{"as_of":"2026-08-08T05:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e5098df447899be05110a3f597d09d0ca748fdccaa00e2b5447833946141c1d2","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T07:33:07.725318Z","state":"measured"},{"denominator":49,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":49,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2607.21417/citation-record","integrity":"/paper/2607.21417/integrity","json":"/paper/2607.21417/citation-record.json","paper":"/paper/2607.21417"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:03.993210Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:03.993210Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:c0cf6bf046f3deb1763b3f85b16443a8c28ae6d69cf627c33995a299a5ead09f","observation_id":"f04b6b89-6a88-4253-9c50-d48125eaf478","resolution":{"observed_at":"2026-08-01T07:33:03.993210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.038962Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.038962Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:57732532650e05819594375de538dc46af3afbc9bb94d979a46aac91dd8e6287","observation_id":"78aca27a-545a-45c6-920a-515979f504d8","resolution":{"observed_at":"2026-08-01T07:33:04.038962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.115387Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.115387Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:743cd9d1c743c4fe071e9b4ded42f8ce42b4967d332124b474a56ee6ec175eaf","observation_id":"a02937db-d1bc-4820-8734-840794ae7800","resolution":{"observed_at":"2026-08-01T07:33:04.115387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.173590Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.173590Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:4a326a5a04078a4f6214f4e2f7de719c441f5bc7361999e78caee21e0059685f","observation_id":"547caf41-5b55-4840-9992-0a2663eb3fb7","resolution":{"observed_at":"2026-08-01T07:33:04.173590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.257187Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.257187Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:c0807138963b2985fd587337e897c8acffff7e4a29afae92947d824b8bcc339f","observation_id":"d18e5115-28e0-43b5-95cb-f384ab01eb64","resolution":{"observed_at":"2026-08-01T07:33:04.257187Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.334687Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.334687Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:145bff6ebae7685781a9c7ee5f9479165ef8a2be69e2d729372258be8c3229e7","observation_id":"2c5db5e5-1d39-4936-9c7c-b6627f182356","resolution":{"observed_at":"2026-08-01T07:33:04.334687Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.390535Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.390535Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:8d418b3d5f5029d3053671a482caae454a45b7aed36f80f8973bf4f637c27b02","observation_id":"56b51cc7-4a9f-472d-8f9c-29547c7ebe1f","resolution":{"observed_at":"2026-08-01T07:33:04.390535Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.481548Z","title":null,"venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.481548Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:cb8d6837e80a278ef642117babab646493197aee9b9dc3f77a67ea7edcb74c81","observation_id":"071cf4e8-38ac-499a-aa89-fc099f409af3","resolution":{"observed_at":"2026-08-01T07:33:04.481548Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.531155Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.531155Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:a68cdc6359c78146484c95b2899871446aee63c824144d25f1d8ad9228d7664a","observation_id":"23cdbb54-fca0-4d18-9714-285e223a7efc","resolution":{"observed_at":"2026-08-01T07:33:04.531155Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.605312Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.605312Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:7851c42d11e1f83b56429b10d327d675585c82b789469e9cf7fdbc1ce5267ded","observation_id":"6e54800c-558e-4fee-9944-d45a9b145cac","resolution":{"observed_at":"2026-08-01T07:33:04.605312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.687258Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.687258Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:3602bbcd83a505e9ab71084b7386cbb045e76f484171538cefd24c34915bab34","observation_id":"f7823230-dde0-4d07-ac30-5494b4fc2b47","resolution":{"observed_at":"2026-08-01T07:33:04.687258Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.755185Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.755185Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:38f0182b515ecf115d1e36a73188377a3c826a27f8010a842918fd416b85a367","observation_id":"d24b037e-64e6-4cca-86a2-b093e1481a77","resolution":{"observed_at":"2026-08-01T07:33:04.755185Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.817524Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.817524Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:ca4432549f867277d7c09ffbfc4687644e0b30494a9a418d9060342f3b12581a","observation_id":"64bffbd7-c3a4-48e4-b648-3996ee21e2c3","resolution":{"observed_at":"2026-08-01T07:33:04.817524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.905125Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.905125Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:fca6aaa55bb8a7b46434047ec7ad21c7d5bc73b2d81a605aaeb274ba043011f5","observation_id":"5841e3be-a643-4011-8058-e14d5ad867d2","resolution":{"observed_at":"2026-08-01T07:33:04.905125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:04.964954Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:04.964954Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:18fc0e83f949170c6a5484e7864c94cf39afba4706067987a043018441f01865","observation_id":"9c5a5225-e3f9-4e44-86e0-044d280c970c","resolution":{"observed_at":"2026-08-01T07:33:04.964954Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22447","last_updated":"2025-05-28T15:09:56Z","snapshot_observed_at":"2026-08-07T13:04:42.049006Z","submitted_at":"2025-05-28T15:09:56Z","title":"Privacy-preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.22447","snapshot_observed_at":"2026-08-01T07:33:05.032359Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.032359Z"},"links":{"cited_paper":"/paper/2505.22447","citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:d046fa9dc819da785fa53d7adb6ff0112cb3e335aa2417bd80b59568c09a8fdb","observation_id":"92be24a2-b96f-4658-8b54-a7fc956fa0d0","resolution":{"observed_at":"2026-08-01T07:33:05.032359Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.099557Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.099557Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:609668127a929dc1a8537b944bc9a0c2e37c55879ce04dbda016c7f9e057f80a","observation_id":"6bc19a83-2993-44db-8d97-09053c4ea5a1","resolution":{"observed_at":"2026-08-01T07:33:05.099557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.06093","last_updated":"2023-08-25T14:30:45Z","snapshot_observed_at":"2026-07-06T16:05:15.383292Z","submitted_at":"2023-08-11T12:05:12Z","title":"Experts Weights Averaging: A New General Training Scheme for Vision Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.06093","snapshot_observed_at":"2026-08-01T07:33:05.152405Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.152405Z"},"links":{"cited_paper":"/paper/2308.06093","citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:39edc3f877695bdaf6dba0755de1fe7a5e1d1f74a8cde28a7418b4e9ab9fa085","observation_id":"16912c84-36d5-44bb-96f6-35527dfdbbde","resolution":{"observed_at":"2026-08-01T07:33:05.152405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.234789Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.234789Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:ec5b6e939f189bb6e3aaa8cb56c336b666c1d8bed844ad4706cb5b418fab281a","observation_id":"d8b42974-dc51-48e5-b703-c3c2fc4c250d","resolution":{"observed_at":"2026-08-01T07:33:05.234789Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.272800Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.272800Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:4ebf3c23b5b8068f6c0c1e08c38928ceadaa435b083aa136315db4638723b06b","observation_id":"468a2a23-dae4-462c-917e-97065bdb845c","resolution":{"observed_at":"2026-08-01T07:33:05.272800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.320557Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.320557Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:99ecf1f102c11fabfb981bc9da6f8dd7670d23b7a8d8af96b338d9b21e59b0f0","observation_id":"d275192e-8506-40f0-8912-648666222f3d","resolution":{"observed_at":"2026-08-01T07:33:05.320557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.406093Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.406093Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:58d26f38e1bf5b83276286defeeac52bc618e40fe4705296c013d4af4489eef7","observation_id":"251a50f6-8f89-40c4-873b-5e781712f8ae","resolution":{"observed_at":"2026-08-01T07:33:05.406093Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.455047Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.455047Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:066bc59db2e22f3a310959ab94cb763bf4644953d2cb3be6a5dc7174c2c97c19","observation_id":"37c36149-6bd0-4d80-bc51-4fc1a9ca8cd7","resolution":{"observed_at":"2026-08-01T07:33:05.455047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.506729Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.506729Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:d554c1809671ed5905dfd078a76728a5110600de55191bbfba22902cb8805c1e","observation_id":"dc8e6399-78bd-4436-9a9d-1b1c060e0935","resolution":{"observed_at":"2026-08-01T07:33:05.506729Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.554952Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.554952Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:319333733f633d69abd645aa050bcb6d5646697110c79da3b65f8b272fcdcd20","observation_id":"a8ab002d-a105-40b7-9725-09a890e7ede3","resolution":{"observed_at":"2026-08-01T07:33:05.554952Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.594067Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.594067Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:135907d2dfef3d9b108e703b804e1e4748dd3fbc2b17cd1f47f6a0aae6e110f8","observation_id":"3e7141a0-0049-4c18-847c-579fe5bc0a6c","resolution":{"observed_at":"2026-08-01T07:33:05.594067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.659282Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.659282Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:960fdc551b9abccea2292b4cf4390003a97eba27f86a8c3891143163ebd05cca","observation_id":"b9976fe9-d035-4cc6-82da-1d2880f792d0","resolution":{"observed_at":"2026-08-01T07:33:05.659282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.765252Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.765252Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:7cb4d9eadc2dd8b69b52887492103449a48c52c3ca0fc8b0c71b33ea5a247c78","observation_id":"ae03abde-9ae2-4f69-8cc4-c6b63d7c598c","resolution":{"observed_at":"2026-08-01T07:33:05.765252Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.835342Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.835342Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:9221b12ad299fc3de56a2247327a03fdcddb47ec4535be9bc47b734ef4cc3f03","observation_id":"b4fa25da-35d4-4056-8980-8a508fb3f5eb","resolution":{"observed_at":"2026-08-01T07:33:05.835342Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:06.067544Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:06.067544Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:fa1bb518e051e6bce365daca85a3cafde3e45d4604dd83cd2196b9c7fb3c1516","observation_id":"53fa4a52-31cd-4a32-aa89-264a7c02790c","resolution":{"observed_at":"2026-08-01T07:33:06.067544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:06.179341Z","title":null,"venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:06.179341Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:0a64da71c7bf31b96fea3f822d2d06890a2c6d94b54db4b1b9d59188ac7d9c82","observation_id":"93324b6c-5844-4956-a7f4-74ae50f04efa","resolution":{"observed_at":"2026-08-01T07:33:06.179341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:06.334065Z","title":"Roy-Chowdhury, Srikanth V","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:06.334065Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:0e57e60ec13006812bea4f3bbdb4de05241879015510c81daa8a10ede9f62adf","observation_id":"ca7bc967-b2cb-49a2-844e-1b071eb7bf3c","resolution":{"observed_at":"2026-08-01T07:33:06.334065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:06.436138Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:06.436138Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:d350de3f6fa8e6641b77963fca534a08a0951fa0b9c36524a85d631b6b3e12b2","observation_id":"b50f17dd-78c9-4759-895b-599815093a04","resolution":{"observed_at":"2026-08-01T07:33:06.436138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:06.574028Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:06.574028Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:16763726b1b818e719566448e88e22c623150b1142e736ddee65524a140e7aa5","observation_id":"fe3d8983-53a0-49d2-b891-a275c638491c","resolution":{"observed_at":"2026-08-01T07:33:06.574028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:06.743102Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:06.743102Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:8215f5b80e4c926732a66d71f86a0d760e3b4c4c1dc73bf94e2725c868b9dad7","observation_id":"65917a67-f072-457c-9d25-edf52c78bb03","resolution":{"observed_at":"2026-08-01T07:33:06.743102Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:06.855320Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:06.855320Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:f69c52bc625663843f09382e2d218d8a5eb63b12e8c0fc9348a687aca2baf99c","observation_id":"76b2154f-149e-49da-9b85-21af48da8cf7","resolution":{"observed_at":"2026-08-01T07:33:06.855320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:06.955421Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:06.955421Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:1193cf6bba8fa5100f718a12e15a7c2c5b56d697f6963bf2485b7b8d930a3699","observation_id":"9b4bc4c0-8fb6-48b6-a243-8f042dae1ccd","resolution":{"observed_at":"2026-08-01T07:33:06.955421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:07.118578Z","title":"Vincent Poor","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:07.118578Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:20ad0b6d9673c2693a928a3f21d3aeead566b0246fc78df5b783cded9eea24e5","observation_id":"2f945a10-1b67-49da-8cc1-9355212249a4","resolution":{"observed_at":"2026-08-01T07:33:07.118578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:07.217381Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:07.217381Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:ee4f5ac7c820bc106e715ffde5b4ae29ce2c555f5cf6301704cfe0b4449639fa","observation_id":"3adf87bc-4e61-423e-a1b9-5a3a8f2e866a","resolution":{"observed_at":"2026-08-01T07:33:07.217381Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:07.376920Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:07.376920Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:861dafcda24ba19a6ca30b3b30d3b105c5a2bf201e3cabdf38da375b166386d4","observation_id":"e6d88fb3-0a3a-4b65-a2b8-9d1047a149d9","resolution":{"observed_at":"2026-08-01T07:33:07.376920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:07.391302Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:07.391302Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:37023925ec49c68e855fe5033871603e8d0ae0231383d972301f4cdedf5e72c8","observation_id":"9913b131-e342-41a9-87bd-d64890533833","resolution":{"observed_at":"2026-08-01T07:33:07.391302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:07.418337Z","title":"Yuen, and Dacheng Tao","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:07.418337Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:815a8d8ad8cd6c57798e70a878f0da7b46178c48481353f8dfec5b94f3f9f560","observation_id":"5138d27d-9927-4ae1-835d-ebcc91747e1a","resolution":{"observed_at":"2026-08-01T07:33:07.418337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:07.531120Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:07.531120Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:20b7d9bcee14be05c1b978a9e09ab373ba5056a524f394bc221a5c77855aaf91","observation_id":"f67b7302-0f11-4b05-ae77-53cb7771a596","resolution":{"observed_at":"2026-08-01T07:33:07.531120Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:07.674325Z","title":"Rajapakse","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:07.674325Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:8e6ef0c10b75ba0e143bbf4274eb7d55e8f142ff0e8a4b9319f2f6d9b42e8c26","observation_id":"48a1bf1c-e7a1-4c93-a888-e073465895b2","resolution":{"observed_at":"2026-08-01T07:33:07.674325Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:07.684816Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:07.684816Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:bef5c8fc9dfab626220b8f3807144992ce17c6032e6ab5e34f020dd14e87ddd1","observation_id":"8f53d218-36da-4529-9f42-611829a1c664","resolution":{"observed_at":"2026-08-01T07:33:07.684816Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:07.712439Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:07.712439Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:5ce8db7c2a49480387e7f802365377afcf45cf5e18ffedc74cf40e4b0a4ff89e","observation_id":"0b240b56-1e71-4122-a0bd-35179880d71a","resolution":{"observed_at":"2026-08-01T07:33:07.712439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:07.719045Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:07.719045Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:b9863970b2dbef045cde8feb9e4b542bc3c613cd24568d799667596951d7e2d1","observation_id":"30b7fee1-f45a-42ca-922f-f9eec248bed9","resolution":{"observed_at":"2026-08-01T07:33:07.719045Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:07.725318Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:07.725318Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:d34df03dbdf79956172b415b6a1dc8b8bfaa79b224086bb2f1819d6b88386217","observation_id":"dc11d1e3-c6f5-4433-92b6-631f8949b08d","resolution":{"observed_at":"2026-08-01T07:33:07.725318Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:33:05.949597Z","title":"InProceedings of the IEEE/CVF international conference on computer vision","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-01T07:33:05.949597Z"},"links":{"citing_paper":"/paper/2607.21417"},"observation_digest":"sha256:e85b6dba1e9d78a58b99e8016534595c7d1281fc79c88a3f6693811b457c9727","observation_id":"6165e35d-7651-451a-a56b-79b22ed0b4a8","resolution":{"observed_at":"2026-08-01T07:33:05.949597Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.21417","last_updated":"2026-07-23T15:22:48Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T18:57:10.535792Z","submitted_at":"2026-07-23T15:22:48Z","title":"Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":48,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":49},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2607.21417."}