{"as_of":"2026-08-20T13:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:753527014abc23302662f895df2bcf2345ca55e7a21f211cd8e67ece4f41445c","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T15:42:38.941337Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T19:34:51.631819Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-10T19:34:52.061222Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"cited_work":{"arxiv_id":"2502.06376","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.06376","snapshot_observed_at":"2026-08-10T19:34:52.061222Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","venue":"cs.LG","work_id":"508e5580-5260-4467-9e97-ffbe45496525","year":2025},"citing_paper":{"arxiv_id":"2501.09934","last_updated":"2026-05-27T03:21:28Z","snapshot_observed_at":"2026-08-19T14:28:10.180794Z","submitted_at":"2025-01-17T03:15:03Z","title":"HEART: Achieving Timely Multi-Model Training for Vehicle-Edge-Cloud-Integrated Hierarchical Federated Learning","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T19:34:51.631819Z"},"links":{"cited_paper":"/paper/2502.06376","citing_paper":"/paper/2501.09934"},"observation_digest":"sha256:ace7546bf92e7b63e7ef42d3641cb51e57b71da92d941c0497f64c4e047681e5","observation_id":"c6d452ac-b203-46ac-b953-497cfa60c4a1","resolution":{"observed_at":"2026-08-10T19:34:52.066622Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.06376/citation-record","integrity":"/paper/2502.06376/integrity","json":"/paper/2502.06376/citation-record.json","paper":"/paper/2502.06376"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.634576Z","title":"Natural gradient works efficiently in learning","venue":null,"work_id":"5fe28a1b-c02e-4995-9d21-23e5d02acdd6","year":1998},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.744435Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:19fd33b414876a828f3bd49d7d10a80fcf63266df2655bbaebdeec348be7b55f","observation_id":"c8fad235-5c1b-41d9-a25a-e9abbc623d29","resolution":{"observed_at":"2026-08-08T15:42:39.639312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.17465","last_updated":"2023-06-30T08:19:38Z","snapshot_observed_at":"2026-08-19T14:28:11.802836Z","submitted_at":"2023-06-30T08:19:38Z","title":"FedBone: Towards Large-Scale Federated Multi-Task Learning","version":1},"cited_work":{"arxiv_id":"2306.17465","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.17465","snapshot_observed_at":"2026-08-08T15:42:39.053727Z","title":"FedBone: Towards Large-Scale Federated Multi-Task Learning","venue":"cs.LG","work_id":"e65c64f3-0f46-44cc-a7e7-fd086941f659","year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.774247Z"},"links":{"cited_paper":"/paper/2306.17465","citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:ef2f5a0fdf01e753af370302596054c1d9a6135e6a7251437f27644dfbb7b472","observation_id":"2d111538-c8dc-48ab-bf1e-87afc104b98f","resolution":{"observed_at":"2026-08-08T15:42:39.058974Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.559667Z","title":"Remote sensing image scene classification: Benchmark and state of the art","venue":null,"work_id":"f4f520d1-9c2f-436b-af9b-37a5d89215ea","year":2017},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.779145Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:e24b5973b8077acfcfca021847afc05d761e377b424a209dc7a9f95cc9ef8f6c","observation_id":"1e273f64-f1a0-4fb3-a404-6a472dfe0d4b","resolution":{"observed_at":"2026-08-08T15:42:39.564474Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.528497Z","title":"Cimpoi, S","venue":null,"work_id":"ef5b19a9-03bc-4610-a71d-efb4a222c11e","year":2014},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.787945Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:29c267431821b6169d38ec886c939b1cc5479c9378c5c7784747e25e9002c16a","observation_id":"040d7bde-8f7d-42f4-872f-f3b3582794cf","resolution":{"observed_at":"2026-08-08T15:42:39.533530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.476078Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":"ad57f22f-fc48-43fd-b808-adce101c87ae","year":2021},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.806523Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:4545973d3f6eae57e3fe5f2ed42c07468cdb8e493918e09524145202598ede1b","observation_id":"3a1470e5-0c80-4826-8db7-b000df79dfab","resolution":{"observed_at":"2026-08-08T15:42:39.482140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.445729Z","title":"Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification,","venue":null,"work_id":"650f0e58-9728-4bf6-bb95-4969239140b0","year":2017},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.816642Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:3b9884e37b6baa7574be75369f68471f814a5c428be61b9a320f3de608d68194","observation_id":"f34c293c-4160-4626-8c42-81b5a674533c","resolution":{"observed_at":"2026-08-08T15:42:39.450340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.429435Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":"2c41f02f-1de8-47be-aaa0-154f8647bc21","year":2021},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.821426Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:60b63964c01659048e1bd74c05ec5fd56aa4016aafda145e87a318fe989aeaf0","observation_id":"425c669a-e3dc-4d54-8f7e-2a686429388d","resolution":{"observed_at":"2026-08-08T15:42:39.434390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.414444Z","title":"Emr-merging: Tuning-free high-performance model merging,","venue":null,"work_id":"22755d22-8e7c-4244-8f42-cee4de34d803","year":2024},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.825768Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:2cb7f7468cdd3adb8990df03a284e7baf648ad7eea6243b82f00ec422ea7ec29","observation_id":"63bfdde1-c420-48d1-a2fc-0bb826570d63","resolution":{"observed_at":"2026-08-08T15:42:39.419124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.383607Z","title":"3d object representations for fine-grained cate- gorization","venue":null,"work_id":"8654e717-22f2-4d5f-b70a-27e40e5462ab","year":2013},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.834668Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:324565dd776cf0e93c43faddb84e6da8218a4231087cd64fbf93540492d552e6","observation_id":"33fde33c-27ba-4fcc-8386-2875b554e3f2","resolution":{"observed_at":"2026-08-08T15:42:39.388300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.354832Z","title":"Mnist handwritten digit database","venue":null,"work_id":"8775f0ab-1fcc-4e4b-8e73-f6fbe793af8a","year":2010},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.843850Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:8ce52af68efb10f2d81ff4298d7173cc3c853a4dbf30a55643e248dbed40a5dc","observation_id":"51864d6c-f733-44b3-8c3e-e6e2ee2f7277","resolution":{"observed_at":"2026-08-08T15:42:39.359696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.324875Z","title":"Federated learning on non-iid data silos: An experimental study,","venue":null,"work_id":"481e1fcd-badb-41fc-a4b3-c9ea8b0a7e1e","year":2021},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.853378Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:a2913b6224c25d61fb05c0a001e6a6fb977a8ceaf1e0c5a9e57fd4ad1c5dc9cd","observation_id":"7146c2fe-1519-492c-be62-3a8b2034bff9","resolution":{"observed_at":"2026-08-08T15:42:39.329868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.308022Z","title":"Wasserstein task embedding for measur- ing task similarities","venue":null,"work_id":"9b66a4ac-e02c-4f36-87b9-136383ca2f24","year":2025},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.858142Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:14f90d844b7618d3f8ed3674ca1a34892270336c172399c6af918f56daffff2c","observation_id":"d1575371-19ab-4ad7-97c8-2335897e9c87","resolution":{"observed_at":"2026-08-08T15:42:39.314659Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.291483Z","title":"Communication-efficient learning of deep networks from decen- tralized data","venue":null,"work_id":"26a822a2-b887-4a46-9bbd-522c762c19ee","year":2017},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.867114Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:6eb8865bb5094c20bb3c0be3af3068abee4a947953add469e97dfca8be3a708b","observation_id":"176f0a5f-21b0-4a42-8637-94d0cf6e5e2d","resolution":{"observed_at":"2026-08-08T15:42:39.296208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.274688Z","title":"Fed up with complexity: Simplifying many-task federated learning with NTKFedavg","venue":null,"work_id":"52db25ed-b922-4f00-bce9-b97ae2860cbc","year":2024},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.871594Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:c0b552b629c533801c799b5e09496d6dd2e42648d675906cb31ad3765dd7fd9b","observation_id":"dbfd61ec-f8fb-4b8b-957b-95a9f49d0530","resolution":{"observed_at":"2026-08-08T15:42:39.280882Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.259281Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":"37b994e4-5291-4b0c-b5ca-ee1320ebb981","year":2011},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.876032Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:633990ce362d4fdd624dccfe691c5b869fb8b116f6f6b5f7348e07dbaffeb224","observation_id":"0d0eb8b7-55a0-4369-a8ca-744189058750","resolution":{"observed_at":"2026-08-08T15:42:39.264263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.243900Z","title":"Task arithmetic in the tangent space: Improved editing of pre-trained models,","venue":null,"work_id":"7d5a770a-bf46-4ab8-8caf-af797963cb61","year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.885859Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:f6919b8e10ee07a082c1d6e30f48ee9a2f4f8355e26ab612b50ab61a21042283","observation_id":"184c1e3e-2e43-4320-88bf-0f9aae997d82","resolution":{"observed_at":"2026-08-08T15:42:39.249111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.15384","last_updated":"2024-04-23T10:50:38Z","snapshot_observed_at":"2026-08-19T16:38:45.940990Z","submitted_at":"2024-04-23T10:50:38Z","title":"FL-TAC: Enhanced Fine-Tuning in Federated Learning via Low-Rank, Task-Specific Adapter Clustering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.15384","snapshot_observed_at":"2026-08-08T15:42:38.890182Z","title":"Fl-tac: Enhanced fine-tuning in feder- ated learning via low-rank, task-specific adapter clustering.arXiv preprint arXiv:2404.15384,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.890182Z"},"links":{"cited_paper":"/paper/2404.15384","citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:140b386d86277f056a92d619824b6b41425c4b5226e255732d3e95a530213951","observation_id":"ad42d544-3981-4767-b31f-e5ad0b236c48","resolution":{"observed_at":"2026-08-08T15:42:38.890182Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.228348Z","title":"The german traffic sign recognition benchmark: A multi-class classification competition","venue":null,"work_id":"5c7fe94e-39c5-4847-8c70-f7092018c74d","year":2011},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.895040Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:5de3e2687c55aaa3333399cc55524a7d9501cc45a868aee59f55509ded4e51a9","observation_id":"ce82bdb9-a4c3-4838-9253-635c191c57a7","resolution":{"observed_at":"2026-08-08T15:42:39.233035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.212759Z","title":"Improving lora in privacy-preserving federated learning,","venue":null,"work_id":"79b4291d-ca81-4e2e-a954-56e3e7c9d54c","year":2024},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.899550Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:f6bf19229cd0a408955f3e84aa5918a648b9bcd0a6bba1521ecabb6b18d9d24b","observation_id":"ed2f0f96-f911-4d2d-a8e4-df8f36650d8a","resolution":{"observed_at":"2026-08-08T15:42:39.217988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.197568Z","title":"Gradient masked averaging for federated learning,","venue":null,"work_id":"1db8dfcc-708a-4305-b116-e8f0c66c7ad1","year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.904156Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:a7f02c60816b442ba6e87865b1342936ae3e7f9e5e5ae3df57189cbfad1a2f83","observation_id":"074fb000-587a-4e68-b12e-e550576236ef","resolution":{"observed_at":"2026-08-08T15:42:39.202302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.182661Z","title":"Federated fine-tuning of foundation models via probabilistic masking,","venue":null,"work_id":"9a3af16d-7e15-4c86-b2bc-7970184b61bf","year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.908869Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:3e624a1c5ec966c09939b40ccdb5934975095a802ce55750065a8d35c023767b","observation_id":"dacd9d8b-b4e0-4277-a21a-9551054b1e6e","resolution":{"observed_at":"2026-08-08T15:42:39.187573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.167224Z","title":"Spot: Better frozen model adaptation through soft prompt transfer,","venue":null,"work_id":"5dcc3890-b9ca-44ab-ab2b-d66a27624cf1","year":2022},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.913429Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:d9dcedae38a59593e0fae75e2b6a44d65a0b0dc75f093b5e84d8e2f4eea21293","observation_id":"e97defab-cf7c-423f-98db-7c47efd91b45","resolution":{"observed_at":"2026-08-08T15:42:39.172394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.151828Z","title":null,"venue":null,"work_id":"27c09096-dd2d-425b-9ff3-125bd86a3144","year":2010},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.918289Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:d400f48ef646c951af0d8fd6077b0eebac7bbcf510af17885b1c242263f896ee","observation_id":"f58aab4c-cfeb-4d14-bc78-0dd9475a729c","resolution":{"observed_at":"2026-08-08T15:42:39.156705Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.135535Z","title":"Adamerg- ing: Adaptive model merging for multi-task learning,","venue":null,"work_id":"3c8d8c76-bf8a-48ff-bcbe-2916292b9b54","year":2024},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.922765Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:b2adc27611f2d9cdb02a99badb19b5412cb405389a8b0c975d80bbeaa31fa618","observation_id":"66412746-2111-4485-adfc-73d3665237e3","resolution":{"observed_at":"2026-08-08T15:42:39.140811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13283","last_updated":"2024-02-11T11:38:38Z","snapshot_observed_at":"2026-08-19T14:24:55.339939Z","submitted_at":"2023-10-20T05:24:28Z","title":"pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.13283","snapshot_observed_at":"2026-08-08T15:42:38.927051Z","title":"Fedlora: Model-heterogeneous personalized federated learn- ing with lora tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.927051Z"},"links":{"cited_paper":"/paper/2310.13283","citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:7e5c665b0435c1f48b203c657245416574a8fd0e78c75281571d50d53b99ff4c","observation_id":"efed6137-f862-4e14-a0ec-99b200f1839f","resolution":{"observed_at":"2026-08-08T15:42:38.927051Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.117274Z","title":"Language models are super mario: Absorbing abili- ties from homologous models as a free lunch,","venue":null,"work_id":"2be29b5c-fa60-4249-a454-39b93133ea6f","year":2024},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.931936Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:1c33567735c24f0c9235bd7c219ff09ea13c191a3ddea3a26e439f8fc72ee868","observation_id":"f1ea16ff-2917-4e80-bb00-e6d91e619643","resolution":{"observed_at":"2026-08-08T15:42:39.123617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.101587Z","title":"Taskon- omy: Disentangling task transfer learning,","venue":null,"work_id":"924e1e84-6949-48fb-b4c1-8ce296e64931","year":2018},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.936782Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:7ddd9e9a1e7f242e9372121e1fd63db3305348fb4250950b118435b6dedfe694","observation_id":"298310c6-d8bb-41ff-9990-4d6fc8ba656b","resolution":{"observed_at":"2026-08-08T15:42:39.106346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.619499Z","title":"Federated learning with personalization layers,","venue":null,"work_id":"31f6fb59-5b8e-4f0a-ad6b-0ea3af3b36ff","year":2019},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":1998,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.749902Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:2e83669d3fd6cdc994fdcf34027a88705f7e591913782f61ae018ba2d878b812","observation_id":"43639036-a501-481e-a1c0-129954b494c5","resolution":{"observed_at":"2026-08-08T15:42:39.624283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.492936Z","title":"Pactran: Pac-bayesian metrics for estimating the transferability of pretrained models to classifi- cation tasks,","venue":null,"work_id":"9f848f69-ede2-455e-adde-afa9dfc5ccf6","year":2022},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.796861Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:d309e646dfaff9ae917a756fbaaa74e5620bbf82658a1702ed7cb899a52fb171","observation_id":"7bf662ff-bb84-4756-a558-8eff24a4d40f","resolution":{"observed_at":"2026-08-08T15:42:39.498639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.340146Z","title":"Federated opti- mization in heterogeneous networks,","venue":null,"work_id":"922621eb-6725-4236-b758-6840ba6617f3","year":2020},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2010,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.848403Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:ee1b2d7213a427c891b8484e9777098b9b94d8e54feb2cc336284c454d85d28f","observation_id":"ae3c852b-f64e-4fd2-8eeb-907ef0fe5504","resolution":{"observed_at":"2026-08-08T15:42:39.344883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.15182","last_updated":"2024-04-12T00:36:43Z","snapshot_observed_at":"2026-08-16T14:01:33.964288Z","submitted_at":"2024-04-12T00:36:43Z","title":"FLoRA: Enhancing Vision-Language Models with Parameter-Efficient Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.15182","snapshot_observed_at":"2026-08-08T15:42:38.880515Z","title":"Flora: Enhancing vision-language models with parameter-efficient federated learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2011,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.880515Z"},"links":{"cited_paper":"/paper/2404.15182","citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:d71b26bc5cfe56e88843a5aed0efad558703776b458c13e7671367cdbd1d3df5","observation_id":"d0122bf2-9bfd-4123-9f9e-c1005744c4a0","resolution":{"observed_at":"2026-08-08T15:42:38.880515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.369063Z","title":"Federatedscope-llm: A com- prehensive package for fine-tuning large language models in fed- erated learning,","venue":null,"work_id":"bfff55e7-c481-44dc-8424-0688e9dace6a","year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.839022Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:f3e5c0259667be2cbd992b8b808e8233b320e1a0f1151edc6f5ec8c59a8293a8","observation_id":"e655447d-07b9-4a04-8de8-203580ade09b","resolution":{"observed_at":"2026-08-08T15:42:39.373674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.510631Z","title":"Imagenet: A large-scale hierarchical im- age database","venue":null,"work_id":"265d3109-86e1-49d8-82f5-ff25e225a806","year":2009},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.792168Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:85d98cff3cbe42c8aa092c320418fb1c6cbe6a26a2ab37ddb80cc8a03ccc3a2c","observation_id":"2d6ea6ab-af96-4b00-ab79-80161ec1e233","resolution":{"observed_at":"2026-08-08T15:42:39.516448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.543708Z","title":"Heterogeneous loRA for federated fine-tuning of on-device foundation models","venue":null,"work_id":"a0280d9b-4ef5-44ee-b46b-aa61b36db116","year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.783787Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:3a0b4d950f6f59e0a72397603ec271a31a34725f5e254c9f2b52e68c1c42e4f3","observation_id":"2aff5785-ca35-4be1-80f4-235e5237e8a9","resolution":{"observed_at":"2026-08-08T15:42:39.548734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.085322Z","title":"Mas: Towards resource-efficient feder- ated multiple-task learning","venue":null,"work_id":"41e7d320-aa9f-45ae-af6a-63c2889838bb","year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.941337Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:e5601276f8b08df9a871b97ee028a8d25b1dc702a1812face0d28565e28113a6","observation_id":"c75963b9-52dc-4f35-81d3-89d25fef4ef3","resolution":{"observed_at":"2026-08-08T15:42:39.090216Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.604730Z","title":"Ezzeldin, Qingfeng Liu, Kee-Bong Song, Mostafa El-Khamy, and Salman Avestimehr","venue":null,"work_id":"308bf369-c44d-4448-9043-8e8f0650e5d1","year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.754522Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:ffcc30448dffd121192891481c375b6150ad1fae8f9f659a7ffb9ba3788748a2","observation_id":"b4baa1e8-a666-408f-93f2-1cf285f1d0ba","resolution":{"observed_at":"2026-08-08T15:42:39.609545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.574190Z","title":"Many-task federated learning: A new problem set- ting and a simple baseline","venue":null,"work_id":"cc33f12a-36b0-4215-89e2-86b29157e9b3","year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.769378Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:62aaa51d0769958309cc294f4d92965665205208119bd1d973e4f2ca72551775","observation_id":"a28190fb-cfc1-4d2f-9d24-093ba4821cab","resolution":{"observed_at":"2026-08-08T15:42:39.579118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.460620Z","title":"Etran: Energy-based transferability estimation,","venue":null,"work_id":"8aaf9989-1e79-4222-b34f-8a4f64866078","year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.811861Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:fa363cde54f4493c8feac7ca08333cfdbcc3696d994dc2a428c40eaa317a212f","observation_id":"1dfdc521-6ec8-4c24-beea-f13ba1446b0b","resolution":{"observed_at":"2026-08-08T15:42:39.465270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.14390","last_updated":"2022-03-05T20:30:32Z","snapshot_observed_at":"2026-07-06T09:42:35.058716Z","submitted_at":"2020-07-28T17:59:07Z","title":"Flower: A Friendly Federated Learning Research Framework","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.14390","snapshot_observed_at":"2026-08-08T15:42:38.764345Z","title":"Flower: A friendly federated learning research framework","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.764345Z"},"links":{"cited_paper":"/paper/2007.14390","citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:aab11b45ff5ea19b41e4aefddaca3cdc4b6dbd210d46004f4143c004bdba1c38","observation_id":"fce4018a-5dfb-4f68-9525-78bfe56bb0cb","resolution":{"observed_at":"2026-08-08T15:42:38.764345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.589739Z","title":"An information-theoretic approach to transferability in task transfer learning,","venue":null,"work_id":"f8a8996b-372c-453c-9b0a-7264a11e0c06","year":2022},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.759525Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:d11a16c206ad7459940eb688c65efeb1a11e3ddc6d997ee1ff8dbc1d10480a38","observation_id":"b4b15e29-eb33-419e-88fe-14d3b9c23fa2","resolution":{"observed_at":"2026-08-08T15:42:39.594523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:42:39.399126Z","title":"Editing models with task arithmetic,","venue":null,"work_id":"c490acd2-2c45-425f-a9e0-e5ec0c6bfa8a","year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.830305Z"},"links":{"citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:8516f3830bab68357b4d3f9b15184b9021d7245bd77749396fb3b72783f71bc6","observation_id":"a393c411-d306-4ab3-97c2-4b551ac1c218","resolution":{"observed_at":"2026-08-08T15:42:39.403953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.13250","last_updated":"2024-02-29T03:32:35Z","snapshot_observed_at":"2026-08-20T10:11:56.975584Z","submitted_at":"2023-11-22T09:12:50Z","title":"FedHCA$^2$: Towards Hetero-Client Federated Multi-Task Learning","version":2},"cited_work":{"arxiv_id":"2311.13250","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.13250","snapshot_observed_at":"2026-08-08T15:42:39.029364Z","title":"FedHCA$^2$: Towards Hetero-Client Federated Multi-Task Learning","venue":"cs.CV","work_id":"862e7655-deae-4593-a1d9-9174d12ad4f3","year":2023},"citing_paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors","version":3},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-08T15:42:38.862479Z"},"links":{"cited_paper":"/paper/2311.13250","citing_paper":"/paper/2502.06376"},"observation_digest":"sha256:25c94a89c4d73435e0278ee16b7733d1b0d0fea03ec2ca1b5bfcdf6b437f9a3b","observation_id":"6f049c2b-c304-464a-818a-58dda84ef99d","resolution":{"observed_at":"2026-08-08T15:42:39.037279Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.06376","last_updated":"2025-07-08T21:23:10Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T14:27:35.636066Z","submitted_at":"2025-02-10T11:56:02Z","title":"Many-Task Federated Fine-Tuning via Unified Task Vectors"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":2,"verified_fuzzy":35},"total_outbound_references":42},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2502.06376."}