37a025fede8b20533ac9f2b69278312d570b7b2e15ab503f532a3bbdbf4fcc","observation_id":"5143366e-bd09-4b14-8fff-5744f7cf2b0e","resolution":{"observed_at":"2026-08-06T17:47:05.465116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.431991Z","title":"Fair transfer learning with factor variational auto-encoder","venue":null,"work_id":"70da82b0-6b3f-4fd4-babc-780edb1b1fad","year":2022},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.442210Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:8d97ff2c9552b4f09050a62af25f85ddab6ae5cd027f429efa9f4f714e1007f4","observation_id":"2bbb8076-2adb-414f-ab60-f4efff56aef2","resolution":{"observed_at":"2026-08-06T17:47:05.436573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.417839Z","title":"Exploring disentangled feature rep- resentation beyond face identification","venue":null,"work_id":"855275b5-442e-4612-b137-32beb21e4884","year":2018},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.446109Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:e8247e3112cdb8e77737c6d7494dbcf3636a2ebc3aee31afe1170f2adcbc801f","observation_id":"781f1db7-8656-4a66-bfab-42c4e19c3dc1","resolution":{"observed_at":"2026-08-06T17:47:05.422487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.404176Z","title":"On the fairness of disentangled representations","venue":null,"work_id":"13459055-3ec5-4b15-8a99-78a37b1bb662","year":2019},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.450387Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:eb052dc84bfd3f01442ea8ad89919316d5c7d1a56c8be6b6ea8a9b20a33dd9e1","observation_id":"4d796bf8-1a94-4b24-925a-ac1e4f28645a","resolution":{"observed_at":"2026-08-06T17:47:05.408330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1511.00830","last_updated":"2017-08-10T03:07:31Z","snapshot_observed_at":"2026-08-14T22:25:06.246618Z","submitted_at":"2015-11-03T09:27:49Z","title":"The Variational Fair Autoencoder","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.00830","snapshot_observed_at":"2026-08-06T17:47:04.454107Z","title":"The variational fair autoencoder","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.454107Z"},"links":{"cited_paper":"/paper/1511.00830","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:07401e72798c9e018812f572c0089e508483f44180c3d67232cab37ff4bcfa6f","observation_id":"736b6cad-1be0-48ce-8bc9-713fd19832be","resolution":{"observed_at":"2026-08-06T17:47:04.454107Z","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":"2026-08-06T17:47:05.390227Z","title":"The variational fair autoencoder, 2017","venue":null,"work_id":"07950af7-d537-4c82-9543-3fc1ce9cb2e5","year":2017},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.458264Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:e45343ff40fa8a4e2a3018777ebdb3e2138627530d1bb1964b8fd77541b97f9f","observation_id":"7505af35-0c9a-4c6c-a73c-122662474bd0","resolution":{"observed_at":"2026-08-06T17:47:05.395040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.06309","last_updated":"2018-10-22T17:01:59Z","snapshot_observed_at":"2026-08-14T19:44:53.780083Z","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":"2026-08-06T17:47:04.461885Z","title":"Learning adversarially fair and transferable represen- tations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.461885Z"},"links":{"cited_paper":"/paper/1802.06309","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:b307a08eeb23f49afbe5cbaf10a0f16daa7a11af3ee4129039e41cddcde13bba","observation_id":"89066fee-ef82-4de0-9b74-1112d212a457","resolution":{"observed_at":"2026-08-06T17:47:04.461885Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1602.05629","last_updated":"2023-01-26T22:54:08Z","snapshot_observed_at":"2026-08-17T13:07:20.583520Z","submitted_at":"2016-02-17T23:40:56Z","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.05629","snapshot_observed_at":"2026-08-06T17:47:04.465790Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.465790Z"},"links":{"cited_paper":"/paper/1602.05629","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:6e6b0d00cbe689d13a1f090dead369ccd97c122d00c4206281edd3060db0f162","observation_id":"f106be87-9049-4259-9c21-a5bcee2aaef1","resolution":{"observed_at":"2026-08-06T17:47:04.465790Z","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":"2026-08-06T17:47:05.374624Z","title":"Privacy–enhancing face biometrics: A com- prehensive survey.IEEE Transactions on Information Foren- sics and Security, 16:4147–4183, 2021","venue":null,"work_id":"049cb845-ecdd-46cb-93e4-6b755e566aff","year":2021},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.470117Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:2453fbf19e5e1e187076030154cbe963b3f81f7019b832afcdca0b27173b0525","observation_id":"090127bf-42a8-4397-8695-161dfe699337","resolution":{"observed_at":"2026-08-06T17:47:05.380192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"cs/0610105","last_updated":"2007-11-22T05:13:06Z","snapshot_observed_at":"2026-08-15T10:59:52.480746Z","submitted_at":"2006-10-18T06:03:41Z","title":"How To Break Anonymity of the Netflix Prize Dataset","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"cs/0610105","snapshot_observed_at":"2026-08-06T17:47:04.474201Z","title":"How to break anonymity of the netflix prize dataset","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.474201Z"},"links":{"cited_paper":"/paper/cs/0610105","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:8117b78d7cc468b625332d2003236aebc8847d7c93b923dcc4718167b07a322a","observation_id":"cb314db6-31f7-4070-ac5a-584bb9e0a3a7","resolution":{"observed_at":"2026-08-06T17:47:04.474201Z","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":"2026-08-06T17:47:05.359724Z","title":"Panda: Unsupervised learning of parts and appearances in the feature maps of GANs","venue":null,"work_id":"474711a1-9ae9-4dea-87aa-728798657c19","year":2023},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.478075Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:4175a85f036786bfc658c5af24d335e6db420ca0e4ac79489e2d598c64a2c7fc","observation_id":"89d2fbf0-b466-4cd2-861c-fafb15c50900","resolution":{"observed_at":"2026-08-06T17:47:05.364522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.01727","last_updated":"2017-10-11T20:26:15Z","snapshot_observed_at":"2026-08-14T20:26:46.528617Z","submitted_at":"2017-10-04T19:15:32Z","title":"Privacy-Preserving Deep Inference for Rich User Data on The Cloud","version":3},"cited_work":{"arxiv_id":"1710.01727","doi":null,"metadata_source":"pith","pith_arxiv_id":"1710.01727","snapshot_observed_at":"2026-08-06T17:47:04.677110Z","title":"Privacy-Preserving Deep Inference for Rich User Data on The Cloud","venue":"cs.CV","work_id":"d2c1e747-d8fc-4af2-99ce-fd053b06864c","year":2017},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.481657Z"},"links":{"cited_paper":"/paper/1710.01727","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:ed95148f3c34845767964e97ddd73810f7f362795933c1ef1850788932925f71","observation_id":"8d0667c0-32cd-4509-a5e5-6e85f2543d90","resolution":{"observed_at":"2026-08-06T17:47:04.681695Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.344590Z","title":"Deep private-feature extraction","venue":null,"work_id":"19e090a8-aa90-4fd5-9314-33c8fcd6103b","year":2018},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.485450Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:ece29b804e1ba41aa745bd093d14b8bfd14e22023f33d349ab0d3bffa60dbafe","observation_id":"294e5230-6667-4bac-b3b9-a426c3a44e99","resolution":{"observed_at":"2026-08-06T17:47:05.349111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.329032Z","title":"Learning privacy preserving encodings through adversarial training","venue":null,"work_id":"2d9e7a25-d09b-41ed-ab2c-594a4d24152b","year":2019},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.489234Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:25f37641aa6ab5ee133a1f151ada5ff71fc76e3cc4b61a3638d51669136ed682","observation_id":"53979623-d96a-4573-9824-17686907b57a","resolution":{"observed_at":"2026-08-06T17:47:05.334275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.314150Z","title":"Discovering fair representations in the data domain","venue":null,"work_id":"beb30f51-9f6f-47c4-8268-7b6881b95587","year":2019},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.492798Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:458db35492fec89b8493778db49eb9ca532c3b41ea9e3a9be0558cb7ecf9db0f","observation_id":"90116fbc-524c-41a4-af4f-e566d701e256","resolution":{"observed_at":"2026-08-06T17:47:05.318815Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.298933Z","title":"Hubs in space: Popular nearest neighbors in high- dimensional data","venue":null,"work_id":"d37bca28-d6e8-44c1-a418-a24bd2253814","year":2010},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.496674Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:5ccd6c01fb865e821a5f0dcd216b1eb93c0feb93076a6e8b08c883ddf6d236ce","observation_id":"895f53de-2baa-4be6-98bf-f7d05c636e12","resolution":{"observed_at":"2026-08-06T17:47:05.304221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.283770Z","title":"Mitigat- ing information leakage in image representations: A maxi- mum entropy approach","venue":null,"work_id":"544d7cb5-161d-46a1-96e1-f9f00704020e","year":2019},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.500184Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:7156f3859c84d377f90fa0961f3c5e061aba1bed8267d9d9b852a3815d71f4e0","observation_id":"27553d1b-2e28-4064-9d24-18f7e40dc594","resolution":{"observed_at":"2026-08-06T17:47:05.289133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.269526Z","title":"Privacy-preserving human activity recog- nition from extreme low resolution","venue":null,"work_id":"f5fb7122-4658-4e1a-9c49-5612c99e32af","year":2017},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.504229Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:3d822436c829137048bdd6dd5fa5f663089e42a88024678cc4eb33cca170e5c5","observation_id":"0c6f5395-06d8-4a5e-a200-3b4486a77a2d","resolution":{"observed_at":"2026-08-06T17:47:05.274117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.254765Z","title":"On the global optima of kernelized adversarial representation learn- ing","venue":null,"work_id":"05f8de39-a7f6-41f2-9894-901f12e93a0b","year":2019},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.507826Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:9fb792812b04976f0af813ccb8eb72f8651aa4d3597d0f6358d4c137a24bf2bc","observation_id":"b73ab8da-7bc1-4776-bf7f-1a8e8831240a","resolution":{"observed_at":"2026-08-06T17:47:05.259821Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.239953Z","title":"On the global optima of kernelized adversarial representation learn- ing","venue":null,"work_id":"2101dda3-1eb7-444d-a367-16b104762e5a","year":2019},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.511893Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:3fb5dca695eb5eb2074998606f761df75081846cd92285e86340ec0fbc48226d","observation_id":"f050dcf5-a3f8-4877-837f-5ea5ae01a3e6","resolution":{"observed_at":"2026-08-06T17:47:05.244497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1904.01067","last_updated":"2019-11-30T14:53:28Z","snapshot_observed_at":"2026-08-14T16:53:24.549008Z","submitted_at":"2019-04-01T19:08:49Z","title":"Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning","version":2},"cited_work":{"arxiv_id":"1904.01067","doi":null,"metadata_source":"pith","pith_arxiv_id":"1904.01067","snapshot_observed_at":"2026-08-06T17:47:04.655655Z","title":"Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning","venue":"cs.CR","work_id":"70edb22b-906f-418d-a6b4-0f636e93b288","year":2019},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.515573Z"},"links":{"cited_paper":"/paper/1904.01067","citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:9da23fae6502037a1e80b65ef0d27761109e404905ddeeeb211f7590262c95f3","observation_id":"1fa8ef49-3ad0-4d80-96bd-e40d1baec8fd","resolution":{"observed_at":"2026-08-06T17:47:04.662004Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.225602Z","title":"Improved techniques for training gans","venue":null,"work_id":"173eb7e5-112e-4ba2-8dea-8be149ce0904","year":2016},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.519506Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:36e0dd9df4aa864c616d8ddf9423ad532117a3a8c2c457f9840a1195a8c0aa4f","observation_id":"ccbf0ff3-3c3e-452f-8537-1c550dc5ad87","resolution":{"observed_at":"2026-08-06T17:47:05.230432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.211015Z","title":"On the fairness of privacy-preserving rep- resentations in medical applications","venue":null,"work_id":"3335ffe6-b5fb-4475-9f7a-b33e5bacad70","year":2020},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.523190Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:5e3b07feb15791b958e003bf4950c263c95e94fd1d30532c90a9abd530d0d899","observation_id":"c24ca5fc-af9d-4c07-93ce-ea0a5ef75736","resolution":{"observed_at":"2026-08-06T17:47:05.215525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.195871Z","title":"Share your representation only: Guar- anteed improvement of the privacy-utility tradeoff in feder- ated learning","venue":null,"work_id":"4bd0a3b5-fa29-4836-bc9a-45b5923bfbe3","year":2023},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.527053Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:75238b68daac1e22ce8ccce60c3923082e752f0e70a304171e36ec18bbeefb9f","observation_id":"188ab1de-3d00-41de-bddc-3c628dc25c00","resolution":{"observed_at":"2026-08-06T17:47:05.201550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.180891Z","title":"Privacy-preserving deep learning","venue":null,"work_id":"b9bf49e7-1e3f-4b3e-afba-48f183b7939e","year":2015},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.531060Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:3e1f75d8bfe9b0cf8a7d7ead9778dbf96e447efb1d9e72a804a7348448780f4a","observation_id":"43b25406-f410-40d9-811c-0e30720e7c3c","resolution":{"observed_at":"2026-08-06T17:47:05.185665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.166613Z","title":"Privacy-preserving adversarial rep- resentation learning in asr: Reality or illusion? Proc","venue":null,"work_id":"0268222b-9a08-4acf-857f-bba197342505","year":2019},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.534865Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:0070ff1a557bef94be6f911e48d104d0dba8286223deed2c3fc3ccd59ad80745","observation_id":"a648cbca-5b52-4be9-9064-ca4838ad689c","resolution":{"observed_at":"2026-08-06T17:47:05.171369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.152440Z","title":"Challenges in disentangling in- dependent factors of variation, 2018","venue":null,"work_id":"53ab67ab-bcb9-41d4-ab82-c22e6436507b","year":2018},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.538823Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:c1e56ce95c2781651961731ed69bd49ac7058b88493b15bc60924cdc889e49fe","observation_id":"90587dd3-d59b-4b29-9b7f-46bc2278fbaa","resolution":{"observed_at":"2026-08-06T17:47:05.157055Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.138752Z","title":"Fairness-aware adver- sarial perturbation towards bias mitigation for deployed deep models","venue":null,"work_id":"64e04fd7-1c6b-493f-bf37-b20659033edf","year":2022},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.542707Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:41e83137eeeb955d9b0a5b9fab5c9d7dcc1d01fd21d512ce730e735bb336d8e5","observation_id":"3c15fc8b-94a7-4eca-a274-2ca27ab14c23","resolution":{"observed_at":"2026-08-06T17:47:05.143404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.125158Z","title":"Privacy-preserving deep action recogni- tion: An adversarial learning framework and a new dataset","venue":null,"work_id":"d51e9294-c0a9-46c4-9f19-4f476311e5f9","year":2020},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.546761Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:0ea031e406c1e2e19ae39673d6612cb7225e37c2cda17b3bdf7eef619b9a9a8e","observation_id":"6af7a5ea-0650-4615-a0b4-8d5858194486","resolution":{"observed_at":"2026-08-06T17:47:05.129538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.112053Z","title":"Adversarial learning of privacy-preserving and task-oriented representations","venue":null,"work_id":"d5cf37c8-d754-436c-88a2-38dd41f186e2","year":2020},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.550446Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:b05a2946acf4d0da33cd563f9ac41ffa380a2094a3aafc61983f0cbf9748ea00","observation_id":"48f98a0a-3abd-4649-a976-4328af6af1f1","resolution":{"observed_at":"2026-08-06T17:47:05.116671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.098932Z","title":"Controllable invariance through adversarial feature learning","venue":null,"work_id":"22908661-c55c-45f2-a69c-d1d364b184b1","year":2017},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.554210Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:1e7ab542fc9b49c3f9dd1a76e3bbe59c833f45a6d34d94db5f98d4e230870aed","observation_id":"e0b84577-ea01-4653-b764-f0962428d57d","resolution":{"observed_at":"2026-08-06T17:47:05.103135Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.085928Z","title":"Investigating bias and fairness in facial expression recogni- tion","venue":null,"work_id":"cede6aa3-7b33-4bfe-8d8b-4e574f10c212","year":2020},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.557877Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:b59e0ba0210ef2fbfc6f1bb00df076624a27e121b6c74448355fa6cde3da2a3a","observation_id":"357089f8-879f-4fe4-b361-d1a64a80a1c6","resolution":{"observed_at":"2026-08-06T17:47:05.090400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.070711Z","title":"Enhancing privacy in face analytics using fully homomorphic encryption","venue":null,"work_id":"c321d8a9-fb3c-441a-b44f-29d647f6b146","year":2024},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.561646Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:42da183b8b376e627262886ea1412699f4dc11b7e1a22af16455e71ba15dd052","observation_id":"3913f73b-4c05-473e-8c39-1cd43674a9f3","resolution":{"observed_at":"2026-08-06T17:47:05.076296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.057422Z","title":"The extended yale face database b","venue":null,"work_id":"7438fe94-e263-4cb5-a428-80d5a780e7ac","year":2001},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.565581Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:151f3b7e5dc412e70aede37506ac4d64de7be9e2484013bc16d113b6a4c4f643","observation_id":"17898d47-299c-4da0-ad74-3f6d2677ef2f","resolution":{"observed_at":"2026-08-06T17:47:05.061956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.044177Z","title":"Learning informative and private representations via generative adversarial networks","venue":null,"work_id":"62633c8f-d1e5-4867-b28d-151a7f77e725","year":2018},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.569140Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:abeb3b226debd4bc72886973f1daaf7e1210c56938966d4857d54f1d3480b2a2","observation_id":"e1318814-1fdc-4eba-8706-68e252fd13d4","resolution":{"observed_at":"2026-08-06T17:47:05.048581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.030555Z","title":"Kitani, and Yoichi Sato","venue":null,"work_id":"0f562c04-a6e7-4f22-8bff-e23d7cfddf50","year":2017},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.572791Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:8100a746e4267701cc36f5ed4c8692eaf47684b04a77cfb98217008ba99314de","observation_id":"e82f0dde-a5c3-442e-8709-18d59f2b6280","resolution":{"observed_at":"2026-08-06T17:47:05.035325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.017496Z","title":"Boosting demographic fairness of face attribute classifiers via latent adversarial representations","venue":null,"work_id":"b335dda1-4b7f-4dc9-873b-954c2830375e","year":2022},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.576565Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:045b037edc13c2dc6cfd5013b9386b8eb0ea0b049b8a522729ca15e55b3e7a24","observation_id":"6f206be9-b92b-48ea-a401-9ba7394973e6","resolution":{"observed_at":"2026-08-06T17:47:05.021930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.003127Z","title":"# !!\"# !$%! Residual Target Enc Dec","venue":null,"work_id":"cf0e84c8-fca3-466b-8298-54001eebb102","year":2017},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.580116Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:fdb25e6eb41e40cc760322568fe83d4cea088392b296f1e1c0c205075a8424da","observation_id":"ef610ec8-a175-4088-9f57-60688ed7e2a0","resolution":{"observed_at":"2026-08-06T17:47:05.007880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:04.988235Z","title":"shortcuts","venue":null,"work_id":"0a6e9ccc-e733-41f2-849c-dba6efd06af8","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.584000Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:fc06c5ef9f26efbfc53f30d27bf01f9874bddc7c2219a5b09f4dcba4563cffee","observation_id":"7305fd94-b273-46cc-b4e1-db01b48845be","resolution":{"observed_at":"2026-08-06T17:47:04.993179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:04.973129Z","title":null,"venue":null,"work_id":"5ffb24c9-64cf-4845-bfef-715efc7d4d6c","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.588323Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:6a8a28242cef2338d1eafd643be1c02d9c9e7d92a087cf37c240c195b065becb","observation_id":"3b3e204a-0161-4f31-a18b-abcec3e2faf3","resolution":{"observed_at":"2026-08-06T17:47:04.977712Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:04.959954Z","title":"We thereby largely follow the pro- tocol of [23, 52]","venue":null,"work_id":"ae61d0b2-a97c-47b1-81b2-bfc04734871a","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.592974Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:5a894199a8cfa459547432b3d943dc40486eee240fd6ea67bd79a922289ffc1f","observation_id":"224e9ad5-a25c-4c9e-b444-8ba234057c32","resolution":{"observed_at":"2026-08-06T17:47:04.964176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:04.946413Z","title":"one-to-one","venue":null,"work_id":"72799aa8-b5c9-4400-b04a-8f87232fea4b","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.597154Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:b48440bee279516ec35174707489e60b594166550ef0258df14d65c767318147","observation_id":"d625a56f-e621-4850-b7a4-a3e645bd4c91","resolution":{"observed_at":"2026-08-06T17:47:04.950633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:04.931711Z","title":null,"venue":null,"work_id":"7ddce418-c05d-48ac-b010-78dfab277f30","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.601030Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:cd48f58ea1d3bbf0b014a7056407f882f509b97ebc6971863e95e01674f97316","observation_id":"fd0add0c-ec0f-49e2-802a-ab5a611d902d","resolution":{"observed_at":"2026-08-06T17:47:04.936881Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:04.916111Z","title":"This visu- alization provides a more in-depth view of how the adver- sarial process leads to a remapping of identities","venue":null,"work_id":"fa4f08e8-8cf0-4c37-8737-ec1dcc9d5486","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.605261Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:ca4d481113c12dd8ec434aa42b28b71b8eb85dca41e28dca6d33813b0ecbc293","observation_id":"67039767-e774-47e8-a389-9ab6140df8e5","resolution":{"observed_at":"2026-08-06T17:47:04.921578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:04.902795Z","title":"relatively unbiased","venue":null,"work_id":"e6716310-545f-43f1-960b-86a84e2c6f11","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.609220Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:632c7250a11525f35b0bca0c69fd440a95e3cc64548de85317dbdafbbc1dfb68","observation_id":"f987cac8-3827-4a48-9fd8-f8b4c96f81d3","resolution":{"observed_at":"2026-08-06T17:47:04.906979Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:04.888377Z","title":null,"venue":null,"work_id":"2f1f4beb-987c-45c4-b806-e22a98a3dc7a","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.612973Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:fe67408a6def2402c0c877058aca0067117f7e0ada3cd8803eb04c741585d2ac","observation_id":"22dff14e-a876-474c-9025-06e8dfe78fcf","resolution":{"observed_at":"2026-08-06T17:47:04.893284Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:04.874494Z","title":"Each column is two different samples from CelebA (one male and one female), and from top to bot- tom, the privacy disclosure is decreasing for each","venue":null,"work_id":"a3b8d084-8026-4c62-b85e-35c9aabaa8bf","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.616477Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:772afcc5da424b21603970f2694e9e8ada840795968eda271a76ca4511f8ba0f","observation_id":"c8777445-f751-4ee5-8260-a0eef8e1b05f","resolution":{"observed_at":"2026-08-06T17:47:04.878851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:04.861554Z","title":"Ta- ble 10 shows the architectures of the V AE, i.e., the encoder and the decoder","venue":null,"work_id":"41aec531-9eb5-4405-889d-b91bc13d3740","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.620273Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:ea1e43d8e6f7cf6066ffdcf6eb46093b3f6b989142127ab86403e641f893e8bd","observation_id":"dc95a4cf-3b01-4233-a650-96ee421c7436","resolution":{"observed_at":"2026-08-06T17:47:04.865561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T17:47:05.446022Z","title":null,"venue":null,"work_id":"2caa393e-1741-450d-926b-0fd6d00176ac","year":null},"citing_paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:04.437393Z"},"links":{"citing_paper":"/paper/2507.10194"},"observation_digest":"sha256:7e4647ddcb6f16891c26cf730f70a09bdd72d5b2586d79387571e1ca6a32f22d","observation_id":"b6548975-6c1b-41ab-9e57-75868bf11da0","resolution":{"observed_at":"2026-08-06T17:47:05.450660Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.10194","last_updated":"2025-07-14T12:01:08Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T15:37:03.693353Z","submitted_at":"2025-07-14T12:01:08Z","title":"Learning Private Representations through Entropy-based Adversarial Training"},"reference_resolution":{"displayed":81,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":5,"verified_fuzzy":61},"total_outbound_references":81},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 81 of 81 outbound references and 0 inbound Pith citation observations for arXiv:2507.10194."}