{"as_of":"2026-08-14T14:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:da424974c1a625542569a2a2b9e3911f87a1db318ca78d23108536772c6ed0f0","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T14:56:04.038587Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+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/2507.17895/citation-record","integrity":"/paper/2507.17895/integrity","json":"/paper/2507.17895/citation-record.json","paper":"/paper/2507.17895"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T14:56:03.890722Z","title":"Deep learning with differential privacy","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.890722Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:8fa2a7e4a912183253d10bc2fb65f7ee9602cad9ad7c1b5121361292756305d8","observation_id":"54c593f5-6bcd-4242-a5fa-e7023735e701","resolution":{"observed_at":"2026-08-06T14:56:03.890722Z","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":"2026-08-06T14:56:04.523301Z","title":"IV.---On least squares and linear combination of observations","venue":null,"work_id":"6f35c3bf-90c0-43f6-aa1f-551a13d0535c","year":1936},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.894607Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:463abe988d9b8f984e7fe8fb84760d8db447180edb384845e53b46cb5d451d1d","observation_id":"8b94406b-bef3-4818-b3e8-d0cae04d5c3a","resolution":{"observed_at":"2026-08-06T14:56:04.526281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.12374","last_updated":"2024-12-16T22:07:33Z","snapshot_observed_at":"2026-08-13T08:57:00.307131Z","submitted_at":"2024-12-16T22:07:33Z","title":"Privacy in Metalearning and Multitask Learning: Modeling and Separations","version":1},"cited_work":{"arxiv_id":"2412.12374","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.12374","snapshot_observed_at":"2026-08-06T14:56:04.224591Z","title":"Privacy in Metalearning and Multitask Learning: Modeling and Separations","venue":"cs.LG","work_id":"69f77889-3c85-44e4-b173-b1352866881a","year":2024},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.897660Z"},"links":{"cited_paper":"/paper/2412.12374","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:c207458593e5f914d04d73503091e2cd9fa06d611ca33a4633252b7404f9ee14","observation_id":"fbbb9fc7-6ca3-47c8-b870-8e145cbadf82","resolution":{"observed_at":"2026-08-06T14:56:04.227992Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.515353Z","title":"Public data-assisted mirror descent for private model training","venue":null,"work_id":"edf6299e-b05e-4183-854d-196f1f4bcf69","year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.901071Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:5581cc274c323a309029350e21e5e3b164208cee41357500ee23004fa5066656","observation_id":"7a35a2dd-7b54-4378-a95d-83cde7d70a92","resolution":{"observed_at":"2026-08-06T14:56:04.518323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.13722","last_updated":"2023-01-08T02:04:41Z","snapshot_observed_at":"2026-08-14T02:20:46.610970Z","submitted_at":"2022-05-27T02:32:26Z","title":"Can Foundation Models Help Us Achieve Perfect Secrecy?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.13722","snapshot_observed_at":"2026-08-06T14:56:03.903764Z","title":"Can foundation models help us achieve perfect secrecy? arXiv preprint arXiv:2205.13722, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.903764Z"},"links":{"cited_paper":"/paper/2205.13722","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:d85d9f2597c2caf3eb1b2aef26796c5126238b5fc678319ce1622bd6daf83dfc","observation_id":"5c50834e-0f4d-4b2a-aa27-ea58b7eb45af","resolution":{"observed_at":"2026-08-06T14:56:03.903764Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09327","last_updated":"2024-07-18T17:37:59Z","snapshot_observed_at":"2026-08-13T04:18:56.331547Z","submitted_at":"2024-02-14T17:17:30Z","title":"Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09327","snapshot_observed_at":"2026-08-06T14:56:03.906871Z","title":"Information complexity of stochastic convex optimization: Applications to generalization and memorization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.906871Z"},"links":{"cited_paper":"/paper/2402.09327","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:26e0386b5a43148c35c44793f904b37cafcd48ab0b2ff68c3e752eb08901143c","observation_id":"9757a501-e865-4b83-96d9-6bca12f90fc4","resolution":{"observed_at":"2026-08-06T14:56:03.906871Z","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":"2026-08-06T14:56:04.506915Z","title":"The power of the hybrid model for mean estimation","venue":null,"work_id":"a90e981a-8e82-49b4-98d5-c014d96de78b","year":2020},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.910435Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:c639b00c6141d8c6837972e8e50af2d479f35fc9761a0b0c1e040a7ec6ffd1b0","observation_id":"84f99ba2-4e4d-4957-b3ae-0051563b8fda","resolution":{"observed_at":"2026-08-06T14:56:04.510038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.498343Z","title":"Private empirical risk minimization: Efficient algorithms and tight error bounds","venue":null,"work_id":"65209cb8-6896-42e4-938f-c79df12bee45","year":2014},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.913454Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:d48e99245cdb22c381929070a92aba633d8a90daacc3a3acdaafe3143f840aeb","observation_id":"c008c349-68d5-4107-a8aa-f6024f9df7dc","resolution":{"observed_at":"2026-08-06T14:56:04.501307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.490004Z","title":"Private query release assisted by public data","venue":null,"work_id":"9b11d0aa-8575-46dc-9e10-f28bcea0921f","year":2020},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.916288Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:7a2e36e61c8859c9db661435d9fcdb033e6eb2e7a74fe2cabb1b35e6d70d3593","observation_id":"684e45f2-eefe-45ac-9568-fd0885821e22","resolution":{"observed_at":"2026-08-06T14:56:04.493124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.481820Z","title":"Private estimation with public data","venue":null,"work_id":"5f464b81-80a5-4b0e-a7ed-26057c31cd52","year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.918977Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:63b4eaa551f9f65e27e06e50abca94a3ac4bb6649c30bc4b2e7bff059bafd2bf","observation_id":"f7208a39-8ca0-446d-acbd-5ad5c12d4313","resolution":{"observed_at":"2026-08-06T14:56:04.484805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.473518Z","title":"Differentially private optimization on large model at small cost","venue":null,"work_id":"f73a8dc2-1d2e-44e3-bc7a-2fb016156268","year":2023},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.921388Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:bbdc7eb5944f0f5d154ad1a825f8248f2af6c2c540ff502e5f5c79a5f7eff85e","observation_id":"1396b9ac-c6b3-49d0-94c2-6abf3149ea46","resolution":{"observed_at":"2026-08-06T14:56:04.476627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.465424Z","title":"Fingerprinting codes and the price of approximate differential privacy","venue":null,"work_id":"b6d07b7f-9b48-4235-b59d-d246fdb7ec6f","year":2014},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.924994Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:5fe12093cfbac066989626591c62399214962c85bee81bf7f0c4aebbfeb22d8c","observation_id":"04129dd9-e7b1-4416-a8b7-612316d682e5","resolution":{"observed_at":"2026-08-06T14:56:04.468266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T14:56:03.927640Z","title":"The cost of privacy: Optimal rates of convergence for parameter estimation with differential privacy","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.927640Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:fc48da2970771298722695120900d29423672465d2e2e205a1c16c6439c3ac9e","observation_id":"eeb649a0-84dd-4736-8502-07086f88639d","resolution":{"observed_at":"2026-08-06T14:56:03.927640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.07152","last_updated":"2025-07-12T21:42:34Z","snapshot_observed_at":"2026-08-13T12:25:42.339361Z","submitted_at":"2023-03-13T14:26:27Z","title":"Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.07152","snapshot_observed_at":"2026-08-06T14:56:03.930247Z","title":"Score attack: A lower bound technique for optimal differentially private learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.930247Z"},"links":{"cited_paper":"/paper/2303.07152","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:7eb0dbbea10dbce4bf6473190467489ee81167862042e15da07df50353eb5c0b","observation_id":"95dec74d-85cd-47a6-83ae-48fa107dc6db","resolution":{"observed_at":"2026-08-06T14:56:03.930247Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.13650","last_updated":"2022-06-16T17:47:42Z","snapshot_observed_at":"2026-08-14T02:25:49.984432Z","submitted_at":"2022-04-28T17:10:56Z","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.13650","snapshot_observed_at":"2026-08-06T14:56:03.933205Z","title":"Unlocking high-accuracy differentially private image classification through scale","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.933205Z"},"links":{"cited_paper":"/paper/2204.13650","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:e0790e33bf9ae0ae95d790ce0f8b44cb61c78581080fd9ef2c23ca769bcd7b5e","observation_id":"e559fc72-b0a9-451e-87e7-ae39280f09b4","resolution":{"observed_at":"2026-08-06T14:56:03.933205Z","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":"2026-08-06T14:56:04.452800Z","title":"Calibrating noise to sensitivity in private data analysis","venue":null,"work_id":"e04b5c07-4c17-4e6e-b04e-f98b61a0b7ff","year":2006},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.936090Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:9b4117020c9c47db8820fdc4ee17507357305ef50079d2a8025e5de997c6b68c","observation_id":"47dab8bf-cab8-4b0d-ba1e-1fd3235aefdb","resolution":{"observed_at":"2026-08-06T14:56:04.455534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.444881Z","title":"Analyze gauss: optimal bounds for privacy-preserving principal component analysis","venue":null,"work_id":"238b6098-ce96-4040-8f50-0d5cbe9c44d7","year":2014},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.938673Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:7f52d0c40998479a9ed56d19d297415cbacfc562fdaf3f459b8814de99feb12d","observation_id":"42da59ba-b07e-4b4c-87ab-c6d39235c2b2","resolution":{"observed_at":"2026-08-06T14:56:04.447806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.436424Z","title":"Robust traceability from trace amounts","venue":null,"work_id":"4703fe8f-604d-4d84-aa46-cdc7546a5b4f","year":2015},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.941249Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:589edcee419a005084afad5953bd00e93e981138f3930922c0544dce54a1ae77","observation_id":"fbdd96e1-2d65-403b-b314-7d7e785f50a0","resolution":{"observed_at":"2026-08-06T14:56:04.439502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.427639Z","title":"Joint selection: Adaptively incorporating public information for private synthetic data","venue":null,"work_id":"6fa46040-4c52-43ba-960d-1ed06642a923","year":2024},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.943699Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:97c33b20b3b488f0900d8280691fd4524932976f3afbb765a3f2904e3ef252f9","observation_id":"262f3144-86c6-4d33-b0ca-fa25d9393ed2","resolution":{"observed_at":"2026-08-06T14:56:04.430976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.419438Z","title":"Why is public pretraining necessary for private model training? In International Conference on Machine Learning, pages 10611--10627","venue":null,"work_id":"17449921-a505-42b1-af17-20d71a501452","year":2023},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.946437Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:330a9a3533bb7e243174f824c85d5fd0bd161e9a33390973fc477c65f7c9c423","observation_id":"4978890b-6c94-4da2-bb02-772d800530ad","resolution":{"observed_at":"2026-08-06T14:56:04.422518Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.00971","last_updated":"2022-01-04T04:23:38Z","snapshot_observed_at":"2026-08-13T17:04:33.710786Z","submitted_at":"2022-01-04T04:23:38Z","title":"Submix: Practical Private Prediction for Large-Scale Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.00971","snapshot_observed_at":"2026-08-06T14:56:03.948968Z","title":"Submix: Practical private prediction for large-scale language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.948968Z"},"links":{"cited_paper":"/paper/2201.00971","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:4d956ca1f52c5220d265e41805c474490c876770784424c2334368e5b92b21bc","observation_id":"58ede26c-6b8b-4e5d-9ccc-c03d5de3993c","resolution":{"observed_at":"2026-08-06T14:56:03.948968Z","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":"2026-08-06T14:56:04.410862Z","title":"Mixed differential privacy in computer vision","venue":null,"work_id":"8fff46cf-505f-4c91-84c7-3e278dbca2d7","year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.951756Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:54c9f4b4613b737b6daf0353762581a13c8c912789a48830690b8e9fe1c6d719","observation_id":"8f2add10-c908-4e4d-9f28-d94a61ddfd5b","resolution":{"observed_at":"2026-08-06T14:56:04.413692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.402369Z","title":"Preventing false discovery in interactive data analysis is hard","venue":null,"work_id":"ec747d35-2d3f-4870-aef9-a09f1ba4304b","year":2014},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.954328Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:170588d0d9de77d5b3de5aa21a90792a3a7431fed8764a7bf0ce42b0819bbfd2","observation_id":"40ef10ea-f269-41fe-a8e5-7520efc79803","resolution":{"observed_at":"2026-08-06T14:56:04.405200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.393796Z","title":"Exploring the limits of differentially private deep learning with group-wise clipping","venue":null,"work_id":"0eb1a8c2-295a-4f75-b879-4d66b75c7296","year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.956914Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:3112deee4b5207ac618b35f59271e73b4db833dbee961d374c72db41090942b6","observation_id":"c97295e3-3602-4975-8a5d-c867c2a8a7e1","resolution":{"observed_at":"2026-08-06T14:56:04.396882Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T14:56:03.959602Z","title":"Auditing differentially private machine learning: How private is private sgd? Advances in Neural Information Processing Systems, 33: 0 22205--22216, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.959602Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:98c1c0c6cb7c9552abcab61ba10cf3ba18d7f6cda51e14fb5966fa44933b1cd3","observation_id":"f60f062f-c31c-459b-8670-2f73998fedce","resolution":{"observed_at":"2026-08-06T14:56:03.959602Z","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":"2026-08-06T14:56:04.380948Z","title":"(nearly) dimension independent private erm with adagrad via publicly estimated subspaces","venue":null,"work_id":"2ceba423-baee-46a4-ab54-d598b7bd1afb","year":2021},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.962120Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:94a2147b48edef2f6e9bb6aa60c6b5530ba7d88a77dd623e40dcceeab0361ee9","observation_id":"4cfbca25-d9f7-44e6-8928-106c028dad6c","resolution":{"observed_at":"2026-08-06T14:56:04.383904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.373360Z","title":"Privately learning high-dimensional distributions","venue":null,"work_id":"b44bb2cf-e488-4927-923a-85a9760b2c7f","year":1902},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.964679Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:9888737a5bb53affba4d8601070b224f82306364b3ed831d7e15c2d6a1475978","observation_id":"103191ad-c34d-472a-8cf3-9f68804d0a26","resolution":{"observed_at":"2026-08-06T14:56:04.376176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.365033Z","title":"New lower bounds for private estimation and a generalized fingerprinting lemma","venue":null,"work_id":"57eb19d7-183e-42f1-ac91-6cdde520935e","year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.967422Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:e63848fb89481f12b3d054d47d4c5c088e3b9908aa7fbd2838819350cff65420","observation_id":"4f3715ca-c290-4eb9-b48c-e3b348eac8fd","resolution":{"observed_at":"2026-08-06T14:56:04.368371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T14:56:03.970006Z","title":"On the convergence of differentially-private fine-tuning: To linearly probe or to fully fine-tune? arXiv preprint arXiv:2402.18905, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.970006Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:28124bc1104f1f3d04401099a1fa235d282219e9401ec9bde2491f1879c6bde5","observation_id":"81ea73d1-023a-4e6b-986f-f0f5945b1db0","resolution":{"observed_at":"2026-08-06T14:56:03.970006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12328","last_updated":"2022-02-09T04:55:14Z","snapshot_observed_at":"2026-08-13T16:50:52.906755Z","submitted_at":"2022-01-28T18:48:18Z","title":"Toward Training at ImageNet Scale with Differential Privacy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12328","snapshot_observed_at":"2026-08-06T14:56:03.972461Z","title":"Toward training at imagenet scale with differential privacy","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.972461Z"},"links":{"cited_paper":"/paper/2201.12328","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:efa87e60d8cb53cbe3bc91e1e5edafd7294d5dc28560179a1ba9a07785e2e08d","observation_id":"c25713c9-bbf6-4dce-97ae-7a818bd0007a","resolution":{"observed_at":"2026-08-06T14:56:03.972461Z","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":"2026-08-06T14:56:04.357482Z","title":"Large language models can be strong differentially private learners","venue":null,"work_id":"ea28da77-22e6-4b9e-8317-c21b3ae2e621","year":2021},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.975302Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:53216d3025a591c06e26303aadd8153e715aa6537d3dc8808bf1e97ff7fa590a","observation_id":"ee4ad2e0-ed5f-4fed-ad6f-6945f6d3dba9","resolution":{"observed_at":"2026-08-06T14:56:04.360289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.349921Z","title":"Leveraging public data for practical private query release","venue":null,"work_id":"30ed0055-1c40-4796-a16b-4043daf4a3c3","year":2021},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.977821Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:ee7bf09e988a46a8ae991796216d020113f3059e976379df31c076236a2ea683","observation_id":"269829fa-7704-4cd4-ba99-8e44710795ca","resolution":{"observed_at":"2026-08-06T14:56:04.352750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.342154Z","title":"Optimal differentially private model training with public data","venue":null,"work_id":"3cde5f4f-b6de-4895-8585-cd6099960d8a","year":2024},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.980602Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:51ccf0c64c8542b019db66b4a1b88ed2039cbcec29d76a06b7f9006ac9b1f5ec","observation_id":"a05642aa-07b0-4784-b1a0-d52408025f5f","resolution":{"observed_at":"2026-08-06T14:56:04.344951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.334286Z","title":"Scalable differential privacy with sparse network finetuning","venue":null,"work_id":"45c1a9ef-5616-47c1-8f56-65a9ecde89be","year":2021},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.983153Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:1968af054b812c00b2e080cc9074e3e4af1a134a93312be508f8a7cedfe42b41","observation_id":"6954c188-70aa-44a6-a93a-6dfa4d6abcfc","resolution":{"observed_at":"2026-08-06T14:56:04.337327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.14396","last_updated":"2024-12-18T23:11:07Z","snapshot_observed_at":"2026-08-13T20:58:55.414153Z","submitted_at":"2024-12-18T23:11:07Z","title":"Fingerprinting Codes Meet Geometry: Improved Lower Bounds for Private Query Release and Adaptive Data Analysis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.14396","snapshot_observed_at":"2026-08-06T14:56:03.985754Z","title":"Fingerprinting codes meet geometry: Improved lower bounds for private query release and adaptive data analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.985754Z"},"links":{"cited_paper":"/paper/2412.14396","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:ceebf5e9f00190ed1e0665076024ce57d363b1bf15f86725dc5cf8c646b19c9b","observation_id":"e5e98370-56e8-44e2-baf3-b06d1553bb55","resolution":{"observed_at":"2026-08-06T14:56:03.985754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.02973","last_updated":"2022-05-20T21:17:42Z","snapshot_observed_at":"2026-08-13T22:06:50.124171Z","submitted_at":"2022-05-06T01:22:20Z","title":"Large Scale Transfer Learning for Differentially Private Image Classification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.02973","snapshot_observed_at":"2026-08-06T14:56:03.988773Z","title":"Large scale transfer learning for differentially private image classification","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.988773Z"},"links":{"cited_paper":"/paper/2205.02973","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:bf569cd2990c87a105b71a520fd04e05f3a33c6781c3b124f420a054f103aad2","observation_id":"d3a567c0-843d-4f51-97a5-0ff135350fd1","resolution":{"observed_at":"2026-08-06T14:56:03.988773Z","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":"2026-08-06T14:56:04.326757Z","title":null,"venue":null,"work_id":"e82868b5-ca7c-44f9-9ac5-d403aa8c5a16","year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.991569Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:b78179abf5c07cff7700805f1219801b56eeada125bdde6886e7c40a67672f03","observation_id":"5e38146d-492a-4357-ab9a-1ff7e510e54c","resolution":{"observed_at":"2026-08-06T14:56:04.329402Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06289","last_updated":"2024-01-04T07:36:29Z","snapshot_observed_at":"2026-08-13T05:53:22.496540Z","submitted_at":"2023-10-10T04:02:43Z","title":"Better and Simpler Lower Bounds for Differentially Private Statistical Estimation","version":2},"cited_work":{"arxiv_id":"2310.06289","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.06289","snapshot_observed_at":"2026-08-06T14:56:04.100424Z","title":"Better and Simpler Lower Bounds for Differentially Private Statistical Estimation","venue":"math.ST","work_id":"74e93792-f96b-4509-833b-e387561d3052","year":2023},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.994305Z"},"links":{"cited_paper":"/paper/2310.06289","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:6bd8a9c161123130490417dee2b565b7ad1836a5d75bdae04a204a2b3902fc7e","observation_id":"297cd488-6dd1-4825-baea-dc26ae504924","resolution":{"observed_at":"2026-08-06T14:56:04.103857Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.318625Z","title":"Tight and robust private mean estimation with few users","venue":null,"work_id":"d929a69d-3d2c-4f8e-a56b-f776b74770c7","year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.997166Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:85aec468fe185e853d567bd7889f38f49d3640efb7475a732df88db92c6773b4","observation_id":"f92c29e5-3275-44d4-9c38-c90ea17fd10d","resolution":{"observed_at":"2026-08-06T14:56:04.321614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.310650Z","title":"Making the shoe fit: Architectures, initializations, and tuning for learning with privacy","venue":null,"work_id":"f59bfc2a-c65b-4ba8-ba98-423bd9afaee5","year":2019},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:03.999799Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:f86f3024ac8084b36691c77d936910ea9041aed1e8a5f6de3a3dcf25a54f989e","observation_id":"04fe2df1-311d-4e7a-8cbc-63e0502a5e4d","resolution":{"observed_at":"2026-08-06T14:56:04.313465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.301872Z","title":"Smooth lower bounds for differentially private algorithms via padding-and-permuting fingerprinting codes","venue":null,"work_id":"db04d40f-e1a8-473b-9577-088b19212580","year":2024},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.002511Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:88a2a3cc1c1cd5dd9cd00bc357aeda07d4b88176c1b60367a5689c12bc00a42c","observation_id":"f1039f7b-56d6-4edc-a27a-b4a33ce281b0","resolution":{"observed_at":"2026-08-06T14:56:04.305141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.17714","last_updated":"2024-04-26T22:17:32Z","snapshot_observed_at":"2026-08-13T15:16:54.097404Z","submitted_at":"2024-04-26T22:17:32Z","title":"Lower Bounds for Private Estimation of Gaussian Covariance Matrices under All Reasonable Parameter Regimes","version":1},"cited_work":{"arxiv_id":"2404.17714","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.17714","snapshot_observed_at":"2026-08-06T14:56:04.088950Z","title":"Lower Bounds for Private Estimation of Gaussian Covariance Matrices under All Reasonable Parameter Regimes","venue":"cs.DS","work_id":"2fcf66ca-6d99-4103-a5cb-7beddf994e90","year":2024},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.005378Z"},"links":{"cited_paper":"/paper/2404.17714","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:157994d107d21e5d74e0e0adec59f9177b57bb06c9de2bf1b2c867293015ec43","observation_id":"4027a4e2-fbeb-4796-890d-57d4953efe92","resolution":{"observed_at":"2026-08-06T14:56:04.092206Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1501.06095","last_updated":"2015-01-24T23:26:21Z","snapshot_observed_at":"2026-07-06T04:07:08.463282Z","submitted_at":"2015-01-24T23:26:21Z","title":"Between Pure and Approximate Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1501.06095","snapshot_observed_at":"2026-08-06T14:56:04.008214Z","title":"Between pure and approximate differential privacy","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.008214Z"},"links":{"cited_paper":"/paper/1501.06095","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:fb5111240f78befdc4afc9fbc86f0b061a7177a50a05af6d4f798103d6d5b1f7","observation_id":"fe7723d8-b390-422e-8f8e-cde9f7496638","resolution":{"observed_at":"2026-08-06T14:56:04.008214Z","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":"2026-08-06T14:56:04.293284Z","title":"Interactive fingerprinting codes and the hardness of preventing false discovery","venue":null,"work_id":"9a886711-399c-468a-906f-9ab737e5ab23","year":2015},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.012251Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:afeb98b4fed451dcddb2cc37a6a79122909a614c44cf9e091c74fc085308ce7e","observation_id":"00f98268-2890-47b1-920b-6739216f650a","resolution":{"observed_at":"2026-08-06T14:56:04.296149Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.285286Z","title":"Tight lower bounds for differentially private selection","venue":null,"work_id":"ca1ec65e-8487-4a7d-9d43-850157b60540","year":2017},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.014802Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:12f7c59eb72dcec7c8a8b1878595702bc8b20f3d926649bfd81113a20cd6a9ac","observation_id":"587636dc-d7ed-4038-ae55-7b61b65989c3","resolution":{"observed_at":"2026-08-06T14:56:04.288191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.275779Z","title":"Differentially private learning needs better features (or much more data)","venue":null,"work_id":"53992fdb-996e-4b3a-82a2-1742d3ef7a37","year":2020},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.017368Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:4886929610140982b4fd284ea1a885084c7f348136161224d9754efeca7fb8bf","observation_id":"b254b71c-3735-4ebd-9841-01034cf7043b","resolution":{"observed_at":"2026-08-06T14:56:04.279461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.06470","last_updated":"2024-07-17T06:53:58Z","snapshot_observed_at":"2026-08-14T03:28:07.899049Z","submitted_at":"2022-12-13T10:41:12Z","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.06470","snapshot_observed_at":"2026-08-06T14:56:04.019949Z","title":"Considerations for differentially private learning with large-scale public pretraining","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.019949Z"},"links":{"cited_paper":"/paper/2212.06470","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:62b4f925070ee77fab05e31962789f1886e1942725023ce9c2a8e287befcf360","observation_id":"7b0ba576-eaad-4d40-b354-44f418d9e43f","resolution":{"observed_at":"2026-08-06T14:56:04.019949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03856","last_updated":"2024-03-06T17:06:11Z","snapshot_observed_at":"2026-08-13T04:02:06.028803Z","submitted_at":"2024-03-06T17:06:11Z","title":"Public-data Assisted Private Stochastic Optimization: Power and Limitations","version":1},"cited_work":{"arxiv_id":"2403.03856","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.03856","snapshot_observed_at":"2026-08-06T14:56:04.060921Z","title":"Public-data Assisted Private Stochastic Optimization: Power and Limitations","venue":"cs.LG","work_id":"1063005a-19bf-4a9f-a10c-671702ab7ec0","year":2024},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.022649Z"},"links":{"cited_paper":"/paper/2403.03856","citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:c3b2c77ee35bc35efdb2884e2c28023acda0fffe16e9c8582c06e94a4fdc263c","observation_id":"63060c34-0577-412b-99fc-dada4ac3ae9a","resolution":{"observed_at":"2026-08-06T14:56:04.066101Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.267909Z","title":"Answering n^ 2+o(1) counting queries with differential privacy is hard","venue":null,"work_id":"4c7b9079-30d9-4ec2-af84-b9eda2819e55","year":2013},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.025481Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:d9e78521398fd94782cfc523c16a596f12e484cb10512d19ceb76c87d58d4c72","observation_id":"22c0e2cb-bae8-4914-83a8-08838cd62937","resolution":{"observed_at":"2026-08-06T14:56:04.270709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.258927Z","title":"The limits of post-selection generalization","venue":null,"work_id":"a992490b-2ae0-442f-8243-1371f28980d6","year":2018},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.028339Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:47f46c1bacd077a95874e47269398e9cac16be3b4f51b74ddf2197f7324dff17","observation_id":"23fe4e86-e5d3-4f6a-b3a1-2b0e49f6bc7f","resolution":{"observed_at":"2026-08-06T14:56:04.262379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T14:56:04.030851Z","title":"High-dimensional probability: An introduction with applications in data science, volume 47","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.030851Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:7515919547717eb08fc28b2c0e6fd333186e62fa18d8ec6a42bb1f376bbe8b46","observation_id":"aee414e9-9459-4799-a132-5bdff7b05e3e","resolution":{"observed_at":"2026-08-06T14:56:04.030851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T14:56:04.033599Z","title":"High-dimensional statistics: A non-asymptotic viewpoint, volume 48","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.033599Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:ad109156298a6dbd16f167c967052dc7ac86d9ff7d0e66b9a61acc95dd749111","observation_id":"474c5b93-5c89-495f-9bd5-ea5656a8648d","resolution":{"observed_at":"2026-08-06T14:56:04.033599Z","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":"2026-08-06T14:56:04.241521Z","title":"Differentially private fine-tuning of language models","venue":null,"work_id":"a0889ff1-6f5c-4c64-862b-e10121fa397d","year":2021},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.036098Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:6149d072fb46877430ac101f8b0a86a2d8ac599ddd2a68e679579cfb207fbec6","observation_id":"092b9303-702f-47ad-8462-53751cee9a3f","resolution":{"observed_at":"2026-08-06T14:56:04.244179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-06T14:56:04.233687Z","title":"Large scale private learning via low-rank reparametrization","venue":null,"work_id":"ab2d19ee-c184-4fad-9b3f-0d1d20406db5","year":2021},"citing_paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-06T14:56:04.038587Z"},"links":{"citing_paper":"/paper/2507.17895"},"observation_digest":"sha256:799dc21a03a8273295ea83468f59af5d01ef358dc50c214ff07667b198a6ab40","observation_id":"2601894b-fd4b-45c0-9e94-9bed7e6cb53c","resolution":{"observed_at":"2026-08-06T14:56:04.236432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.17895","last_updated":"2025-07-23T19:46:08Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T19:18:22.684960Z","submitted_at":"2025-07-23T19:46:08Z","title":"Lower Bounds for Public-Private Learning under Distribution Shift"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":4,"verified_fuzzy":33},"total_outbound_references":54},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2507.17895."}