{"as_of":"2026-08-08T20:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:85cbde089a29f2b907a4101337ec52ea5a34bf5d559e61fdd021f5b95b7e969c","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T13:23:20.185349Z","state":"measured"},{"denominator":26,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":26,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2510.01137/citation-record","integrity":"/paper/2510.01137/integrity","json":"/paper/2510.01137/citation-record.json","paper":"/paper/2510.01137"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:23:18.227875Z","title":"Deep learning with differential privacy","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:18.227875Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:f40b16dcd42f851ed44ff14e11241e8e58ddd5a25e1fa7df790157179d5ddf0e","observation_id":"600ca78e-40ef-49c0-ba98-30bc34bce595","resolution":{"observed_at":"2026-08-04T13:23:18.227875Z","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":"2026-08-04T13:23:18.335026Z","title":"Eigenvalues of large sample covariance matrices of spiked population models","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:18.335026Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:449dcc577983321716a26e42fb8137b5afea052d14c2ad11521b6fe8885b4170","observation_id":"40919b85-343e-41a3-b4b4-d0c3f23be60e","resolution":{"observed_at":"2026-08-04T13:23:18.335026Z","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":"2026-08-04T13:23:18.456895Z","title":"Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:18.456895Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:7a4e55fe845214b2d92ceb99ddb4d47ac4924074e15514116bed7a6ec43ba58d","observation_id":"db2aba6e-65dd-489b-8fc7-9d5018f3a316","resolution":{"observed_at":"2026-08-04T13:23:18.456895Z","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":"2026-08-04T13:23:18.618556Z","title":"Improving the G aussian mechanism for differential privacy: Analytical calibration and optimal denoising","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:18.618556Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:d3b0e686857f6788d84bf8d868309fe7712b23b56f6e2d0bbdab4d8d846c1fd1","observation_id":"67656f11-20df-4eb3-ab5a-cc692c3d46cf","resolution":{"observed_at":"2026-08-04T13:23:18.618556Z","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":"2026-08-04T13:23:18.779020Z","title":"The singular values and vectors of low rank perturbations of large rectangular random matrices","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:18.779020Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:36a0d3ce39f1ffaf68e5c78218299e8f0c2f7517f009481d9ec0ff168b9470f1","observation_id":"4756ac33-7e8d-4074-b7ae-ee70b97e11ec","resolution":{"observed_at":"2026-08-04T13:23:18.779020Z","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":"2026-08-04T13:23:18.831227Z","title":"On the convergence and calibration of deep learning with differential privacy","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:18.831227Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:3c85cfb9a0230e9760ce992a9629ca1a61738e20af54221a7f2e0e026e8d6adc","observation_id":"25f31821-1e43-445c-a853-0cf6af2a29dc","resolution":{"observed_at":"2026-08-04T13:23:18.831227Z","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":"2026-08-04T13:23:18.901265Z","title":"Extracting training data from large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:18.901265Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:62276c68dad0e5262b58b792cde8cb1e5a7554e85ff6796ccad876e22a49b003","observation_id":"f737e626-21c0-4b45-a0c6-d2210e4bcad7","resolution":{"observed_at":"2026-08-04T13:23:18.901265Z","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":"2026-08-04T13:23:19.050314Z","title":"Membership inference attacks from first principles","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.050314Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:c3a149abb49f9525d4c75277b878c348a2168f80bfc18f6e202c5d6c18bfad55","observation_id":"e45c750e-5769-43bf-98f5-ffb8878df95a","resolution":{"observed_at":"2026-08-04T13:23:19.050314Z","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":"2026-08-04T13:23:19.127132Z","title":"Optimal shrinkage of eigenvalues in the spiked covariance model","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.127132Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:5d65c59c0c244e7241ef3e3a4e64145543fef91d192df2b267d3f4af519358ae","observation_id":"54f5582e-ed06-414c-990f-eb61078c2af2","resolution":{"observed_at":"2026-08-04T13:23:19.127132Z","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":"2026-08-04T13:23:19.166441Z","title":"The algorithmic foundations of differential privacy","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.166441Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:59763e2179fcef180d134d7c52400dfa14eb9f2375f1830498f25a02d4ffcdd2","observation_id":"25f2e030-451a-4ef6-aa31-0de78911445f","resolution":{"observed_at":"2026-08-04T13:23:19.166441Z","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":"2026-08-04T13:23:19.196378Z","title":"The optimal hard threshold for singular values is 4/ 3","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.196378Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:fbb89e1cda5283ccd5905653740ca726fe6e13e96d880cdde1a63ce27d1bad77","observation_id":"c3382dc7-5d91-486b-a43a-6ff058778854","resolution":{"observed_at":"2026-08-04T13:23:19.196378Z","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":"2026-08-04T13:23:19.228909Z","title":"Numerical composition of differential privacy","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.228909Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:6e1496baf48bf2f584bc68e33f482097f727efc3a4df42ed4a41a24399b793b4","observation_id":"1330eee9-318c-41f8-add0-7e5d8850defb","resolution":{"observed_at":"2026-08-04T13:23:19.228909Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.05679","last_updated":"2022-11-10T18:42:34Z","snapshot_observed_at":"2026-08-08T11:17:29.711698Z","submitted_at":"2021-10-12T01:45:27Z","title":"Large Language Models Can Be Strong Differentially Private Learners","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.05679","snapshot_observed_at":"2026-08-04T13:23:19.265620Z","title":"Large language models can be strong differentially private learners","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.265620Z"},"links":{"cited_paper":"/paper/2110.05679","citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:91d682d2197ba25207b9b915df4759654cd6700afe9f4925568b45ee784cbcdf","observation_id":"62aced60-f253-4939-b246-9adcb8dc5a35","resolution":{"observed_at":"2026-08-04T13:23:19.265620Z","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":"2026-08-04T13:23:19.313099Z","title":"When does differentially private learning not suffer in high dimensions? Advances in Neural Information Processing Systems, 35: 0 28616--28630, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.313099Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:37c912380c5cade6caea1e5e40d1ef95aa7d30925a8a81dcd2e3d81a0c940021","observation_id":"825a113c-7046-406d-8baa-0378b15aa379","resolution":{"observed_at":"2026-08-04T13:23:19.313099Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-07-31T22:31:37.910868Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-04T13:23:19.381361Z","title":"Roberta: A robustly optimized bert pretraining approach","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.381361Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:cfad0c2fd6762708c8e45c2a74e99ca75ed101fff74785b4d650ddc6187e1210","observation_id":"1f2936bd-fca4-4b17-8850-0a93a6eb89d0","resolution":{"observed_at":"2026-08-04T13:23:19.381361Z","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":"2026-08-04T13:23:19.432574Z","title":"Distribution of eigenvalues for some sets of random matrices","venue":null,"work_id":null,"year":1967},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.432574Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:64a851a78c2972b1b5c1fe0846236f9450f303134648906608f710c79d9aaada","observation_id":"fa3b7a0d-8fd8-46d1-b8a4-ed52cb5082a7","resolution":{"observed_at":"2026-08-04T13:23:19.432574Z","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":"2026-08-04T13:23:19.494833Z","title":"Reconstruction of a low-rank matrix in the presence of gaussian noise","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.494833Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:c2da1374c6f47cb4ab92d173b9e21405cf929499de56289b31d63e6b5e14a2d9","observation_id":"f48ce7ef-8269-4c9e-8eb4-ef4c3ef7e4a6","resolution":{"observed_at":"2026-08-04T13:23:19.494833Z","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":"2026-08-04T13:23:19.558693Z","title":"Topics in random matrix theory, volume 132","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.558693Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:db60cccd3472664725afb11508e7947db263d15f613bb29d0496c281abcbb079","observation_id":"e42dba1f-a317-4041-9128-05fb623eda4d","resolution":{"observed_at":"2026-08-04T13:23:19.558693Z","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":"2026-08-04T13:23:19.630151Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.630151Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:0d5ed822284190bcb891fd44923c893cc9882f7ea3507681ac698e5e859d783a","observation_id":"88078c00-73cc-4506-a0d6-66a15398e777","resolution":{"observed_at":"2026-08-04T13:23:19.630151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-04T13:23:19.701681Z","title":"Differentially private fine-tuning of language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.701681Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:58fa5d6886e04d91b9cb26173d845b596d240152f3aae1747be611f59324074b","observation_id":"1c3bf0f5-7db8-43a6-b2b8-2d11f3281cf6","resolution":{"observed_at":"2026-08-04T13:23:19.701681Z","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":"2026-08-04T13:23:19.768922Z","title":"Doppler: Differentially private optimizers with low-pass filter for privacy noise reduction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.768922Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:42ebe864a09d0f28a49fa3a0703f373531cab903cb0922612c9e2ebe55b55a0c","observation_id":"99d9058a-0d7e-4854-9bbc-441800c59ae3","resolution":{"observed_at":"2026-08-04T13:23:19.768922Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03507","last_updated":"2024-06-02T21:24:12Z","snapshot_observed_at":"2026-07-06T17:40:15.746482Z","submitted_at":"2024-03-06T07:29:57Z","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03507","snapshot_observed_at":"2026-08-04T13:23:19.776029Z","title":"Galore: Memory-efficient llm training by gradient low-rank projection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.776029Z"},"links":{"cited_paper":"/paper/2403.03507","citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:f0ec75bb79da851c58bbe76df11a8ea6a5ba721097d465a0a669562993e98a8f","observation_id":"df56a579-a3b7-4172-aa28-407eb9762e33","resolution":{"observed_at":"2026-08-04T13:23:19.776029Z","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":"2026-08-04T13:23:19.834171Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.834171Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:cb1053863b5b9889bbdd85d08cc0294aaf84b2c89b21267f60bb5a95dbfd9757","observation_id":"9384c4af-7b6e-4b8b-88ac-e3b3d888c665","resolution":{"observed_at":"2026-08-04T13:23:19.834171Z","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":"2026-08-04T13:23:19.959017Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:19.959017Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:d497c12d50a5efda1e41eb1cb86ae487c1d2ba9d6fe7566b54d313a203772710","observation_id":"e60ef481-db06-43d2-afde-a46faf1ee834","resolution":{"observed_at":"2026-08-04T13:23:19.959017Z","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":"2026-08-04T13:23:20.054877Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:20.054877Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:751fcfa9a64e966f3f533be363694c86bb3816d8a67f85216a1f5cef3bb81bae","observation_id":"5aa39f7c-2e39-4a09-a96c-665adf5a691e","resolution":{"observed_at":"2026-08-04T13:23:20.054877Z","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":"2026-08-04T13:23:20.185349Z","title":"e , 9 Z4Mz> yH>'w= N&","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-04T13:23:20.185349Z"},"links":{"citing_paper":"/paper/2510.01137"},"observation_digest":"sha256:51db72af649dd64306f783381521f2491d51f6f571529b89a58b85ca76864ac3","observation_id":"1d4b2e42-5314-4b48-b22b-1d1d32c973e8","resolution":{"observed_at":"2026-08-04T13:23:20.185349Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2510.01137","last_updated":"2026-05-28T18:48:28Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T13:23:17.377482Z","submitted_at":"2025-10-01T17:25:23Z","title":"Re-examining Low Rank adaptation for private LLM fine-tuning"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":25,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":26},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2510.01137."}