{"as_of":"2026-08-10T07:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6d16cdd9dbf64888a6a076d37e4ad5c60345f7b0f788a1b738dcaac99cbe03ff","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":10,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":10,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":10,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":10,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T22:05:02.520377Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":4,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.07737","last_updated":"2024-07-10T15:07:58Z","snapshot_observed_at":"2026-07-06T18:44:16.139499Z","submitted_at":"2024-07-10T15:07:58Z","title":"Fine-Tuning Large Language Models with User-Level Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07737","snapshot_observed_at":"2026-08-09T22:05:02.520377Z","title":"B., Mitchell, N., Pillutla, K., and Rush, K","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.18914","last_updated":"2025-01-31T06:32:46Z","snapshot_observed_at":"2026-08-09T21:55:30.723303Z","submitted_at":"2025-01-31T06:32:46Z","title":"Scaling Laws for Differentially Private Language Models","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-09T22:05:02.520377Z"},"links":{"cited_paper":"/paper/2407.07737","citing_paper":"/paper/2501.18914"},"observation_digest":"sha256:709ffae1c1c52652684e45238f36724cd6052166488ffcb2df844bd814f652bb","observation_id":"f4006fd1-d80f-413e-a2dd-f0258cdd653a","resolution":{"observed_at":"2026-08-09T22:05:02.520377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07737","last_updated":"2024-07-10T15:07:58Z","snapshot_observed_at":"2026-07-06T18:44:16.139499Z","submitted_at":"2024-07-10T15:07:58Z","title":"Fine-Tuning Large Language Models with User-Level Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07737","snapshot_observed_at":"2026-08-07T14:44:22.165394Z","title":"Brendan McMahan, Nicole Mitchell, Krishna Pil- lutla, and Keith Rush","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17716","last_updated":"2025-05-23T10:33:14Z","snapshot_observed_at":"2026-08-08T15:42:18.320838Z","submitted_at":"2025-05-23T10:33:14Z","title":"Get Experience from Practice: LLM Agents with Record & Replay","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T14:44:22.165394Z"},"links":{"cited_paper":"/paper/2407.07737","citing_paper":"/paper/2505.17716"},"observation_digest":"sha256:7fbfcf9d80d4ce8b8561377ac12082f72539c1ff5a6fa8e3a01ff631397dd0ce","observation_id":"630895a8-50c6-4bbc-b73f-3489133076ea","resolution":{"observed_at":"2026-08-07T14:44:22.165394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07737","last_updated":"2024-07-10T15:07:58Z","snapshot_observed_at":"2026-07-06T18:44:16.139499Z","submitted_at":"2024-07-10T15:07:58Z","title":"Fine-Tuning Large Language Models with User-Level Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07737","snapshot_observed_at":"2026-08-06T21:36:24.040736Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.23762","last_updated":"2025-06-30T12:09:29Z","snapshot_observed_at":"2026-08-06T21:29:49.550137Z","submitted_at":"2025-06-30T12:09:29Z","title":"Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T21:36:24.040736Z"},"links":{"cited_paper":"/paper/2407.07737","citing_paper":"/paper/2506.23762"},"observation_digest":"sha256:b4ffbaf75e6e52ff9adeedb83bb2c71980f1241cca6406783637262eb81afb61","observation_id":"5650d8f2-58f9-4179-9bdc-ef1404651e15","resolution":{"observed_at":"2026-08-06T21:36:24.040736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07737","last_updated":"2024-07-10T15:07:58Z","snapshot_observed_at":"2026-07-06T18:44:16.139499Z","submitted_at":"2024-07-10T15:07:58Z","title":"Fine-Tuning Large Language Models with User-Level Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07737","snapshot_observed_at":"2026-08-06T21:09:31.221412Z","title":"Brendan McMahan, Nicole Mitchell, Krishna Pillutla, and Keith Rush","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01129","last_updated":"2025-07-01T18:44:35Z","snapshot_observed_at":"2026-08-09T07:57:08.844393Z","submitted_at":"2025-07-01T18:44:35Z","title":"On Design Principles for Private Adaptive Optimizers","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T21:09:31.221412Z"},"links":{"cited_paper":"/paper/2407.07737","citing_paper":"/paper/2507.01129"},"observation_digest":"sha256:5a04474571b0dde13cf06726e61096b7968b9dd82dfe77a4af35fd1e1a97efdd","observation_id":"def44379-5fdb-4d66-9b89-b13190f6098d","resolution":{"observed_at":"2026-08-06T21:09:31.221412Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07737","last_updated":"2024-07-10T15:07:58Z","snapshot_observed_at":"2026-07-06T18:44:16.139499Z","submitted_at":"2024-07-10T15:07:58Z","title":"Fine-Tuning Large Language Models with User-Level Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07737","snapshot_observed_at":"2026-08-06T19:34:04.156388Z","title":"Qinzi Zhang, Hoang Tran, and Ashok Cutkosky","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.05610","last_updated":"2025-07-09T02:44:06Z","snapshot_observed_at":"2026-08-06T19:19:36.343625Z","submitted_at":"2025-07-08T02:38:14Z","title":"On the Inherent Privacy of Zeroth Order Projected Gradient Descent","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T19:34:04.156388Z"},"links":{"cited_paper":"/paper/2407.07737","citing_paper":"/paper/2507.05610"},"observation_digest":"sha256:5a39fe0d2aa83934eb30f592a888b9a7393a002f815e4955ee53f0520917b0c3","observation_id":"b994d25b-8049-4b31-8d14-3dc03894156e","resolution":{"observed_at":"2026-08-06T19:34:04.156388Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07737","last_updated":"2024-07-10T15:07:58Z","snapshot_observed_at":"2026-07-06T18:44:16.139499Z","submitted_at":"2024-07-10T15:07:58Z","title":"Fine-Tuning Large Language Models with User-Level Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07737","snapshot_observed_at":"2026-08-05T16:10:53.214154Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18911","last_updated":"2025-08-27T04:14:45Z","snapshot_observed_at":"2026-08-09T23:58:33.125526Z","submitted_at":"2025-08-26T10:34:13Z","title":"Enhancing Model Privacy in Federated Learning with Random Masking and Quantization","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-05T16:10:53.214154Z"},"links":{"cited_paper":"/paper/2407.07737","citing_paper":"/paper/2508.18911"},"observation_digest":"sha256:3de00a3e7cb0f21ab2f1a8125532dd7882c979fbbee808eb2ffecdb0030bb5a0","observation_id":"c95b0279-7f4a-4e75-8419-044adfbac69a","resolution":{"observed_at":"2026-08-05T16:10:53.214154Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07737","last_updated":"2024-07-10T15:07:58Z","snapshot_observed_at":"2026-07-06T18:44:16.139499Z","submitted_at":"2024-07-10T15:07:58Z","title":"Fine-Tuning Large Language Models with User-Level Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07737","snapshot_observed_at":"2026-08-05T15:26:33.422169Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.19870","last_updated":"2025-08-27T13:33:35Z","snapshot_observed_at":"2026-08-07T05:20:03.066438Z","submitted_at":"2025-08-27T13:33:35Z","title":"Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T15:26:33.422169Z"},"links":{"cited_paper":"/paper/2407.07737","citing_paper":"/paper/2508.19870"},"observation_digest":"sha256:8b06fca8da013d3d4bee32756cfc30bee853a1dd452f35a1f42507c266d5f1b1","observation_id":"3ef2fd98-721b-49af-a167-94f0b1624143","resolution":{"observed_at":"2026-08-05T15:26:33.422169Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07737","last_updated":"2024-07-10T15:07:58Z","snapshot_observed_at":"2026-07-06T18:44:16.139499Z","submitted_at":"2024-07-10T15:07:58Z","title":"Fine-Tuning Large Language Models with User-Level Differential Privacy","version":1},"cited_work":{"arxiv_id":"2407.07737","doi":"10.48550/arxiv.2407.07737","metadata_source":"arxiv_reference","pith_arxiv_id":"2407.07737","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"B.; Mitchell, N.; Pillutla, K.; and Rush, K","venue":"arXiv (Cornell University)","work_id":"be906f4c-5f9e-41bb-9547-079786e91a3d","year":2024},"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":7,"source":"arxiv_source","source_observed_at":"2026-05-25T08:28:39.748595Z"},"links":{"cited_paper":"/paper/2407.07737","citing_paper":"/paper/2509.12958"},"observation_digest":"sha256:12b2e02b5fb84a9cfc2929848c5bbef7ff3b7e60be5012d463ad997e1c855e92","observation_id":"aecfc9ef-cd51-47b7-be06-4d5b6c698f74","resolution":{"observed_at":"2026-05-25T08:30:31.793380Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07737","last_updated":"2024-07-10T15:07:58Z","snapshot_observed_at":"2026-07-06T18:44:16.139499Z","submitted_at":"2024-07-10T15:07:58Z","title":"Fine-Tuning Large Language Models with User-Level Differential Privacy","version":1},"cited_work":{"arxiv_id":"2407.07737","doi":"10.48550/arxiv.2407.07737","metadata_source":"arxiv_reference","pith_arxiv_id":"2407.07737","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"B.; Mitchell, N.; Pillutla, K.; and Rush, K","venue":"arXiv (Cornell University)","work_id":"be906f4c-5f9e-41bb-9547-079786e91a3d","year":2024},"citing_paper":{"arxiv_id":"2606.09145","last_updated":"2026-06-08T07:42:44Z","snapshot_observed_at":"2026-07-06T23:48:30.569726Z","submitted_at":"2026-06-08T07:42:44Z","title":"PrivCode++: Latent-Conditioned Differentially Private Code Generation for Comprehensive Guarantees","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-06-27T16:28:06.351376Z"},"links":{"cited_paper":"/paper/2407.07737","citing_paper":"/paper/2606.09145"},"observation_digest":"sha256:8f0c5c548ad31edbc44afb1163bfd0f52a9911a18cba706554083ad82f230367","observation_id":"dd902fb5-26dd-4979-a27e-dc34690c9163","resolution":{"observed_at":"2026-06-27T16:31:02.411009Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07737","last_updated":"2024-07-10T15:07:58Z","snapshot_observed_at":"2026-07-06T18:44:16.139499Z","submitted_at":"2024-07-10T15:07:58Z","title":"Fine-Tuning Large Language Models with User-Level Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07737","snapshot_observed_at":"2026-08-06T14:54:47.919996Z","title":"Fine-tuning large language models with user-level differential privacy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.04854","last_updated":"2026-08-05T13:47:59Z","snapshot_observed_at":"2026-08-08T23:13:18.685740Z","submitted_at":"2026-08-05T13:47:59Z","title":"Transforming Remanufacturing Automation with Large Language Models: A Forward-Looking Analysis with Case Studies","version":1},"reference_index":170,"source":"pdf_text","source_observed_at":"2026-08-06T14:54:47.919996Z"},"links":{"cited_paper":"/paper/2407.07737","citing_paper":"/paper/2608.04854"},"observation_digest":"sha256:2a74f64f22475f58af28fdeaca614c482220bfaf86b8a0110165307c83bc8cd7","observation_id":"01a5efd4-37ab-419f-946d-6bd9c8ea213c","resolution":{"observed_at":"2026-08-06T14:54:47.919996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2407.07737/citation-record","integrity":"/paper/2407.07737/integrity","json":"/paper/2407.07737/citation-record.json","paper":"/paper/2407.07737"},"outbound":[],"paper":{"arxiv_id":"2407.07737","last_updated":"2024-07-10T15:07:58Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T18:44:16.139499Z","submitted_at":"2024-07-10T15:07:58Z","title":"Fine-Tuning Large Language Models with User-Level Differential Privacy"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 10 inbound Pith citation observations for arXiv:2407.07737."}