{"as_of":"2026-08-05T14:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f1c58c0f5c0b41a8078078e88de7cfacc7be442f8618764f157cecded0874da0","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":25,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":25,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":25,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":25,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T19:11:57.435191Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T08:29:41.295298Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"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":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2305.15717","last_updated":"2023-05-25T05:00:12Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-25T05:00:12Z","title":"The False Promise of Imitating Proprietary LLMs","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-05-18T06:54:31.175090Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2305.15717"},"observation_digest":"sha256:04897b9f98026321cd05ef5a977090aa81a080afd20fcdbde6ef73f372cdcd7e","observation_id":"ae74ea7c-2e2c-4e18-a075-b5b9164c3bf7","resolution":{"observed_at":"2026-05-18T06:54:31.322412Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2401.00870","last_updated":"2026-04-08T14:54:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-30T01:26:42Z","title":"ConfusionPrompt: Practical Private Inference for Online Large Language Models","version":5},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-24T04:57:55.197897Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2401.00870"},"observation_digest":"sha256:dc98e9b521095a44236ff3e9385d17392578f9835bf0af06269e72d866bb58a1","observation_id":"260aa599-7632-4582-819e-15ea40a85301","resolution":{"observed_at":"2026-05-24T04:58:54.900344Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2402.16391","last_updated":"2026-04-28T07:39:39Z","snapshot_observed_at":"2026-08-01T03:48:12.462157Z","submitted_at":"2024-02-26T08:31:45Z","title":"Industry Practitioners Perspectives on AI Model Quality: Perceptions, Challenges, and Solutions","version":4},"reference_index":139,"source":"pdf_text","source_observed_at":"2026-05-24T04:21:49.775278Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2402.16391"},"observation_digest":"sha256:1bf07fa48af7e92fe3248f220a0d68ea01caf282de944a9c9e04182cfc8380ee","observation_id":"a6debab8-3cc4-4b0b-8cff-800bd81b9a21","resolution":{"observed_at":"2026-05-24T04:23:52.783217Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2501.02407","last_updated":"2026-05-20T14:04:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-05T00:03:18Z","title":"Towards the Anonymization of the Language Modeling","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-23T06:28:16.975305Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2501.02407"},"observation_digest":"sha256:2742978fdd53c8521e7d65911efde09393d4ed5e68d023e4a14c314dc77d5d85","observation_id":"b67333cf-64d1-480d-a070-782540281fb5","resolution":{"observed_at":"2026-05-23T06:32:39.496907Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2506.05640","last_updated":"2026-05-19T03:36:42Z","snapshot_observed_at":"2026-07-06T21:37:42.063760Z","submitted_at":"2025-06-06T00:05:05Z","title":"FedShield-LLM: A Secure and Scalable Federated Fine-Tuned Large Language Model","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-22T01:43:44.406488Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2506.05640"},"observation_digest":"sha256:dec6a41886b343c65b0127e289ceadef319ef5a3bca54498d80426cabaa9c082","observation_id":"4709dde3-9eca-44c9-9b65-565f40fb7a01","resolution":{"observed_at":"2026-05-22T01:44:30.369790Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2506.15588","last_updated":"2026-05-18T12:41:38Z","snapshot_observed_at":"2026-08-02T14:39:33.262823Z","submitted_at":"2025-06-18T16:05:09Z","title":"Memory-Efficient Differentially Private Training with Gradient Random Projection","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-21T23:46:54.620034Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2506.15588"},"observation_digest":"sha256:07fea03a51522046c052907bc8f34bcb58f45fe207aaf24c8e881cf39c2adbf7","observation_id":"a1f65a3b-00f5-4ef3-a864-6a15fd13490c","resolution":{"observed_at":"2026-05-21T23:50:47.467243Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-08-04T19:11:57.435191Z","title":"Differentially private fine-tuning of language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09485","last_updated":"2025-09-12T01:27:15Z","snapshot_observed_at":"2026-08-04T19:11:38.476774Z","submitted_at":"2025-09-11T14:17:04Z","title":"Balancing Utility and Privacy: Dynamically Private SGD with Random Projection","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-04T19:11:57.435191Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2509.09485"},"observation_digest":"sha256:33730e0bb0f0a66d35191200887b772f44c171d853f8f71cc06308761ecfb5f3","observation_id":"08b4b149-bc7a-4117-8013-6250178a2b9c","resolution":{"observed_at":"2026-08-04T19:11:57.435191Z","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":"2026-08-04T17:28:50.996266Z","title":"Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, and Huishuai Zhang","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10932","last_updated":"2025-09-13T18:11:51Z","snapshot_observed_at":"2026-08-05T14:14:59.854748Z","submitted_at":"2025-09-13T18:11:51Z","title":"Public Data Assisted Differentially Private In-Context Learning","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-04T17:28:50.996266Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2509.10932"},"observation_digest":"sha256:a37a9aaf55fa201b26e9c090928bdc6f642e0819a92e86702ab9a9cf8fec389c","observation_id":"7f3af31e-05f6-4ae7-925b-7619d522ae67","resolution":{"observed_at":"2026-08-04T17:28:50.996266Z","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":"2026-08-04T17:03:13.505526Z","title":"Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, and Huishuai Zhang","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.11176","last_updated":"2025-09-14T09:16:11Z","snapshot_observed_at":"2026-08-04T17:03:02.843377Z","submitted_at":"2025-09-14T09:16:11Z","title":"Differentially-private text generation degrades output language quality","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-04T17:03:13.505526Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2509.11176"},"observation_digest":"sha256:7c3181d186aab1510b29879fd8371904344f9b40333cbba224f89820b8e34609","observation_id":"b43cc37a-fbfc-4eed-b71f-3e578f6c51bb","resolution":{"observed_at":"2026-08-04T17:03:13.505526Z","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":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2509.12958","last_updated":"2026-05-22T06:49:39Z","snapshot_observed_at":"2026-08-02T02:59:54.362556Z","submitted_at":"2025-09-16T11:01:59Z","title":"Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-05-25T08:28:39.748595Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2509.12958"},"observation_digest":"sha256:de0df0b08eeb77b91a8d332acefdaf205e0369c514e2214891f25b9261d56eb5","observation_id":"776659d6-0a5a-4f2e-bdd1-b40c3ac10bcc","resolution":{"observed_at":"2026-05-25T08:30:31.812981Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-08-04T13:23:19.701681Z","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":{"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":"2026-08-04T11:23:22.202539Z","title":"Differentially private fine-tuning of language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.05699","last_updated":"2026-05-25T05:56:04Z","snapshot_observed_at":"2026-08-04T11:23:04.619511Z","submitted_at":"2025-10-07T09:05:40Z","title":"Membership Inference Attacks on Tokenizers of Large Language Models","version":4},"reference_index":105,"source":"pdf_text","source_observed_at":"2026-08-04T11:23:22.202539Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2510.05699"},"observation_digest":"sha256:1099d946796e09a6cae2d3355f2cf721535efe8f5d9637e2ee4cded176075476","observation_id":"8a7d745c-2c63-486e-a62b-9cbd6c2b0de5","resolution":{"observed_at":"2026-08-04T11:23:22.202539Z","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":"2026-08-03T18:53:11.031697Z","title":"A., Kamath, G., Kulkarni, J., Lee, Y","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.03238","last_updated":"2026-07-09T21:40:53Z","snapshot_observed_at":"2026-08-04T23:00:48.940171Z","submitted_at":"2025-12-02T21:14:39Z","title":"How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy","version":2},"reference_index":266,"source":"arxiv_source","source_observed_at":"2026-08-03T18:53:11.031697Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2512.03238"},"observation_digest":"sha256:1d755fc75ff1a003343fe7ccbf7656504d22c370334fd421cb89134e2bd191ed","observation_id":"c76114fd-300f-4417-9610-a96510aa5279","resolution":{"observed_at":"2026-08-03T18:53:11.031697Z","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":"2026-08-03T15:38:38.260190Z","title":"Differentially private fine- tuning of language models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.16292","last_updated":"2025-12-21T20:55:37Z","snapshot_observed_at":"2026-08-03T15:38:35.637557Z","submitted_at":"2025-12-18T08:26:26Z","title":"In-Context Probing for Membership Inference in Fine-Tuned Language Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T15:38:38.260190Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2512.16292"},"observation_digest":"sha256:bda20c1c677db2461bcefed3e72fbc05ceef3ec8a3c4ee9034e49bce03bd29a0","observation_id":"0fa656be-9b48-4765-966c-ffa8f65f7f49","resolution":{"observed_at":"2026-08-03T15:38:38.260190Z","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":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2603.01059","last_updated":"2026-04-09T00:42:09Z","snapshot_observed_at":"2026-08-02T10:05:40.434546Z","submitted_at":"2026-03-01T11:29:25Z","title":"GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-05-15T18:27:16.527361Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2603.01059"},"observation_digest":"sha256:4cda4cb5bb5b26fa3a01f9fb1971e095c3200d0e54d1b4e48334ac31302bed03","observation_id":"98d02fb2-06a1-47b0-9714-1858adf65f8c","resolution":{"observed_at":"2026-05-15T18:30:14.378808Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2604.09952","last_updated":"2026-04-10T23:11:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-10T23:11:57Z","title":"SLM Finetuning for Natural Language to Domain Specific Code Generation in Production","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-05-10T16:38:30.184565Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2604.09952"},"observation_digest":"sha256:97d33f9eaa030d5b9dbe5bf5571b5887c2dfb4cda5ed1070880b07ba027d2193","observation_id":"08f79bd1-adc6-46fc-ade4-15e072c632fd","resolution":{"observed_at":"2026-05-11T08:26:00.845144Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2604.21905","last_updated":"2026-04-23T17:50:23Z","snapshot_observed_at":"2026-07-06T23:08:23.939574Z","submitted_at":"2026-04-23T17:50:23Z","title":"Low-Rank Adaptation Redux for Large Models","version":1},"reference_index":226,"source":"pdf_text","source_observed_at":"2026-05-09T21:48:48.992712Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2604.21905"},"observation_digest":"sha256:30d5093de5d92d9897b3c1f419e30cbfdae92f1e27dbb4cb46c23fd80f29c735","observation_id":"9e6e2780-234f-4d5c-9e9d-bb9bc01be6d4","resolution":{"observed_at":"2026-05-11T14:26:03.838691Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2605.12512","last_updated":"2026-03-31T09:10:55Z","snapshot_observed_at":"2026-07-06T23:24:13.851504Z","submitted_at":"2026-03-31T09:10:55Z","title":"Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-05-14T21:19:05.453523Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2605.12512"},"observation_digest":"sha256:36ab731078821a094eb874a8862957cbdd579d5371ac6189e145b103b3dc3888","observation_id":"8b0fd4ef-e250-4005-9a13-9f4de961c532","resolution":{"observed_at":"2026-05-14T21:19:27.906926Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2605.15248","last_updated":"2026-05-14T12:16:34Z","snapshot_observed_at":"2026-07-06T23:26:32.979566Z","submitted_at":"2026-05-14T12:16:34Z","title":"Probing Privacy Leaks in LLM-based Code Generation via Test Generation","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-05-19T16:21:11.506550Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2605.15248"},"observation_digest":"sha256:1158d035471caa3b4fbd4fa17ddb80c1e7bb4e7748776327fef32cdbb25ceb95","observation_id":"c1cee4e5-94ef-4007-a719-5d7b05012106","resolution":{"observed_at":"2026-05-19T16:22:39.571884Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2605.17432","last_updated":"2026-05-17T12:55:11Z","snapshot_observed_at":"2026-07-06T23:28:26.397778Z","submitted_at":"2026-05-17T12:55:11Z","title":"DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-20T13:35:02.869657Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2605.17432"},"observation_digest":"sha256:864c95cfddffe68274fd3860e5358a932b1cdedb237fea32e80c73fa36080bf6","observation_id":"f5f81c92-e052-4616-86dc-16637c38ede2","resolution":{"observed_at":"2026-05-20T13:38:19.381523Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2606.01908","last_updated":"2026-07-03T01:57:20Z","snapshot_observed_at":"2026-07-12T15:23:32.094817Z","submitted_at":"2026-06-01T08:45:59Z","title":"Private and Stable Test-Time Adaptation with Differential Privacy","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-06-28T15:15:33.564332Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2606.01908"},"observation_digest":"sha256:bf0b0bc1a54d9e2d412ef32e80ec9ac7fb7ac3ab8af454385f834e5ba7abca70","observation_id":"eb26dbee-b79e-4981-8684-7638623e308c","resolution":{"observed_at":"2026-07-01T22:36:17.163634Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2606.05004","last_updated":"2026-06-03T15:23:06Z","snapshot_observed_at":"2026-07-06T23:45:02.342193Z","submitted_at":"2026-06-03T15:23:06Z","title":"SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-06-28T05:29:47.894226Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2606.05004"},"observation_digest":"sha256:64d13bfcd6136dffad447a7539a6bd0c63ce33d4575898804657b19c7a8f46d6","observation_id":"1e51e073-2328-4e70-84c7-4e8dcb51185d","resolution":{"observed_at":"2026-07-02T09:26:51.564972Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2606.09125","last_updated":"2026-06-08T07:19:42Z","snapshot_observed_at":"2026-07-06T23:48:30.569726Z","submitted_at":"2026-06-08T07:19:42Z","title":"Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-06-27T16:33:28.848573Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2606.09125"},"observation_digest":"sha256:0d9d732204d17aa481ebaaa41737d12e8bb4e5ba72b26bdee50952e9dce41b4a","observation_id":"b7880f4a-a4da-4ce8-bfdc-5994d6040aa1","resolution":{"observed_at":"2026-07-03T01:27:30.932613Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2606.20897","last_updated":"2026-06-18T19:45:28Z","snapshot_observed_at":"2026-08-01T22:17:51.886515Z","submitted_at":"2026-06-18T19:45:28Z","title":"PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-06-26T17:12:38.192534Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2606.20897"},"observation_digest":"sha256:539e05be00a0d94913cadb7e95d6c4b8f54eccb99f5489d3ae669a4d7c0c7ee4","observation_id":"68be48d9-ae2b-4745-9f12-24ab3e6f2b71","resolution":{"observed_at":"2026-07-04T04:09:34.577689Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":"2110.06500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-07-04T08:29:41.295298Z","title":"A.; Kamath, G.; Kulkarni, J.; Lee, Y","venue":null,"work_id":"1db6de97-8a14-48b9-9d17-51e95cd18762","year":2021},"citing_paper":{"arxiv_id":"2606.22153","last_updated":"2026-06-20T17:22:36Z","snapshot_observed_at":"2026-08-03T08:43:51.480863Z","submitted_at":"2026-06-20T17:22:36Z","title":"$\\pi$-RAG: Oblivious Retrieval via Semantic Quantization and Transcendental Addressing for Large Language Models","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-06-26T11:42:58.442012Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2606.22153"},"observation_digest":"sha256:6bb41816a9039329a654ea6567799f022d045d05d47546bcaad0f918986bcbb1","observation_id":"cc13f7aa-5571-42fd-971d-4c8e1bcce5de","resolution":{"observed_at":"2026-07-04T08:29:41.297061Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2110.06500/citation-record","integrity":"/paper/2110.06500/integrity","json":"/paper/2110.06500/citation-record.json","paper":"/paper/2110.06500"},"outbound":[],"paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T11:57:21.548494Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 25 inbound Pith citation observations for arXiv:2110.06500."}