{"as_of":"2026-08-16T09:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5e89f9d0fa22458cdd9d060e836e09001d45c4f89143e456c3c22b57429f6584","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T13:56:36.697875Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2411.15831/citation-record","integrity":"/paper/2411.15831/integrity","json":"/paper/2411.15831/citation-record.json","paper":"/paper/2411.15831"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T13:56:37.386929Z","title":"Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus","venue":null,"work_id":"c7846915-972d-4957-ba9e-cec9496b2629","year":null},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.497397Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:20ab2d2828c7bd2aee83c438130674d462d41047ecc25ce18495165d51b85320","observation_id":"223977ef-8c27-43be-8f1e-2b9441498007","resolution":{"observed_at":"2026-08-12T13:56:37.391448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.366223Z","title":null,"venue":null,"work_id":"4d4441fa-ceaf-4e8e-98ce-d6fe6fc4ab03","year":2021},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.506195Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:ab83ebdf08d5eee33b619d0c111ce335205d02b4db57d40b96106ec2ec5c86c8","observation_id":"74aba8e0-fdd4-40e5-b6ec-55b645269ecd","resolution":{"observed_at":"2026-08-12T13:56:37.370066Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00888","last_updated":"2024-11-14T22:20:49Z","snapshot_observed_at":"2026-08-13T04:32:07.137910Z","submitted_at":"2024-01-30T04:00:54Z","title":"Security and Privacy Challenges of Large Language Models: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00888","snapshot_observed_at":"2026-08-12T13:56:36.509928Z","title":"Hadi Amini, and Yanzhao Wu","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.509928Z"},"links":{"cited_paper":"/paper/2402.00888","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:5b7ef035527f8bda8a123dedb0c2345c439bf65c6d6a0009ee2c08478c760837","observation_id":"54fd381c-3015-4c4a-8e5d-6afaf2bd696f","resolution":{"observed_at":"2026-08-12T13:56:36.509928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.00513","last_updated":"2019-05-17T18:47:05Z","snapshot_observed_at":"2026-08-14T18:05:35.251990Z","submitted_at":"2018-11-01T17:32:44Z","title":"Auditing Data Provenance in Text-Generation Models","version":2},"cited_work":{"arxiv_id":"1811.00513","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.00513","snapshot_observed_at":"2026-08-12T13:56:36.964072Z","title":"Auditing Data Provenance in Text-Generation Models","venue":"cs.CR","work_id":"cb02856b-b6ff-43ef-ba1e-e041f8daa144","year":2018},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.514152Z"},"links":{"cited_paper":"/paper/1811.00513","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:1acb1b6dad52a44b222253c26b05062c26efa8d6428415e193a063c9edaf0a69","observation_id":"78070b30-7dde-422e-a5e5-6146f1b3fc7f","resolution":{"observed_at":"2026-08-12T13:56:36.968393Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.353542Z","title":"Extracting training data from large language models","venue":null,"work_id":"0c4285dd-e8c9-4583-87a7-1fa3ddfa8690","year":2021},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.518198Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:d7b5d22381930228a11b994bc6ef6402713d2f7a91a270102abef8e7453b2210","observation_id":"08a2ac51-a95e-4456-a9ed-563b7b593455","resolution":{"observed_at":"2026-08-12T13:56:37.357805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.341227Z","title":"Quantifying privacy risks of masked language models using membership inference attacks","venue":null,"work_id":"77eba542-2ffc-40a8-9d2c-72e4be900305","year":2022},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.522266Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:ae64a5ce0e159034561512e7fddac1eb97a5d689c09b30da0517c94cf12a3cca","observation_id":"9058162b-b1f9-4393-a703-a137cd42eac9","resolution":{"observed_at":"2026-08-12T13:56:37.345289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06714","last_updated":"2024-02-22T21:19:59Z","snapshot_observed_at":"2026-08-13T05:52:55.984749Z","submitted_at":"2023-10-10T15:41:26Z","title":"Exploring Memorization in Fine-tuned Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06714","snapshot_observed_at":"2026-08-12T13:56:36.526324Z","title":"Exploring memorization in fine-tuned language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.526324Z"},"links":{"cited_paper":"/paper/2310.06714","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:b7c6a4849218ed977e0c83d3972c804d80cc18f3f3650cfc132426f1f6a0efb3","observation_id":"68ecf6bf-1bda-49fd-8d05-ffda0958a811","resolution":{"observed_at":"2026-08-12T13:56:36.526324Z","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":"2026-08-12T13:56:37.329086Z","title":"Deep learning with differential privacy","venue":null,"work_id":"6c699c11-ced1-4500-98ff-d282cf4186a0","year":2016},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.530982Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:8515bacbde4f2626677aaa5391f9ac618c21e934332f2d65bf1430f2210d8b17","observation_id":"2c7bfb88-e0b5-40b0-9e8e-fac38c9fde6f","resolution":{"observed_at":"2026-08-12T13:56:37.333117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.317131Z","title":"The Algorithmic F oundations of Differential Privacy","venue":null,"work_id":"cb8e567a-48f9-4726-8279-01ad4b05d7f6","year":2014},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.534928Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:d04570b5f5772efaa0938aefc31a0b204cd682c5cf2095d408daa3feec1ee47e","observation_id":"a9e5fb98-2887-4e7d-a272-f47cc260255f","resolution":{"observed_at":"2026-08-12T13:56:37.320760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.305735Z","title":"Training text-to-text transformers with privacy guarantees","venue":null,"work_id":"a2a6c5be-3f47-4314-942e-eb02b438b43b","year":2022},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.538784Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:51d59c0d0db792abdaed77ac763f78af85d547c38ed889f3ea5d0c4ddaf9370d","observation_id":"2905a58b-bf6f-406e-9d0f-bab6e6a038a2","resolution":{"observed_at":"2026-08-12T13:56:37.309488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.294297Z","title":"Differential privacy has disparate impact on model accuracy","venue":null,"work_id":"638e6b00-d9a5-4796-a854-2537aa535bfd","year":2019},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.542848Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:32720f683ec68466f1d8a33bba4c2772199753746952e0786b24f9b25dd3815c","observation_id":"5ef9afe9-1d01-404c-ae2b-f3dabf6c7e0c","resolution":{"observed_at":"2026-08-12T13:56:37.298047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.282490Z","title":"Differentially private fine-tuning of language models","venue":null,"work_id":"c22fb762-a205-4b21-aba2-f385974b7c49","year":2022},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.546947Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:5d1ce4a4ff32452d62e87516d76c02f4c8f7215a0dc0e06bd733622b5337373e","observation_id":"b799998c-effa-497a-b189-afa63136d72c","resolution":{"observed_at":"2026-08-12T13:56:37.286023Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.00036","last_updated":"2024-06-19T02:40:18Z","snapshot_observed_at":"2026-08-15T08:45:10.947069Z","submitted_at":"2022-09-30T18:30:48Z","title":"Differentially Private Bias-Term Fine-tuning of Foundation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.00036","snapshot_observed_at":"2026-08-12T13:56:36.550757Z","title":"Differentially private bias-term only fine-tuning of foundation models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.550757Z"},"links":{"cited_paper":"/paper/2210.00036","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:e6a7ed01247a4bc56cff57b13ff4bb4bb5d7920c7ecdc5739c54a3875126140d","observation_id":"aa3979d9-2413-41e5-ad40-195d69c51d72","resolution":{"observed_at":"2026-08-12T13:56:36.550757Z","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":"2026-08-13T17:54:58.734783Z","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":"2026-08-12T13:56:36.554893Z","title":"Hashimoto","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.554893Z"},"links":{"cited_paper":"/paper/2110.05679","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:0bf1bbe1903c2e72559f745aa4f2806601d3aa25fa364f56abf1047825afff28","observation_id":"677e0c7c-f66f-4650-96bf-11e25ce16b68","resolution":{"observed_at":"2026-08-12T13:56:36.554893Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14608","last_updated":"2024-09-16T02:54:50Z","snapshot_observed_at":"2026-08-04T09:07:42.158421Z","submitted_at":"2024-03-21T17:55:50Z","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14608","snapshot_observed_at":"2026-08-12T13:56:36.559012Z","title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.559012Z"},"links":{"cited_paper":"/paper/2403.14608","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:d16bfa2fbf133c4c4f3eb3a8473c2eb297cd30463b7087f6922ed207b1680f04","observation_id":"1715d546-9392-4560-9a8d-d7545cde9b62","resolution":{"observed_at":"2026-08-12T13:56:36.559012Z","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":"2026-08-12T13:56:37.269958Z","title":"Parameter efficient fine tuning: A comprehensive analysis across applications, April 2024","venue":null,"work_id":"fcd70341-62fc-4cb4-bcc2-91ddb54a543c","year":2024},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.563177Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:2677c5b53b70aae0f9b0a6ef203eef52e5270e1fad4910212fe2d075d04f8796","observation_id":"135d10ab-89a2-4c45-9c7b-a777d16a7b22","resolution":{"observed_at":"2026-08-12T13:56:37.274291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.257384Z","title":"Lora learns less and forgets less","venue":null,"work_id":"02b59935-5568-480b-9ee1-1a1583c2d569","year":2024},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.566854Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:680ffc2a8cfd213a67c205960cec353e3b6e160017092f88cbe28818111b8668","observation_id":"cef0df3e-2f0f-4a48-be54-1ab9381bbf3f","resolution":{"observed_at":"2026-08-12T13:56:37.261674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.244312Z","title":"Calibrating noise to sensitivity in private data analysis","venue":null,"work_id":"48416139-0dde-4f20-be52-ba3333d29217","year":2006},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.570620Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:c3a91e9b008397428f9dd98566b7f1422dba23c24f9b5a03c27d066598ff8cb6","observation_id":"6ea8cd64-86fe-483b-aa99-82d5017df5cd","resolution":{"observed_at":"2026-08-12T13:56:37.248396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.232228Z","title":null,"venue":null,"work_id":"0cbcb11d-3cb0-45fa-9086-00b4f4a60600","year":2017},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.574443Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:19f9495cbcdaa4f289f2bcee2bf1e3abe4c07f075db2b166ef6b2f979883feca","observation_id":"da82e07b-6899-4abd-bae1-1252528ad8b1","resolution":{"observed_at":"2026-08-12T13:56:37.236097Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.219467Z","title":"Opacus: User-friendly differential privacy library in pytorch","venue":null,"work_id":"573cc024-eb48-4c10-bfcc-a222b783d419","year":2021},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.578423Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:08b4a98b4ca975c698f89ecc0013dc3d16f42b4c839d80ce9fda5a2fb2c7f85c","observation_id":"39babc6b-25ed-40ba-9c4e-5170a517238b","resolution":{"observed_at":"2026-08-12T13:56:37.223641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.207948Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":"b365f10a-9b5c-4895-a9e4-ffa24069cd38","year":2019},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.582217Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:81c7ce6f1211d164297a3aa3f0a9c828ef1f47556b389b056728d92ab60d60b3","observation_id":"a179391a-c2a5-44b8-b14b-e0572eaa0735","resolution":{"observed_at":"2026-08-12T13:56:37.211475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-11T08:20:29.798517Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-12T13:56:36.586213Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Zhize Li, Lei Wang, and Weizhu Chen","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.586213Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:c90d261dc43bd696cfbe65e2f9a83908c2b90777fd30464c0df836bdfacdd2fc","observation_id":"e4786aa8-fa8c-4a5f-bba7-5d3fd9e7cb39","resolution":{"observed_at":"2026-08-12T13:56:36.586213Z","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":"2026-08-12T13:56:37.196256Z","title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","venue":null,"work_id":"51716e6a-55f7-4abc-bfa3-29d519652ccc","year":2022},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.590198Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:d3eaf288130098e41d7211fb0027bf59c889fd31d8ff141de78b2f99f609dc10","observation_id":"b4902318-79d4-40d9-8efa-ffbad8a2f717","resolution":{"observed_at":"2026-08-12T13:56:37.200056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10329","last_updated":"2023-05-17T16:10:36Z","snapshot_observed_at":"2026-08-16T07:11:48.649952Z","submitted_at":"2023-05-17T16:10:36Z","title":"G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks","version":1},"cited_work":{"arxiv_id":"2305.10329","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.10329","snapshot_observed_at":"2026-08-12T13:56:36.880901Z","title":"G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks","venue":"cs.LG","work_id":"a4bda79f-e1f0-42d4-b3c2-2865d08c6ffe","year":2023},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.593928Z"},"links":{"cited_paper":"/paper/2305.10329","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:6b68738dd207e7cafd9bab00bc5e12545556ba4164666fe85ae698576b706dee","observation_id":"6ada4c96-435d-4b66-abd5-4b848bea5aeb","resolution":{"observed_at":"2026-08-12T13:56:36.885504Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.05350","last_updated":"2024-02-14T09:26:51Z","snapshot_observed_at":"2026-08-15T12:48:50.758763Z","submitted_at":"2023-06-08T16:53:02Z","title":"PEFT-SER: On the Use of Parameter Efficient Transfer Learning Approaches For Speech Emotion Recognition Using Pre-trained Speech Models","version":2},"cited_work":{"arxiv_id":"2306.05350","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.05350","snapshot_observed_at":"2026-08-12T13:56:36.862768Z","title":"PEFT-SER: On the Use of Parameter Efficient Transfer Learning Approaches For Speech Emotion Recognition Using Pre-trained Speech Models","venue":"cs.SD","work_id":"cc78eedf-2ec8-4be2-984c-4cc4af77e3e5","year":2023},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.597920Z"},"links":{"cited_paper":"/paper/2306.05350","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:3e35b1865f42405e5766094b2be40f8318c466db9d3c71a0e369b6d27b7ce86b","observation_id":"1ea5b567-b375-4ff9-a69a-a7d9d947a6a6","resolution":{"observed_at":"2026-08-12T13:56:36.867712Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.17451","last_updated":"2022-11-02T02:44:23Z","snapshot_observed_at":"2026-07-06T14:12:37.347291Z","submitted_at":"2022-10-31T16:23:36Z","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","version":2},"cited_work":{"arxiv_id":"2210.17451","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.17451","snapshot_observed_at":"2026-08-12T13:56:36.843478Z","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","venue":"cs.CL","work_id":"638e56db-a835-4071-81e0-80b3d836850b","year":2022},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.601558Z"},"links":{"cited_paper":"/paper/2210.17451","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:110782b7fd0ce8325d417462698f5f77eaeca1bfec92cbe0eb2c4b1d6a85a36d","observation_id":"2efdc84c-e0f3-402f-a195-a97923e3d9b1","resolution":{"observed_at":"2026-08-12T13:56:36.848758Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18403","last_updated":"2024-08-07T03:30:30Z","snapshot_observed_at":"2026-08-13T11:30:47.962636Z","submitted_at":"2023-05-28T15:15:48Z","title":"LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18403","snapshot_observed_at":"2026-08-12T13:56:36.605223Z","title":"Pruning meets low-rank parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.605223Z"},"links":{"cited_paper":"/paper/2305.18403","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:19c5b26e81019f62e7027cc1f0c34106823d9280de215584ed9a0c61bb6d9686","observation_id":"ab134f4f-490a-45e5-9508-943d89387983","resolution":{"observed_at":"2026-08-12T13:56:36.605223Z","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":"2026-08-12T13:56:37.182953Z","title":null,"venue":null,"work_id":"56b7bbc7-df05-42be-8117-5ef19b8139fe","year":2023},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.609408Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:dc1f2edb3ca89a6beb57862ddc8e153d9cb6346285c6a63e480c69730be643b6","observation_id":"2471c4b4-cd29-457b-9dcd-7a8a317f6550","resolution":{"observed_at":"2026-08-12T13:56:37.186825Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.09339","last_updated":"2020-07-18T06:21:35Z","snapshot_observed_at":"2026-08-16T06:00:39.449308Z","submitted_at":"2020-07-18T06:21:35Z","title":"ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.09339","snapshot_observed_at":"2026-08-12T13:56:36.613346Z","title":null,"venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.613346Z"},"links":{"cited_paper":"/paper/2007.09339","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:5a525387da581380c6fa5f84e8e224c4bbedb30f3d4b0ae329c70a54d05831c2","observation_id":"7ec115e9-7ecd-4d01-b9d8-9daaa577015e","resolution":{"observed_at":"2026-08-12T13:56:36.613346Z","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":"2026-08-12T13:56:37.170346Z","title":"Introducing a new privacy testing library in tensorflow, 2020","venue":null,"work_id":"f0fc5238-7265-43fa-8b5e-c25068f1ec0b","year":2020},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.617403Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:ddeee8388bcdaa9fa8fca2a8fa10ee45396a186a953f08dc1febbb7666c892e1","observation_id":"60642e65-d51a-4a03-956f-0d01564b227e","resolution":{"observed_at":"2026-08-12T13:56:37.174473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.156724Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":"0d45a303-9dbf-42cf-86f6-ebd2b7fcad8b","year":2017},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.621273Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:a52ed3d069d1ba5d27bf00080a8e3a67197fcf79aecffb40fd0dea2f0354da38","observation_id":"c2679906-fab0-4cfa-8e29-8a04853da5c3","resolution":{"observed_at":"2026-08-12T13:56:37.161357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.06062","last_updated":"2024-11-26T03:19:15Z","snapshot_observed_at":"2026-08-13T05:28:26.446906Z","submitted_at":"2023-11-10T13:55:05Z","title":"Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.06062","snapshot_observed_at":"2026-08-12T13:56:36.625054Z","title":"Practical membership inference attacks against fine-tuned large language models via self-prompt calibration","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.625054Z"},"links":{"cited_paper":"/paper/2311.06062","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:1f35ac393289a31fa5eadf1e4771c65fcea12440fedd417e5c6ea2d0fa1232f3","observation_id":"c15750d7-6251-4ce7-a8d7-b208e8050d95","resolution":{"observed_at":"2026-08-12T13:56:36.625054Z","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":"2026-08-12T13:56:37.143466Z","title":"An empirical analysis of memorization in fine-tuned autoregressive language models","venue":null,"work_id":"bcc23ece-95ca-4c0e-9eed-c85ad313cab3","year":2022},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.629144Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:0c9ab94c1a26211cfce1179467eb36ae583939abdc7eb87c7c426dcf166dd645","observation_id":"7ae012c0-6e69-49f2-8bf1-dce64691fb78","resolution":{"observed_at":"2026-08-12T13:56:37.147535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.130748Z","title":"Effects of differential privacy and data skewness on membership inference vulnerability","venue":null,"work_id":"796a0fda-d498-434e-990d-f174ed494d6f","year":2019},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.632874Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:6d02e37888a20226806bb20ce92b343ab24e55c7d18430e2ec99c4a91a1aefd4","observation_id":"4bfe26d2-5d9c-434c-a1a4-1ca9ee4459b7","resolution":{"observed_at":"2026-08-12T13:56:37.134836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.03075","last_updated":"2023-11-06T12:59:18Z","snapshot_observed_at":"2026-08-13T06:56:41.992161Z","submitted_at":"2023-11-06T12:59:18Z","title":"SoK: Memorisation in machine learning","version":1},"cited_work":{"arxiv_id":"2311.03075","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.03075","snapshot_observed_at":"2026-08-12T13:56:36.784168Z","title":"SoK: Memorisation in machine learning","venue":"cs.LG","work_id":"c027a852-1e17-4590-aa49-a3fbd8834937","year":2023},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.636755Z"},"links":{"cited_paper":"/paper/2311.03075","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:2f133fed5dd14522a09b361b914cd0821f5f27308f588312504a7ff78037e868","observation_id":"f9dd347a-4a76-4ff4-89a3-17160b119653","resolution":{"observed_at":"2026-08-12T13:56:36.789674Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.117859Z","title":"Sok: Membership inference is harder than previously thought","venue":null,"work_id":"d9671545-c9c7-4be5-a525-a7a4d7e51250","year":2023},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.640942Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:4f59323ac662c7ce226021e2d5f6ea483ec95f22bbf702d4cb252aa34099e8de","observation_id":"e3ef44cc-d492-4739-ba32-124514254316","resolution":{"observed_at":"2026-08-12T13:56:37.122030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.105425Z","title":"Low-cost high-power membership inference by boosting relativity","venue":null,"work_id":"dbd892c9-394f-4e59-9a42-befd1fc58964","year":2023},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.644714Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:99d05b4dd4dea3642f48305f1871c0cebb44d2fc521abac80a7ff430fa3c4545","observation_id":"ec61dc91-bb90-4bbf-8f6c-3e11059a08d4","resolution":{"observed_at":"2026-08-12T13:56:37.109540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.05526","last_updated":"2017-12-15T04:26:26Z","snapshot_observed_at":"2026-07-06T06:14:30.795326Z","submitted_at":"2017-12-15T04:26:26Z","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.05526","snapshot_observed_at":"2026-08-12T13:56:36.648473Z","title":"Targeted backdoor attacks on deep learning systems using data poisoning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.648473Z"},"links":{"cited_paper":"/paper/1712.05526","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:29497ae6132fd8974a224ef191f18da8569c8d2d4a60f83959f335a7ddaf4a71","observation_id":"433ebc4c-9558-4776-a16c-ce24f9fc40f4","resolution":{"observed_at":"2026-08-12T13:56:36.648473Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13459","last_updated":"2025-05-29T14:42:38Z","snapshot_observed_at":"2026-08-14T07:31:10.852407Z","submitted_at":"2024-02-21T01:30:03Z","title":"Learning to Poison Large Language Models for Downstream Manipulation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13459","snapshot_observed_at":"2026-08-12T13:56:36.652527Z","title":"Learning to poison large language models during instruction tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.652527Z"},"links":{"cited_paper":"/paper/2402.13459","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:366f7f19bbaba539312c119391e9d7cf00d1a8d9e6b1696d5cbdd2b51d89ba38","observation_id":"e8ac5296-cbea-4474-9949-b41fa795a601","resolution":{"observed_at":"2026-08-12T13:56:36.652527Z","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":"2026-08-12T13:56:37.092996Z","title":"Amplifying membership exposure via data poisoning","venue":null,"work_id":"ce5ca2f5-aa8a-4c6f-a5de-b4df9dd1f0e6","year":2024},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.656721Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:2323ee80d6e8e0665d52864d275cd6efd49815421683d867043d3200e073b732","observation_id":"a05a653b-562f-46c5-a6ef-875d038cadbb","resolution":{"observed_at":"2026-08-12T13:56:37.097207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:36.660409Z","title":"The secret sharer: Evaluating and testing unintended memorization in neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.660409Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:28a092beebeeaa2c316e2d1aa826b11d00e7bfaab4257cf6a317a32ad72acb9c","observation_id":"114c91e4-54d8-4d9a-aca2-e67407455157","resolution":{"observed_at":"2026-08-12T13:56:36.660409Z","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":"2026-08-12T13:56:37.071319Z","title":"Evaluating differentially private machine learning in practice","venue":null,"work_id":"6f7fae54-f97b-4474-aa87-94cc94d2dfe4","year":1912},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.664323Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:6eabdfcb47576335d728c5cc88826ff138632a6f2c25b2a2040933b52df63f09","observation_id":"344cc69e-01ef-45e1-a515-1647a430874b","resolution":{"observed_at":"2026-08-12T13:56:37.075408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:37.058489Z","title":"Membership inference attacks against language models via neighbourhood comparison","venue":null,"work_id":"aa037074-9959-4f94-99c2-2b841615632f","year":2023},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.668231Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:d3305f416ac9e3e6328d25ac7ce74f9e65ea9bbdae1f07995317a2fb13cc4162","observation_id":"97008386-2f0e-4ca3-be4a-7e983b786e5b","resolution":{"observed_at":"2026-08-12T13:56:37.062817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01108","last_updated":"2020-03-01T02:57:50Z","snapshot_observed_at":"2026-08-07T19:07:36.327251Z","submitted_at":"2019-10-02T17:56:28Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01108","snapshot_observed_at":"2026-08-12T13:56:36.672287Z","title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.672287Z"},"links":{"cited_paper":"/paper/1910.01108","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:f2970c0a755f3539360f8a76b4241212666d235c5475dcceb7695cba9568cfbd","observation_id":"5e6f59f3-d588-42e1-9f86-3bf0ea2526f6","resolution":{"observed_at":"2026-08-12T13:56:36.672287Z","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":"2026-08-12T13:56:37.045923Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":"bd090ef8-53f4-476f-a5e2-da46deb669f6","year":2019},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.676949Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:8f884c161eaa26ce8da9e1483074a3d9887c46f59e691746713f17565e8541db","observation_id":"7edf4054-d27e-4309-a2da-083e3683a7e0","resolution":{"observed_at":"2026-08-12T13:56:37.050086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:36.680349Z","title":"Peft: State-of-the-art parameter-efficient fine-tuning methods","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.680349Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:42daf483ab9a10a04b48a42b9cf57f8879f5887cc39a3772e88da0797049d04f","observation_id":"952641af-a6f4-4dd4-9b49-18f3bceb9b2f","resolution":{"observed_at":"2026-08-12T13:56:36.680349Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14322","last_updated":"2024-08-16T15:02:45Z","snapshot_observed_at":"2026-08-12T23:38:22.636715Z","submitted_at":"2024-06-20T13:54:32Z","title":"Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14322","snapshot_observed_at":"2026-08-12T13:56:36.683955Z","title":"Mind the privacy unit! user-level differential privacy for language model fine-tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.683955Z"},"links":{"cited_paper":"/paper/2406.14322","citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:f3313edc4425915c821074051c2c991f9929662d9f9b25609143ebc1d3e0db6e","observation_id":"c2d1ba51-f7da-4214-83c0-4ca8f93db6ca","resolution":{"observed_at":"2026-08-12T13:56:36.683955Z","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":"2026-08-12T13:56:37.024397Z","title":"Inan, and Andre Manoel","venue":null,"work_id":"745d7fc2-21aa-487d-a0fa-f4f73b566dcb","year":2022},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.687580Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:721277b5bb3cca5327fb2aeb7d413737b15a9dad24871cb58e589527f06ca4c8","observation_id":"4bc88228-e082-44bc-98be-10fec7c93b7a","resolution":{"observed_at":"2026-08-12T13:56:37.029097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:36.691068Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.691068Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:346d40604a9ff4b954ed5eb3fea73a59ff94ee8262935a898823937f764f2fe7","observation_id":"08aa82c4-45ce-4186-8fa1-7804fffcee95","resolution":{"observed_at":"2026-08-12T13:56:36.691068Z","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":"2026-08-12T13:56:37.003192Z","title":"Zen and the art of model adaptation: Low-utility-cost attack mitigations in collaborative machine learning","venue":null,"work_id":"c8c2b69a-aac4-4caa-8902-43a2578c241c","year":2022},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.694485Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:f8c69832e628a65e25a41bb59282f1969cbf5b8c869240a74301ea81e3a1846d","observation_id":"2e3902ea-603c-4533-bd6d-99fd8ab362dc","resolution":{"observed_at":"2026-08-12T13:56:37.007079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:36.991362Z","title":"Reconstructing training data from trained neural networks","venue":null,"work_id":"83e5f58e-63cc-47ad-af8d-6c554a8c9b34","year":2022},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.697875Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:1a94b870defd938c4cb6a44382f833bd8057737e5798fa6d92d6caf3346171fa","observation_id":"26b36887-9074-4f8f-8c10-74a211217a95","resolution":{"observed_at":"2026-08-12T13:56:36.995175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-12T13:56:36.502142Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-12T13:56:36.502142Z"},"links":{"citing_paper":"/paper/2411.15831"},"observation_digest":"sha256:789fbc632e143aef1abafc7997a0bed9dc2b82a414c2c9d0f95c6486660cf6c2","observation_id":"2aa166bc-7624-49de-bb38-5e3d256043f4","resolution":{"observed_at":"2026-08-12T13:56:36.502142Z","resolver_source":null,"status":"parse_uncertain"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.15831","last_updated":"2024-11-24T13:17:36Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T22:34:11.372099Z","submitted_at":"2024-11-24T13:17:36Z","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":19,"verified_exact":5,"verified_fuzzy":27},"total_outbound_references":52},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2411.15831."}