{"as_of":"2026-08-09T14:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a661f419c9cf95724b8335f80b5c23522e30c53304f970a3618ffee21ec89d91","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T11:13:58.916649Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2502.08008/citation-record","integrity":"/paper/2502.08008/integrity","json":"/paper/2502.08008/citation-record.json","paper":"/paper/2502.08008"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T11:13:59.370257Z","title":"When moe meets llms: Parameter efficient fine-tuning for multi-task medical applications,","venue":null,"work_id":"c39b3296-206a-4bec-9445-daeeac775259","year":2024},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.811822Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:ce6632566385d2f60183606b00a016855477c1ca11094b021e73756099c75e04","observation_id":"fc96d55b-9bb5-4870-91a9-9e925440b70f","resolution":{"observed_at":"2026-08-08T11:13:59.374174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.359483Z","title":"Reconstructing training data with informed adversaries,","venue":null,"work_id":"f8515360-226c-4ccd-aeca-8070f30b6d2e","year":2022},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.815871Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:53c9b231da75ee7afa2fe6b175ac292c9734f1e98dbd10030e13484878799023","observation_id":"571c7c6c-0ee2-40f6-a2b0-7e14cc5e1564","resolution":{"observed_at":"2026-08-08T11:13:59.363276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.347602Z","title":"Bounding training data reconstruction in dp-sgd,","venue":null,"work_id":"3c884af0-0bc5-4140-8b02-93ce0aa7d559","year":2024},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.819633Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:5ff1ead8d2694e2f8b24cc224045e6607353661a98467ea63acfd6717d06c919","observation_id":"cf344155-46b3-41a3-bb5b-8767cb0917f6","resolution":{"observed_at":"2026-08-08T11:13:59.351896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.336313Z","title":"Machine learning with membership privacy using adversarial regularization,","venue":null,"work_id":"0319a6c3-a826-4193-96e7-5badcf55bfa2","year":2018},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.823115Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:f6bfbf1e6c3934c5b47f47b77ebef45f2d5351d43ba2147da0dce60df26eb87d","observation_id":"5d46263b-6c12-4c60-a6a7-2f1ceac8706f","resolution":{"observed_at":"2026-08-08T11:13:59.340379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.324738Z","title":"Privacy risk in machine learning: Analyzing the connection to overfitting,","venue":null,"work_id":"38cadc3a-cb98-4403-aaf0-f5e0b7c6db5a","year":2018},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.826934Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:a579a45e5791fe9dc822a150b4f83b226c86670112fea16e84fbd1f9463702f8","observation_id":"91b02849-286f-4410-b4f4-c012eeb29369","resolution":{"observed_at":"2026-08-08T11:13:59.328750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.310682Z","title":"The secret sharer: Evaluating and testing unintended memorization in neural networks,","venue":null,"work_id":"e0692ce1-666d-4cc4-8a80-e25fa85a5284","year":2019},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.831275Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:4ae2eff84c0c5cbd7e16492dd3cea61bce812c48e05c1dd726ac3f5fe422dc2d","observation_id":"9ce7542f-1005-4c1a-9a38-3ab219b27158","resolution":{"observed_at":"2026-08-08T11:13:59.315434Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.298675Z","title":"Ex- tracting training data from large language models,","venue":null,"work_id":"1c512d80-c6ba-4792-9b13-a1047a3f6f7f","year":2021},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.835515Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:201241793fbc69e22164423400daeb501b65c90b7f31a26ba668c6d08d572c8c","observation_id":"f61e2055-ca06-40af-9836-ff24d11936d9","resolution":{"observed_at":"2026-08-08T11:13:59.302571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.287859Z","title":"Calibrating noise to sensitivity in private data analysis,","venue":null,"work_id":"32dc3c48-1719-4edc-9dc3-51a25e193d62","year":2006},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.839233Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:305906246546c0c379e1905649375f0d820bf7b5e5bd66ef0c0d42ac7ed9720e","observation_id":"cc2111c0-e726-47fd-890f-e410dc43aa0c","resolution":{"observed_at":"2026-08-08T11:13:59.291784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.276252Z","title":"Limits of computa- tional differential privacy in the client/server setting,","venue":null,"work_id":"45ff6262-4fa0-4c4b-8e33-707f00ec0179","year":2011},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.843373Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:4748b9dc4b164ad9a18bf78d63254dc427aebae7974b3d518d3b4e6689617d01","observation_id":"e36be104-4bba-4361-b25c-847f51b23ae1","resolution":{"observed_at":"2026-08-08T11:13:59.280226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.02903","last_updated":"2018-12-07T04:18:12Z","snapshot_observed_at":"2026-08-08T16:17:30.311416Z","submitted_at":"2018-12-07T04:18:12Z","title":"Applied Federated Learning: Improving Google Keyboard Query Suggestions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.02903","snapshot_observed_at":"2026-08-08T11:13:58.847312Z","title":"Applied federated learning: Improving google keyboard query suggestions,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.847312Z"},"links":{"cited_paper":"/paper/1812.02903","citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:e997e94ceef94a1e2ab62c3c0f97147a9367e8a19bc03df9c1965234bff435f2","observation_id":"2e9bd173-ae6d-400f-8120-acdc1f4c08c0","resolution":{"observed_at":"2026-08-08T11:13:58.847312Z","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":"2026-08-08T11:13:59.264644Z","title":"Differentially pri- vate stochastic gradient descent with fixed-size minibatches: Tighter RDP guarantees with or without replacement,","venue":null,"work_id":"a94eda36-7f05-48c1-99d4-a617e56737e2","year":2024},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.851526Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:559189c2cb4bc84308be4e16ef814a30feded345b1987774bddd7a5a910f3803","observation_id":"1ab4b796-4b46-4343-a790-fb5e8214eaed","resolution":{"observed_at":"2026-08-08T11:13:59.268856Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.252407Z","title":"R ´enyi differential privacy,","venue":null,"work_id":"05917756-ec11-48f5-9762-82bfd805ab13","year":2017},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.855187Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:933072d33670b165caa05119a6f276e9273bb142c392666bb8143756b38a36a6","observation_id":"98f8c532-38a0-4114-83d9-073858bf5b9d","resolution":{"observed_at":"2026-08-08T11:13:59.256188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:58.859471Z","title":"Client selection in federated learning: Principles, challenges, and opportunities,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.859471Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:97a523cc30ea1394d8474a6039672baaeefe23b221e7066c395808ab85075cc3","observation_id":"fed9f81f-0c8a-4f24-8c1d-55cc73a83663","resolution":{"observed_at":"2026-08-08T11:13:58.859471Z","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":"2026-08-08T11:13:59.232740Z","title":"Vehicle selection and resource optimization for federated learning in vehicular edge computing,","venue":null,"work_id":"c4f2c4a2-26ad-434f-8c9e-1262ffbf35b7","year":2021},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.862872Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:e91c2d6470c1a598e346399f95d410a18c13f77d434bb0d0e7f4914bc55913b1","observation_id":"66ca20ec-f454-4875-a278-38e908746abd","resolution":{"observed_at":"2026-08-08T11:13:59.237168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.219555Z","title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding,","venue":null,"work_id":"b66c4f8b-fdb9-4d93-8c06-927cbb8a2ad4","year":2019},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.866550Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:04d0dc6f9bd8504b4d0a9f6298afd9bae4be0fb3bb59501cdbccdec693bc15a4","observation_id":"7d59c149-b392-48ce-989f-0fee82319200","resolution":{"observed_at":"2026-08-08T11:13:59.224718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.207667Z","title":"Ew- tune: A framework for privately fine-tuning large language models with differential privacy,","venue":null,"work_id":"fe61818b-b729-4809-b756-e3352661772c","year":2022},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.870127Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:e42c40cf44973659d824606aa40a61e6c135c530cc657174d08dd72d8b492cc0","observation_id":"5da65edb-f8c9-46aa-90bd-efd554a48ca3","resolution":{"observed_at":"2026-08-08T11:13:59.211721Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-08-08T11:13:58.873653Z","title":"Differentially private fine-tuning of language models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.873653Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:a3b329daf7f511912edc627f77bc2a43db7ad2f611e36227cdb75e02465bbc72","observation_id":"2fdc81cb-ecb6-4630-bd61-32d7aabb480b","resolution":{"observed_at":"2026-08-08T11:13:58.873653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-08T11:13:58.877372Z","title":"Bert: Pre- training of deep bidirectional transformers for language understand- ing,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.877372Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:65684eb7795b0678f7a8dbb25781a126cf1e0611ebbcf29908689642afab2bfa","observation_id":"a923853b-8a62-4b9e-b3fa-a8e2f0e5bc29","resolution":{"observed_at":"2026-08-08T11:13:58.877372Z","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":"2026-08-08T11:13:59.086172Z","title":"Communication-efficient learning of deep networks from decentral- ized data,","venue":null,"work_id":"e25f7d2b-f81e-4ea9-8056-b17ec0f8ea45","year":2017},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.881538Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:e2ff1cb48b2285e6bef65a15941cc223a73cbd2f1af7f06aabe686fcfe8f5e14","observation_id":"f9c07951-3d69-4e3f-9021-bcafa92864c9","resolution":{"observed_at":"2026-08-08T11:13:59.090325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.074739Z","title":"The algorithmic foundations of differential privacy,","venue":null,"work_id":"4818f94f-3952-4484-b0fa-78fb92f945e3","year":2014},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.885880Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:627d81114b4a3f7c1855bc6595cc6a869b0f7c0bf4d60d52dc4eabf8f12e3725","observation_id":"224909c1-ac47-413e-946f-45659c601539","resolution":{"observed_at":"2026-08-08T11:13:59.078861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:58.889739Z","title":"Deep learning with differential privacy,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.889739Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:2c865f9dcf0be80ab42ed8a858ef0fef3ee5e52899dff21b52271bfb25f98700","observation_id":"d908732e-e271-4847-b49e-e09e1ae566bb","resolution":{"observed_at":"2026-08-08T11:13:58.889739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1603.01887","last_updated":"2016-03-16T16:29:29Z","snapshot_observed_at":"2026-08-06T12:58:02.116480Z","submitted_at":"2016-03-06T22:41:12Z","title":"Concentrated Differential Privacy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1603.01887","snapshot_observed_at":"2026-08-08T11:13:58.894146Z","title":"Concentrated differential privacy,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.894146Z"},"links":{"cited_paper":"/paper/1603.01887","citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:c4d4d9c92c4baaf1a0755db368bbbc2e2fa53c3ac946aecdee9bd2a6b0a174c4","observation_id":"d09bb585-e3bb-4d30-bc9a-ed71009b1a67","resolution":{"observed_at":"2026-08-08T11:13:58.894146Z","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":"2026-08-08T11:13:59.055270Z","title":"https://opacus.ai/docs/introduction, Last accessed on 2025-1-8","venue":null,"work_id":"2930737b-a8d5-4596-b4c4-3f728c55f0a6","year":2025},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.898123Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:936d45027f32c9d9d26a747ee620e331514456d01209dcd0820be0352d14951c","observation_id":"c715fb67-517b-46a1-8d99-7f0f339ff4fd","resolution":{"observed_at":"2026-08-08T11:13:59.059519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.042961Z","title":"Privacy amplification by sub- sampling: Tight analyses via couplings and divergences,","venue":null,"work_id":"3156235f-a429-4f87-9f96-78d19265890c","year":2018},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.901721Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:d3bac4fcb4a52fb523182b61cf58c1e3a5bab97ad2a4d199138cbe8519073924","observation_id":"a34920db-fc52-4f09-98ee-f9316a7c56bd","resolution":{"observed_at":"2026-08-08T11:13:59.047021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.030538Z","title":"Subsampled r´enyi differential privacy and analytical moments accountant,","venue":null,"work_id":"03575913-81ae-40bb-9767-9a0bf32249b0","year":2019},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.905501Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:d0f8216dd9e334affbecce3bb3cd43714d4b1391c6ef557fd31316faa1e9bde0","observation_id":"29b889c5-5b08-4b9a-8a49-f0811931c840","resolution":{"observed_at":"2026-08-08T11:13:59.034949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.018253Z","title":"Bayesian differential privacy for ma- chine learning,","venue":null,"work_id":"6cf93dc7-eb12-49b7-af1e-4c4928474d52","year":2020},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.909407Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:b0053dd0ab470b858f89b571472f1f282c20b3d1f80c547534af0f3000505a13","observation_id":"c29427eb-94e2-4f44-bd56-8fd747c30734","resolution":{"observed_at":"2026-08-08T11:13:59.022268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:59.005492Z","title":"Superglue: A multi-task benchmark and analysis platform for natural language understanding,","venue":null,"work_id":"8a8c6087-f47d-4ad5-8d69-0a7082576414","year":2019},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.913030Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:c4fe658199f7896790f8f0e974ea47d50fe5f6f4006e5d54b1b8f72c5f4a1add","observation_id":"2d00bf06-bc54-48df-b874-2f80b1fa9ffa","resolution":{"observed_at":"2026-08-08T11:13:59.009550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-08T11:13:58.988418Z","title":"Recursive deep models for semantic compositionality over a sentiment treebank,","venue":null,"work_id":"042e33f2-f7b4-42c9-bfb0-8cfdd7994671","year":2013},"citing_paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T11:13:58.916649Z"},"links":{"citing_paper":"/paper/2502.08008"},"observation_digest":"sha256:e1f32a2a5ce997684bf94660937b8e755a6aab528d3b80d1d8b4c9baa2c9d99c","observation_id":"2eb36726-c627-412d-a921-408a9a4a4e1e","resolution":{"observed_at":"2026-08-08T11:13:58.995620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.08008","last_updated":"2025-02-14T18:52:34Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T11:07:41.002345Z","submitted_at":"2025-02-11T23:07:14Z","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":22},"total_outbound_references":28},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2502.08008."}