{"as_of":"2026-08-15T04:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:06b9769400468959793a160a22bf2ac93357d00550a9492a493bb17b47d45f51","coverage":[{"denominator":50,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":50,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T12:49:37.765070Z","state":"measured"},{"denominator":50,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":50,"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/2412.13818/citation-record","integrity":"/paper/2412.13818/integrity","json":"/paper/2412.13818/citation-record.json","paper":"/paper/2412.13818"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1602.05629","last_updated":"2023-01-26T22:54:08Z","snapshot_observed_at":"2026-08-14T22:09:52.579364Z","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":"2026-08-11T12:49:37.495415Z","title":"Federated learning of deep networks using model averaging,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.495415Z"},"links":{"cited_paper":"/paper/1602.05629","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:baa5f88381bb21755761b3d321b3b5d37e147e2f69bcc9c11329aebe12661978","observation_id":"5144f640-e5df-445b-9fdd-83b405192f25","resolution":{"observed_at":"2026-08-11T12:49:37.495415Z","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":"2026-08-11T12:49:37.500772Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.500772Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:1402cf0984b25af7b73fa0d9141a27484e246b8741806fd5517658efee7a2d3e","observation_id":"30bd8d4e-9a2c-4406-b9fc-a2fe2ea26bee","resolution":{"observed_at":"2026-08-11T12:49:37.500772Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.02527","last_updated":"2016-10-08T13:25:15Z","snapshot_observed_at":"2026-08-14T21:36:07.062248Z","submitted_at":"2016-10-08T13:25:15Z","title":"Federated Optimization: Distributed Machine Learning for On-Device Intelligence","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.02527","snapshot_observed_at":"2026-08-11T12:49:37.505188Z","title":"Federated optimization: Distributed machine learning for on-device intelligence,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.505188Z"},"links":{"cited_paper":"/paper/1610.02527","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:34dae47f55fc64ab9b0dad72a8479e88288f305b48156fdb65dcada35b19d956","observation_id":"153e0476-4249-47f6-a8a7-ca629410e542","resolution":{"observed_at":"2026-08-11T12:49:37.505188Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.05492","last_updated":"2017-10-30T20:52:14Z","snapshot_observed_at":"2026-08-13T17:19:46.488095Z","submitted_at":"2016-10-18T09:11:51Z","title":"Federated Learning: Strategies for Improving Communication Efficiency","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.05492","snapshot_observed_at":"2026-08-11T12:49:37.511639Z","title":"Federated learning: Strategies for improving communication efficiency,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.511639Z"},"links":{"cited_paper":"/paper/1610.05492","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:038280bd6cae17dcc221e49ab42ee41283a30ae0ab065437637646c8d4b85928","observation_id":"a2074923-b222-478c-a6bb-1341eb414fef","resolution":{"observed_at":"2026-08-11T12:49:37.511639Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.08935","last_updated":"2019-12-19T05:09:29Z","snapshot_observed_at":"2026-08-14T16:12:44.382531Z","submitted_at":"2019-06-21T03:46:43Z","title":"Deep Leakage from Gradients","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.08935","snapshot_observed_at":"2026-08-11T12:49:37.517760Z","title":"Deep leakage from gradients,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.517760Z"},"links":{"cited_paper":"/paper/1906.08935","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:1a78bd340d54fe303c9bc5ff6432f02e2bad4e07a0f4376da0d75ee7bc664c35","observation_id":"62b73346-fe58-43d9-b740-0121e21edbd5","resolution":{"observed_at":"2026-08-11T12:49:37.517760Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.14053","last_updated":"2020-09-11T11:41:10Z","snapshot_observed_at":"2026-08-12T11:37:19.011664Z","submitted_at":"2020-03-31T09:35:02Z","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.14053","snapshot_observed_at":"2026-08-11T12:49:37.522830Z","title":"Inverting gradients – how easy is it to break privacy in federated learning?","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.522830Z"},"links":{"cited_paper":"/paper/2003.14053","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:42323f5857f63e7cccdfb7a2464f50b6268a226d25fb01aa6917aa70f7367647","observation_id":"94019469-b930-430e-91cc-3ce0b17479a4","resolution":{"observed_at":"2026-08-11T12:49:37.522830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.02610","last_updated":"2020-01-08T16:45:09Z","snapshot_observed_at":"2026-08-12T01:33:52.396724Z","submitted_at":"2020-01-08T16:45:09Z","title":"iDLG: Improved Deep Leakage from Gradients","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.02610","snapshot_observed_at":"2026-08-11T12:49:37.527741Z","title":"idlg: Improved deep leakage from gradients,","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.527741Z"},"links":{"cited_paper":"/paper/2001.02610","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:00fb1ef46da512b7b501ef4a694e5b5f7fec0d2bd5bf0d6ff6942d9b2ed069cc","observation_id":"677ddfc3-fda7-4c12-b958-e11272e7dcda","resolution":{"observed_at":"2026-08-11T12:49:37.527741Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.07586","last_updated":"2021-04-15T16:43:17Z","snapshot_observed_at":"2026-08-14T11:39:26.510106Z","submitted_at":"2021-04-15T16:43:17Z","title":"See through Gradients: Image Batch Recovery via GradInversion","version":1},"cited_work":{"arxiv_id":"2104.07586","doi":null,"metadata_source":"pith","pith_arxiv_id":"2104.07586","snapshot_observed_at":"2026-08-11T12:49:38.128747Z","title":"See through Gradients: Image Batch Recovery via GradInversion","venue":"cs.LG","work_id":"99a25c3f-29d9-490d-b087-333feda46ccb","year":2021},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.537799Z"},"links":{"cited_paper":"/paper/2104.07586","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:6028afb6ca37c0e12c42d7811b26e89714fc47bb2f0345051ce171327ccb3995","observation_id":"8afc7cbb-6e81-4c3d-9d80-cbcd89677486","resolution":{"observed_at":"2026-08-11T12:49:38.134324Z","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":"1711.10677","last_updated":"2017-11-29T04:29:29Z","snapshot_observed_at":"2026-08-14T20:09:03.266453Z","submitted_at":"2017-11-29T04:29:29Z","title":"Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.10677","snapshot_observed_at":"2026-08-11T12:49:37.543591Z","title":"Private federated learn- ing on vertically partitioned data via entity resolution and additively homomorphic encryption,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.543591Z"},"links":{"cited_paper":"/paper/1711.10677","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:a643d07e416d2c880a732fe2c580ac421921c532c4c7a8b8f8bacb1b8089672e","observation_id":"e5eaa536-2cd4-4a49-b81b-5c9b0411a0b9","resolution":{"observed_at":"2026-08-11T12:49:37.543591Z","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":"2026-08-11T12:49:37.549828Z","title":"How to share a secret,","venue":null,"work_id":null,"year":1979},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.549828Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:16c741e6e621908413564ecd16ab7b824975aa78ea9c839c8f269807de74a6a9","observation_id":"5d3c6765-3d48-4145-ba85-c43304af0dfa","resolution":{"observed_at":"2026-08-11T12:49:37.549828Z","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":"2026-08-11T12:49:38.652649Z","title":"Safeguarding cryptographic keys,","venue":null,"work_id":"318a30a7-5e06-4acb-97ab-cd74b92dd360","year":1979},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.555733Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:4e928fea7311bbe1a7678ee55f6f4b6976bf6b1b45909d4bdeb27c1cdfda0834","observation_id":"545ac669-c464-4ee5-85cf-4087e17e3bcc","resolution":{"observed_at":"2026-08-11T12:49:38.657186Z","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":"2026-08-11T12:49:38.640410Z","title":"Practical secure aggregation for privacy-preserving ma- chine learning,","venue":null,"work_id":"fd72cf52-861a-44de-b7c0-8e244e10fa2b","year":2017},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.561626Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:d9156ada8611870a60b6c836fa9a2adda6ccc81876f0b66d98e99c32011e683c","observation_id":"9138b9ae-130b-45c1-855b-fc78e712eb63","resolution":{"observed_at":"2026-08-11T12:49:38.644482Z","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":"2026-08-11T12:49:38.627381Z","title":"Deep learning with differential privacy,","venue":null,"work_id":"4dfffd18-dcd2-43cd-8454-21a1024cd22c","year":2016},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.566959Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:e617b5297140cb60dd078bcb1360350a701897b4eb5fce978617a0248d4d3ef5","observation_id":"868e0bc2-84ff-4bce-af96-964369fb3c2f","resolution":{"observed_at":"2026-08-11T12:49:38.631935Z","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":"2026-08-11T12:49:38.614129Z","title":"Deep gradient compression: Reducing the communication band- width for distributed training,","venue":null,"work_id":"30e0c036-50f5-427b-8e46-fbdac96b932e","year":2018},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.580201Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:ccfb7e37ef3aa7d9eb806a7192cd71e99c9cf2d682763fd256fa73d239db1678","observation_id":"4750cd40-56a9-45b6-8e2e-14e53f964659","resolution":{"observed_at":"2026-08-11T12:49:38.619096Z","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":"2026-08-11T12:49:38.601593Z","title":"Gradient disaggregation: Breaking privacy in federated learning by reconstructing the user participant matrix,","venue":null,"work_id":"137f7ee9-6d6c-4119-8255-2c32d6fd296b","year":2021},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.584516Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:75fc4394d4a1ba407a56d0630b295b1b84c059e67fd55c9d1216a700f4588db1","observation_id":"ea1be1b1-83e9-4e18-a8bf-a62845f8e7f2","resolution":{"observed_at":"2026-08-11T12:49:38.606025Z","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":"2026-08-11T12:49:38.588930Z","title":"Gradient- leakage resilient federated learning,","venue":null,"work_id":"f3178b8a-56b1-496e-a92d-05f0d060f534","year":2021},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.589942Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:02f0356cc288ac79269a2d3c4b7468591db51f54e3f3621638c59998218fe56a","observation_id":"702bd2fe-cc63-453d-8a24-1e6d026bf0f7","resolution":{"observed_at":"2026-08-11T12:49:38.593242Z","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":"2026-08-11T12:49:38.576210Z","title":"Differentially private federated learning on heterogeneous data,","venue":null,"work_id":"5f9d9e15-fb8c-473c-b20e-e1ce95e579e3","year":2022},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.594562Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:5cf1c3a5a90da2816712adcae7473b1e758dbbb6e886887643c8096368a29bdd","observation_id":"15705edb-9d1a-403a-9e98-faeae1fc9e49","resolution":{"observed_at":"2026-08-11T12:49:38.580528Z","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":"2026-08-11T12:49:38.563567Z","title":"A fine-grained differentially private federated learning against leakage from gradients,","venue":null,"work_id":"1e7da208-7a4d-42fc-8ff0-b2960fbf4ff7","year":2021},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.600304Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:81f156422d3895443284f4dac2448dc310e8a1f4ae07b7d4fbdef70321ab1f91","observation_id":"4f4cec85-0c87-4227-84c7-ff0781f6b5f0","resolution":{"observed_at":"2026-08-11T12:49:38.567626Z","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":"2026-08-11T12:49:37.606663Z","title":"Performance-enhanced federated learning with differential privacy for internet of things,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.606663Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:9e14f0ec058b3798eaa2d75cccb3018910a3cae7c94ca728c6b3bc35cb601c4c","observation_id":"253742e9-329a-428e-bf9d-a2c919358152","resolution":{"observed_at":"2026-08-11T12:49:37.606663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03385","last_updated":"2015-12-10T19:51:55Z","snapshot_observed_at":"2026-07-06T04:39:28.429064Z","submitted_at":"2015-12-10T19:51:55Z","title":"Deep Residual Learning for Image Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03385","snapshot_observed_at":"2026-08-11T12:49:37.611558Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.611558Z"},"links":{"cited_paper":"/paper/1512.03385","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:bc68c56e4c579d6c42d284aec8cfec32d5e5c6ba5cd8149d559a3e7e40e85b10","observation_id":"05d15179-062d-4dc5-a6d5-4b7487145c54","resolution":{"observed_at":"2026-08-11T12:49:37.611558Z","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":"2026-08-11T12:49:38.545829Z","title":"mixup: Beyond empirical risk minimization,","venue":null,"work_id":"e70f4653-3a5f-4c68-899b-8cf23c5f6cd5","year":2017},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.620145Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:9305a921a214dd3af3011371f6ca4b31607f3583861a4ddbe7f0f4b1b6de8942","observation_id":"3f328b1d-1546-4239-ae7f-bd17c202427e","resolution":{"observed_at":"2026-08-11T12:49:38.549806Z","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":"2026-08-11T12:49:38.534187Z","title":"Between-class learning for image classification,","venue":null,"work_id":"385db19b-5cdc-49cf-b26e-f7ce197d9ba2","year":2018},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.625703Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:a6a083fef17ee3a63d2432408e27f7680daac238eeeed4dee10c4c528c078647","observation_id":"6d19be51-7b96-499b-a471-af08658e2680","resolution":{"observed_at":"2026-08-11T12:49:38.538395Z","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":"2026-08-11T12:49:38.523363Z","title":"Mixup as locally linear out-of-manifold regularization,","venue":null,"work_id":"8f36749f-3e12-4122-9224-896e32612fc3","year":2019},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.631289Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:17fd533284fe6a0b14a0fe53e24b02b6cc7c2ae2e8c51d1f2469adaa85c51d05","observation_id":"3d6ea715-51f5-4ce3-9933-87651603fc31","resolution":{"observed_at":"2026-08-11T12:49:38.527137Z","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":"2026-08-11T12:49:38.511113Z","title":"Autoaugment: Learning augmentation policies from data,","venue":null,"work_id":"a8402de0-582b-4cba-bd87-2f43887b77ec","year":2018},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.635528Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:a9c0cf994c90846c5c97235ed8ad0c908fa9d00c54aa0fb326728e8bf7643e75","observation_id":"fc0588a6-3e12-4768-a4ca-b675ab5da2c0","resolution":{"observed_at":"2026-08-11T12:49:38.516385Z","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":"1912.02781","last_updated":"2020-02-17T06:16:13Z","snapshot_observed_at":"2026-08-14T11:38:20.162100Z","submitted_at":"2019-12-05T18:18:10Z","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.02781","snapshot_observed_at":"2026-08-11T12:49:37.640835Z","title":"Augmix: A simple data processing method to improve robustness and uncertainty,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.640835Z"},"links":{"cited_paper":"/paper/1912.02781","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:b693638cdd45e21aeeb8bb64c18d5d9378b3015b893abf4aeec27c822ccc3015","observation_id":"0e621f61-5572-450b-b61f-842b26d1856d","resolution":{"observed_at":"2026-08-11T12:49:37.640835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.09979","last_updated":"2022-06-20T19:47:43Z","snapshot_observed_at":"2026-08-13T16:17:31.466117Z","submitted_at":"2022-06-20T19:47:43Z","title":"Mitigating Data Heterogeneity in Federated Learning with Data Augmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.09979","snapshot_observed_at":"2026-08-11T12:49:37.646959Z","title":"Mitigating data heterogeneity in federated learning with data augmentation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.646959Z"},"links":{"cited_paper":"/paper/2206.09979","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:a0620332d71ab46b01b3d844cb2424196590880a2d0cd4f2f7a1b99c1acff512","observation_id":"552dc4f7-515c-4d6c-8a0b-f580548cd1b5","resolution":{"observed_at":"2026-08-11T12:49:37.646959Z","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":"2026-08-11T12:49:38.498728Z","title":"Data- augmentation-based federated learning,","venue":null,"work_id":"20494444-d522-4efa-98c0-0202eb52e0bf","year":2023},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.652770Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:fb83c7cf2be92564355782c1bfe2456616fe374565114dd7ecb5f4e9ea5877e4","observation_id":"01301d40-3dda-4fb2-8d7b-83243fe10274","resolution":{"observed_at":"2026-08-11T12:49:38.503234Z","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":"2026-08-11T12:49:37.657224Z","title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.657224Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:8e39ec84d7cd68dd95cf68f98cc60ed5e3df955760dd718eee5ac464c027c93a","observation_id":"01d40d91-ed0a-413d-9c06-17c70fc3ecdb","resolution":{"observed_at":"2026-08-11T12:49:37.657224Z","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":"2026-08-11T12:49:38.487337Z","title":"Exploiting unintended feature leakage in collaborative learning,","venue":null,"work_id":"8623649a-9d4d-4230-b8b8-e405903b2e88","year":2019},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.661343Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:47ac6507a3f3e0289c3656e714b944e5bc3aff5f69d21707b0597a8c2a40539c","observation_id":"ab785b6e-4ff5-4487-9dad-29603fcd25d9","resolution":{"observed_at":"2026-08-11T12:49:38.491274Z","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":"2026-08-11T12:49:38.473751Z","title":"Model inversion attacks that exploit confidence information and basic countermeasures,","venue":null,"work_id":"a387dd18-398c-4a40-94d2-5d58188650d3","year":null},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.665193Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:7cb1ee7542aab2c2a3465da7c18482864a142fbae68c3851400e3ea10cb7f0a0","observation_id":"1a82f7a5-d738-4482-a50e-cdf136b4da0a","resolution":{"observed_at":"2026-08-11T12:49:38.479140Z","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":"2026-08-11T12:49:38.448509Z","title":"Information theory and privacy in data banks,","venue":null,"work_id":"73c7184e-1990-42c2-91f6-5b63e305c372","year":1973},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.675231Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:be930802b5fbe5d87ac014f68bc42922b152b92668b7340a45fba883d7783e60","observation_id":"be7186f0-be90-4a33-8918-86df2ad2792f","resolution":{"observed_at":"2026-08-11T12:49:38.452941Z","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":"2026-08-11T12:49:38.435241Z","title":"A source coding problem for sources with additional outputs to keep secret from the receiver or wiretappers (corresp.),","venue":null,"work_id":"b1dfb745-91ff-4b86-8154-b43753b21325","year":1983},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.681541Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:91e8cf67a26e2b0a76af3fb3cf731a5293185767e3c5c6a2455e8c2f36068d4b","observation_id":"e03cfe65-5468-455c-8d71-4a20a5731391","resolution":{"observed_at":"2026-08-11T12:49:38.439892Z","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":"2026-08-11T12:49:38.423478Z","title":"Utility- privacy tradeoffs in databases: An information-theoretic approach,","venue":null,"work_id":"a7b9d85e-5b8b-497f-98e5-5a9f2b58cd29","year":2013},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.689902Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:976311fd7a51109e0193519fe1656a5350468e77e7e5de6a839fe05a567faa3a","observation_id":"5853e22b-4306-4449-b52d-4158e4e69f00","resolution":{"observed_at":"2026-08-11T12:49:38.427876Z","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":"2026-08-11T12:49:38.409815Z","title":"On the relation between identifiability, differential privacy, and mutual- information privacy,","venue":null,"work_id":"891d11eb-0f56-4324-a8b6-fc9e6e054912","year":2016},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.694210Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:a349f6d9c8ef97e5ddc5143e06eee574babe28ee7e1021a567cef7982a0c8683","observation_id":"64549d0d-2ccd-40de-99ba-0ea0f10ccfd2","resolution":{"observed_at":"2026-08-11T12:49:38.415237Z","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":"2026-08-11T12:49:38.397671Z","title":"An estimation-theoretic view of privacy,","venue":null,"work_id":"195d8c60-a3b8-4244-b210-8b0d74cd4b93","year":2017},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.699154Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:62c7d7cdfefe7d759c953ddd4ba0c5e9d92cdc2e5694baff11ed87cdd82d4be5","observation_id":"9e2bcc57-09a6-455c-b022-86f1b6b6aa9f","resolution":{"observed_at":"2026-08-11T12:49:38.401596Z","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":"2209.00230","last_updated":"2023-02-21T10:34:18Z","snapshot_observed_at":"2026-08-13T14:34:51.193663Z","submitted_at":"2022-09-01T05:20:04Z","title":"Trading Off Privacy, Utility and Efficiency in Federated Learning","version":3},"cited_work":{"arxiv_id":"2209.00230","doi":null,"metadata_source":"pith","pith_arxiv_id":"2209.00230","snapshot_observed_at":"2026-08-11T12:49:37.842132Z","title":"Trading Off Privacy, Utility and Efficiency in Federated Learning","venue":"cs.LG","work_id":"58841b7f-0199-43be-87f6-527c47a760ca","year":2022},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.703920Z"},"links":{"cited_paper":"/paper/2209.00230","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:8c227b063ed042da41988b00396591a3e95d4a44d67dcec5997e41636fba1c21","observation_id":"af955242-ad66-4798-8813-508603951c07","resolution":{"observed_at":"2026-08-11T12:49:37.847160Z","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":"2026-08-11T12:49:38.384829Z","title":"Learning privacy preserving encodings through adversarial training,","venue":null,"work_id":"2d3a7062-711e-40fd-b19c-1840da3a7246","year":2019},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.708876Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:c53c2b0118d2176fe94c2497fda0063eb388f33a741bac4280178ca81e873944","observation_id":"2586436d-54f4-471f-a73b-94efb03043ae","resolution":{"observed_at":"2026-08-11T12:49:38.389227Z","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":"2026-08-11T12:49:38.370298Z","title":"Fl- 11 apb: Balancing privacy protection and performance optimization for adversarial training in federated learning,","venue":null,"work_id":"1bf1c646-7d18-4d6a-905c-39a85adfac04","year":2024},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.712987Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:12d903663f4afe28286e96631827eefe5b59968064c91ce63053bfaf4554c8f4","observation_id":"edce0f01-dff4-4277-8d4a-0c01febfb2a3","resolution":{"observed_at":"2026-08-11T12:49:38.375378Z","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":"2305.15148","last_updated":"2023-06-03T12:35:57Z","snapshot_observed_at":"2026-08-13T11:34:26.794498Z","submitted_at":"2023-05-24T13:44:02Z","title":"Theoretically Principled Federated Learning for Balancing Privacy and Utility","version":2},"cited_work":{"arxiv_id":"2305.15148","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.15148","snapshot_observed_at":"2026-08-11T12:49:37.819172Z","title":"Theoretically Principled Federated Learning for Balancing Privacy and Utility","venue":"cs.LG","work_id":"d8bf4d50-fdd2-4f2d-9122-5f46abdbb8bc","year":2023},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.717065Z"},"links":{"cited_paper":"/paper/2305.15148","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:4e6c71fa9ee3f9813aadb7fec9bf761e366919ea174e576f7feb984dd6a9a76c","observation_id":"08826c0d-6f3a-4a4c-b4d5-a0a62e59a5d9","resolution":{"observed_at":"2026-08-11T12:49:37.826434Z","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":"1710.09412","last_updated":"2018-04-27T21:39:25Z","snapshot_observed_at":"2026-08-08T10:28:19.597631Z","submitted_at":"2017-10-25T18:30:49Z","title":"mixup: Beyond Empirical Risk Minimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.09412","snapshot_observed_at":"2026-08-11T12:49:37.723203Z","title":"mixup: Beyond empirical risk minimization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.723203Z"},"links":{"cited_paper":"/paper/1710.09412","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:bb00a06b3cdd10a98ec8cd2b373c223b624c6627b61857f136826c5de57bd673","observation_id":"fa7fa78c-64b1-4828-9d80-4056da3b516f","resolution":{"observed_at":"2026-08-11T12:49:37.723203Z","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":"2026-08-11T12:49:38.355301Z","title":"Data augmentation: A comprehensive survey of modern approaches,","venue":null,"work_id":"4da9c53c-56bf-46c4-9719-ad2bf17c0a4e","year":2022},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.732257Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:5ac5304920f994266e3be7a630e3cf1272d48d34fa48846b62c1181ce1c247c2","observation_id":"e7345a60-acf2-403c-81f8-13b08c26a51c","resolution":{"observed_at":"2026-08-11T12:49:38.360054Z","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":"2026-08-11T12:49:38.336971Z","title":"Learning with pseudo-ensembles,","venue":null,"work_id":"61144ed1-99e4-4b80-8e73-51f445822a81","year":2014},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.737126Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:906d6374dc4dba65bc904cdc7fb5bc8c257252e62261c103b778a038dacfbf70","observation_id":"793990a7-611b-4407-a681-3d9594deeb10","resolution":{"observed_at":"2026-08-11T12:49:38.341344Z","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":"2026-08-11T12:49:38.305198Z","title":"Improv- ing the robustness of deep neural networks via stability training,","venue":null,"work_id":"04606806-4a76-475f-89a6-aeb791721cdd","year":2016},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.747504Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:31551c6f9ac6c0092ea718a4f17e2dcc58b60eddc7f381cdaf7b7421d30d010c","observation_id":"5a77e4b6-477f-4ee3-8958-b3bc0430f568","resolution":{"observed_at":"2026-08-11T12:49:38.310160Z","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":"2026-08-11T12:49:38.288365Z","title":"Adversarial logit pairing,","venue":null,"work_id":"d091b6cb-1c20-4afa-bb59-77a2dd013000","year":2018},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.751426Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:4106bd3680fbf7a702c683d672f4cf5a1434a5119c705a398532647be1eaf7ad","observation_id":"cc81a331-ead7-4d31-b48f-cfd01dc53774","resolution":{"observed_at":"2026-08-11T12:49:38.294017Z","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":"2026-08-11T12:49:38.270753Z","title":"Mnist hand- written digit database,","venue":null,"work_id":"12d6db10-1806-4d13-9aca-19606242a8dc","year":2010},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.755723Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:2d552c1d1514c7caf5286362f1b866eb042938a80be584cb626378c4cf7837e4","observation_id":"64e65f9a-23f4-4bf9-998a-05815c40c1d8","resolution":{"observed_at":"2026-08-11T12:49:38.275981Z","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":"2026-08-11T12:49:37.760747Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.760747Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:99e93e03b0aa67e481daa1dd1d423e8a14c7788725cf0ce0e7b827f59e16d351","observation_id":"5013f4eb-50b0-4fbc-ab82-027d086175ff","resolution":{"observed_at":"2026-08-11T12:49:37.760747Z","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":"2026-08-11T12:49:38.240001Z","title":"Gradient- based learning applied to document recognition,","venue":null,"work_id":"69e02c19-54e8-4627-b3f3-a6d2ccfe846d","year":1998},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.765070Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:cd973e3c056fb8b5b5cb7055734a97b60ccc66f58dd4b1ddbd921c0e4a4a5131","observation_id":"3304816b-0f50-45a0-a249-b4c526fd88f4","resolution":{"observed_at":"2026-08-11T12:49:38.244908Z","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":"2026-08-11T12:49:38.461379Z","title":"Available: https://api.semanticscholar.org/ CorpusID:207229839","venue":null,"work_id":"f884e24a-db37-4a12-8c02-22702b4e95e8","year":null},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.669816Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:f175783b62b194d5c18c2b16290947042339a824ac4a010ae63621c131eaf6b9","observation_id":"8891a695-78b8-4b88-99ea-e72d483ad797","resolution":{"observed_at":"2026-08-11T12:49:38.465493Z","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":"2026-08-11T12:49:38.665661Z","title":"Available: https://api.semanticscholar.org/ CorpusID:210064455","venue":null,"work_id":"b94a66a3-4063-43e9-b8c9-3883d3326577","year":null},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.532904Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:9e3b868154350524db143caa3d3b79182d3d61ca2d2669d9981b8d82c1d867d3","observation_id":"79aa42e4-bbdf-4b48-984d-d3e744d82ef6","resolution":{"observed_at":"2026-08-11T12:49:38.670626Z","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":"2026-08-11T12:49:38.322214Z","title":"Available: http://papers.nips.cc/paper/ 5487-learning-with-pseudo-ensembles.pdf","venue":null,"work_id":"5ba961b0-d829-43e8-9f43-67fe93625229","year":null},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":3373,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.742719Z"},"links":{"citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:03092d77df65a56b580560df0b80a13e6909bcc613fd45fb58c305252817a84f","observation_id":"20f577e7-2d9c-4413-a2d1-f92cb0552645","resolution":{"observed_at":"2026-08-11T12:49:38.326751Z","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":"2412.13818","last_updated":"2024-12-18T13:05:55Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-14T11:39:09.360133Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation"},"reference_resolution":{"displayed":50,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":3,"verified_fuzzy":31},"total_outbound_references":50},"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 15 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 0 inbound Pith citation observations for arXiv:2412.13818."}