{"as_of":"2026-08-07T18:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:41329dc632b8cfb1f31bf80b76a37d433743b0392657a16e9e96dd239c59c0ee","coverage":[{"denominator":59,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":59,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:36:53.073061Z","state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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":"2026-06-29T13:36:39.308309Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-06-29T13:53:28.990736Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"cited_work":{"arxiv_id":"2506.21144","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.21144","snapshot_observed_at":"2026-06-29T13:53:28.990736Z","title":"Person- alized federated learning via dual-prompt optimization and cross fusion.arXiv preprint arXiv:2506.21144,","venue":null,"work_id":"f61b089d-df36-4bc0-8452-4b1588885420","year":null},"citing_paper":{"arxiv_id":"2605.27900","last_updated":"2026-05-27T03:21:49Z","snapshot_observed_at":"2026-08-01T05:48:06.708767Z","submitted_at":"2026-05-27T03:21:49Z","title":"Decoupled Training with Local Reinforcement Fine-Tuning in Federated Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-29T13:36:39.308309Z"},"links":{"cited_paper":"/paper/2506.21144","citing_paper":"/paper/2605.27900"},"observation_digest":"sha256:271a01e8affa8f636dc01465baa74daa49f38a90ed7ebd2bd57a25192d98675c","observation_id":"a5a17d79-1da3-4f17-8961-d5a5f015a67d","resolution":{"observed_at":"2026-06-29T13:53:28.992487Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.21144/citation-record","integrity":"/paper/2506.21144/integrity","json":"/paper/2506.21144/citation-record.json","paper":"/paper/2506.21144"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:37:01.194868Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":"32b1f1be-f3cc-41d3-bb58-2de108291e8d","year":2021},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:47.159090Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:21455c4154d1a76d0ba98e8ec3f9005efa077eb79ba3db164cd596ed0e08e9d3","observation_id":"3d9540a4-7cde-4e3e-883d-4efea569bb13","resolution":{"observed_at":"2026-08-06T22:37:01.247874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:37:01.066250Z","title":"Promptfl: Let feder- ated participants cooperatively learn prompts instead of models-federated learning in age of foundation model,","venue":null,"work_id":"8365e78a-5537-42b7-9061-0041ad900df0","year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:47.269101Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:efc0f3984985026f700e247d654d69da23cf6239a689c61360e7510f56b81211","observation_id":"a1dc1e37-84b7-4b06-bb30-105f20a4615b","resolution":{"observed_at":"2026-08-06T22:37:01.122097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:37:00.934429Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":"887afa9a-0f96-4699-b69f-d1c518498c82","year":2020},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:47.348661Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:fd570ba9e42779afae2701da60f88cca3a4656a9d03236b7e11b12bf66918b13","observation_id":"4dbe9e80-1cca-41d2-86ab-eb6cd4234103","resolution":{"observed_at":"2026-08-06T22:37:00.976761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:37:00.816102Z","title":"Global and local prompts coop- eration via optimal transport for federated learning,","venue":null,"work_id":"7bcb5e17-b7b7-49e6-bc2a-871020310019","year":2024},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:47.455115Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:9ec0aa38293c69b642c5c7f55761686696874f93c7a877eba2e0d5c5b2cf9fe7","observation_id":"0701138a-da7c-4aa5-bbba-efa32e55516d","resolution":{"observed_at":"2026-08-06T22:37:00.858784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:37:00.663228Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":"01057e55-07a8-4b61-ba9d-957bf1f09f64","year":2017},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:47.584997Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:e631c6de1af85fbc2a2ffd1c69e65344b8e4ff32849fb9a406716510169c7c7a","observation_id":"c9b15bb7-2d0f-4e7f-bb5a-d064bd9dfab6","resolution":{"observed_at":"2026-08-06T22:37:00.741610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.11414","last_updated":"2024-03-19T20:04:43Z","snapshot_observed_at":"2026-07-06T15:29:31.707746Z","submitted_at":"2023-05-19T03:51:59Z","title":"Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.11414","snapshot_observed_at":"2026-08-06T22:36:47.680139Z","title":"Federated foundation mod- els: Privacy-preserving and collaborative learning for large models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:47.680139Z"},"links":{"cited_paper":"/paper/2305.11414","citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:258fbdb3c680b553b385531810ab7ad244a4a92242e0002a1b4409de5294247b","observation_id":"6882a275-b96b-492a-b12e-99218086745b","resolution":{"observed_at":"2026-08-06T22:36:47.680139Z","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":"2026-08-06T22:37:00.520716Z","title":"Feddisco: Fed- erated learning with discrepancy-aware collaboration,","venue":null,"work_id":"83c20dc3-0e76-4b8d-8771-9f289a83b5b5","year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:47.811019Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:2369dcd6b8e138bafd3a0ef1aaa5e51ef5c24fbeec7ebad1cd774acec16a838f","observation_id":"a6a034c2-686a-4d59-8c34-048854b9dfb6","resolution":{"observed_at":"2026-08-06T22:37:00.588972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:37:00.381351Z","title":"Not all minori- ties are equal: Empty-class-aware distillation for heterogeneous federated learning,","venue":null,"work_id":"4730a4c4-dd2f-4f78-81da-2d238cc9712f","year":2025},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:47.971467Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:e0bbf014126625a18b0cf437451e96e938b274739d11dc2d0568999e728ae269","observation_id":"c14fca99-caf4-48fa-994d-9a921e654c5e","resolution":{"observed_at":"2026-08-06T22:37:00.439281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:37:00.246919Z","title":"Harmonizing generalization and personalization in federated prompt learning,","venue":null,"work_id":"70acd5ca-1b5a-4ee6-ad77-52de35412fee","year":2024},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:48.097886Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:6e5210fee4b45c44fec9de6b4e849fa00522b4169ae49fd6ebf8ee7bcec436ae","observation_id":"8053258c-a50f-4ea4-93ae-205a28f74d56","resolution":{"observed_at":"2026-08-06T22:37:00.304369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:37:00.082117Z","title":"Efficient model person- alization in federated learning via client-specific prompt generation,","venue":null,"work_id":"c2deafe3-7be9-482a-ba80-931d7e38ae18","year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:48.256487Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:5ad1c428640494bb38ef13b3bb806646fecc75bdc588962e58d5473755d62631","observation_id":"8ac4152f-cba5-4a69-acb0-3bdd9335fb01","resolution":{"observed_at":"2026-08-06T22:37:00.161875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:59.941808Z","title":"Scaling up visual and vision-language representation learning with noisy text supervision,","venue":null,"work_id":"012aaa75-3871-4a29-ab30-cccc4e2433df","year":2021},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:48.366274Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:208bb77f2f2248d4c442cc3002b2aeb041bdc08876dbed7a6bc45e05287415a9","observation_id":"aa91972e-5347-475a-ad8c-86f080e78ab7","resolution":{"observed_at":"2026-08-06T22:36:59.990668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.12268","last_updated":"2023-01-24T13:07:01Z","snapshot_observed_at":"2026-07-06T13:45:31.237782Z","submitted_at":"2022-08-25T15:27:41Z","title":"FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.12268","snapshot_observed_at":"2026-08-06T22:36:48.434213Z","title":"Reduce communication costs and preserve privacy: Prompt tuning method in federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:48.434213Z"},"links":{"cited_paper":"/paper/2208.12268","citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:58f962e5b0cd0a2162a2dadd1a931d868d32d85b6695e9592289967172c2a62e","observation_id":"007e9351-5617-4550-8d81-4eaa05f31778","resolution":{"observed_at":"2026-08-06T22:36:48.434213Z","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":"2026-08-06T22:36:48.528866Z","title":"Pre- train, prompt, and predict: A systematic survey of prompting methods in natural language processing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:48.528866Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:e0d03f191e817f133917744fc2dd695dc879a7d1201b72a78a094555985928ca","observation_id":"92d11d26-ad3f-4093-b8db-3d6967ac80d8","resolution":{"observed_at":"2026-08-06T22:36:48.528866Z","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":"2026-08-06T22:36:59.797763Z","title":"Fedbn: Federated learning on non-iid features via local batch normalization,","venue":null,"work_id":"3d773f24-65e9-4189-816a-5016895ed9c8","year":2021},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:48.616894Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:16188c6b101e0ffa7843e1c14cdc7fbf769d4854249dffab1d4f113cddbf40ff","observation_id":"13f54f78-42ca-4c39-94dd-b0119fd6ea8f","resolution":{"observed_at":"2026-08-06T22:36:59.841152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:48.705844Z","title":"Model-contrastive federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:48.705844Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:dc941a89d27ca2ad7019f4e0390d7ffe014739e598d5453b275988a1d989ed7d","observation_id":"6e702f05-f2be-46b6-9be4-a424d04ec4d8","resolution":{"observed_at":"2026-08-06T22:36:48.705844Z","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":"2026-08-06T22:36:59.640126Z","title":"Pfedprompt: Learning personalized prompt for vision-language models in federated learning,","venue":null,"work_id":"5b0a8c89-4795-47bf-9c84-e9763c6a324c","year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:48.798391Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:dde724921ec8fa38c9409e35cb393ef1ba9eae4b210bbe90250477d15beff1a0","observation_id":"839550eb-99dd-458a-ab99-f326f7e4be88","resolution":{"observed_at":"2026-08-06T22:36:59.717416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03103","last_updated":"2024-08-29T17:24:20Z","snapshot_observed_at":"2026-08-04T06:54:35.698693Z","submitted_at":"2023-10-04T18:47:34Z","title":"Learning to Prompt Your Domain for Vision-Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03103","snapshot_observed_at":"2026-08-06T22:36:48.888398Z","title":"Dual prompt tuning for domain-aware federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:48.888398Z"},"links":{"cited_paper":"/paper/2310.03103","citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:e0aab9a680c4fbfc93c3fad76aeb89cbf8ce30424532fbca439d844e7a360e7e","observation_id":"5bf8675a-b974-47d3-9de3-4399f4e4940b","resolution":{"observed_at":"2026-08-06T22:36:48.888398Z","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":"2026-08-06T22:36:59.493237Z","title":"Diprompt: Disentangled prompt tuning for multiple latent domain generalization in federated learning,","venue":null,"work_id":"09a727c3-31cd-4afb-a657-948053515051","year":2024},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:48.982282Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:b11e37e88a7f423936d1182779db1538a03abe46851d9c19c00121554daa9f3e","observation_id":"562ce677-b4b8-45b5-ac6f-185d66b0e09e","resolution":{"observed_at":"2026-08-06T22:36:59.564766Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:59.309376Z","title":"Learning to prompt for vision- language models,","venue":null,"work_id":"f2b5f92c-7507-4a78-8733-7c6247874dcf","year":2022},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:49.041524Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:e4917cc9def1e42534a1d2172fdfb1959be000a41714e3033859c1fa1b0b0b3f","observation_id":"5d7d7352-7c31-469a-8d85-77065e55ff33","resolution":{"observed_at":"2026-08-06T22:36:59.397026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:59.134365Z","title":"Visual prompt tuning,","venue":null,"work_id":"5663f79e-a9e1-4649-a7bb-504eb7f8f09e","year":2022},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:49.112570Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:1f9cde29378eec0bbadbeb202b7dee4059be0ef51d67ef1a671de747e56a45e6","observation_id":"90298bce-dc96-4faf-b24b-c9a40e773c0c","resolution":{"observed_at":"2026-08-06T22:36:59.217793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:58.958502Z","title":"Dual modality prompt tuning for vision-language pre-trained model,","venue":null,"work_id":"ce65ac69-1aa9-4a09-b5b0-649a80db0bb3","year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:49.188954Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:8afe9e5050d518e84ef26490e08fd15ccaec2ff0b4fcb1a594423666d269b4ca","observation_id":"c9ee57dd-0d0b-4470-9f6a-292f59833389","resolution":{"observed_at":"2026-08-06T22:36:59.042394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11867","last_updated":"2023-06-20T19:58:58Z","snapshot_observed_at":"2026-08-06T13:05:33.985582Z","submitted_at":"2023-06-20T19:58:58Z","title":"Personalized Federated Learning with Feature Alignment and Classifier Collaboration","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.11867","snapshot_observed_at":"2026-08-06T22:36:49.284977Z","title":"Personalized federated learning with feature alignment and classifier collaboration,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:49.284977Z"},"links":{"cited_paper":"/paper/2306.11867","citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:cbccc353bb5a574c355336ff8c8cbc5b97478adf3a2f9f9bd7a82eb7170063a5","observation_id":"6a24e9ce-475d-4e9c-becf-1d8e621d6501","resolution":{"observed_at":"2026-08-06T22:36:49.284977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.00818","last_updated":"2019-12-02T14:29:00Z","snapshot_observed_at":"2026-07-06T08:41:25.156353Z","submitted_at":"2019-12-02T14:29:00Z","title":"Federated Learning with Personalization Layers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.00818","snapshot_observed_at":"2026-08-06T22:36:49.373903Z","title":"Federated learning with personalization layers,","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:49.373903Z"},"links":{"cited_paper":"/paper/1912.00818","citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:c0c1b84bc019967e2ab81f5b2300fd95ed0074060bb5cccb39c8886379e73a81","observation_id":"39d1dc97-9a64-49a3-95c1-f5f77f14abe4","resolution":{"observed_at":"2026-08-06T22:36:49.373903Z","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":"2026-08-06T22:36:58.798049Z","title":"Exploiting shared representations for personalized federated learning,","venue":null,"work_id":"37f173ae-5baf-417f-88b5-716e70e4961a","year":2021},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:49.475660Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:dd5fd3afec2e22cda35716cd68d17e4583951bf21a8bd8250845e3bc28fa44a0","observation_id":"8ccb739d-4c07-4cce-ac59-f5d09057937e","resolution":{"observed_at":"2026-08-06T22:36:58.890834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.06042","last_updated":"2022-03-16T03:50:49Z","snapshot_observed_at":"2026-07-06T11:18:09.557612Z","submitted_at":"2021-06-04T04:34:26Z","title":"FedBABU: Towards Enhanced Representation for Federated Image Classification","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.06042","snapshot_observed_at":"2026-08-06T22:36:49.564532Z","title":"Fedbabu: Towards enhanced representa- tion for federated image classification,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:49.564532Z"},"links":{"cited_paper":"/paper/2106.06042","citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:e63ff7e9beecdf26cca8507caed4357022f78df109fa300d009c66bc6a4a08b3","observation_id":"863ab62c-8759-46b7-bc27-98e22fdb2b0c","resolution":{"observed_at":"2026-08-06T22:36:49.564532Z","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":"2026-08-06T22:36:58.662211Z","title":"Fedtp: Federated learning by transformer personalization,","venue":null,"work_id":"52eca574-347e-4650-b2cf-cae144078415","year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:49.685451Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:a3879f084fbadee16a9e034559752d4ac901f73731e74837f4dabbdf650c905c","observation_id":"d67d5f15-1213-4630-908f-8bbbef3ab42a","resolution":{"observed_at":"2026-08-06T22:36:58.720692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:58.527108Z","title":"Partialfed: Cross-domain per- sonalized federated learning via partial initialization,","venue":null,"work_id":"f1aec018-11bd-4b14-b9f6-b0fa4a73fea8","year":2021},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:49.754212Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:65825b4b3b471a27105b46db2ab1f8c6f2a25630920ef6672068823ee64e3b19","observation_id":"e045e596-7023-4571-a94c-c52b881b348d","resolution":{"observed_at":"2026-08-06T22:36:58.584941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06123","last_updated":"2023-10-09T19:57:24Z","snapshot_observed_at":"2026-07-06T16:30:08.320348Z","submitted_at":"2023-10-09T19:57:24Z","title":"Text-driven Prompt Generation for Vision-Language Models in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06123","snapshot_observed_at":"2026-08-06T22:36:49.837635Z","title":"Text-driven prompt generation for vision-language models in federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:49.837635Z"},"links":{"cited_paper":"/paper/2310.06123","citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:9ed854a0aa36a7fcc4af79fe720385cc887e05a539cde5ab1629a05c68192e67","observation_id":"44644214-b36d-4f22-ab3d-039fb54fce92","resolution":{"observed_at":"2026-08-06T22:36:49.837635Z","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":"2026-08-06T22:36:49.933351Z","title":"Position paper: Assessing robustness, privacy, and fairness in federated learning integrated with foundation models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:49.933351Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:1474da3d001b27f0d5ba833ce9b8c7ef8535bd2935b859573b833e675218d319","observation_id":"39a0cd62-307c-4484-853d-3e17dd9d6563","resolution":{"observed_at":"2026-08-06T22:36:49.933351Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13485","last_updated":"2023-07-09T12:36:50Z","snapshot_observed_at":"2026-07-06T14:56:04.791076Z","submitted_at":"2023-02-27T02:49:06Z","title":"FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13485","snapshot_observed_at":"2026-08-06T22:36:49.990780Z","title":"Fedclip: Fast generalization and personalization for clip in federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:49.990780Z"},"links":{"cited_paper":"/paper/2302.13485","citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:c6a617d4a61fd60a5e9a25587fef7f71f130d4f0e2c787ff6186365f63213d0d","observation_id":"19adbfa3-aa8c-4c65-b062-83461af2b2b1","resolution":{"observed_at":"2026-08-06T22:36:49.990780Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09970","last_updated":"2024-09-22T01:43:01Z","snapshot_observed_at":"2026-07-06T15:43:35.260552Z","submitted_at":"2023-06-16T17:02:12Z","title":"Continual Adaptation of Vision Transformers for Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09970","snapshot_observed_at":"2026-08-06T22:36:50.079956Z","title":"Hepco: Data-free heterogeneous prompt consolidation for continual federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:50.079956Z"},"links":{"cited_paper":"/paper/2306.09970","citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:6e24b7be25eada8d8a41721b4e670484a831f26f509d08f1f46141a21d9869cd","observation_id":"33802378-0efe-46c0-88ef-0cae27c43303","resolution":{"observed_at":"2026-08-06T22:36:50.079956Z","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":"2026-08-06T22:36:58.348402Z","title":"Federated adaptive prompt tuning for multi-domain collaborative learning,","venue":null,"work_id":"bdb3de77-3004-4760-8430-af1ad7ed02e9","year":2024},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:50.166223Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:bb4b246ccf62c1fcffd70aee2129f6978530a046f5044f361b0840184bc08324","observation_id":"e6e638e5-4aef-4250-8343-c1f6b8052f58","resolution":{"observed_at":"2026-08-06T22:36:58.448270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:58.161031Z","title":"Squeeze-and-excitation networks,","venue":null,"work_id":"24eee236-b75c-4850-a5ee-0eac0813ff7c","year":2018},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:50.295662Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:c2d4b93a2270432007b62d3dd138619603bf9b529d7b961bf5bf5500b2fad4b3","observation_id":"c615603a-508a-4765-a507-c887cdff35c3","resolution":{"observed_at":"2026-08-06T22:36:58.260366Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:57.950868Z","title":"Eca-net: Effi- cient channel attention for deep convolutional neural networks,","venue":null,"work_id":"61fbebef-81b7-4f0c-a97d-6e82fb283e25","year":2020},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:50.363486Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:abe8580c2baa16165081399382b9165b9906a57dd62f012d1d701f9a5913b007","observation_id":"a71afd33-8db1-4a99-90c4-5bdc5cbe0dec","resolution":{"observed_at":"2026-08-06T22:36:58.049188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:57.742510Z","title":"Stand-alone self-attention in vision models,","venue":null,"work_id":"ae010c0d-44cb-4170-87fe-faaf6d2fbda2","year":2019},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:50.449832Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:794cfbcd324c6c62a35b595f1bae043d25969f00d71876a8db8ad415cf91f927","observation_id":"08fcc2f6-e2c9-4ac7-810c-0f4aec93f46e","resolution":{"observed_at":"2026-08-06T22:36:57.839943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:57.533288Z","title":"Exploring self-attention for image recognition,","venue":null,"work_id":"78db01f5-d47d-46e0-b9d0-53991a4357d9","year":2020},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:50.590036Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:5209e96604b0a8355d9392a17dcfee3b5e9e88d556e8498f509f743fcbca164f","observation_id":"06d43359-76ea-45a8-84af-e7b2dc2b0641","resolution":{"observed_at":"2026-08-06T22:36:57.630434Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:57.287404Z","title":"Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories,","venue":null,"work_id":"f16ed1df-f381-4d70-95db-353b0e596e61","year":2004},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:50.701299Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:7f8c962dd43797e74ee54908f4b5a5561c30f4d23b6d1ad1cecf81a4468aebc5","observation_id":"9e167584-e0c8-4e4c-82a5-8c85c58fdd36","resolution":{"observed_at":"2026-08-06T22:36:57.420439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:57.076287Z","title":"Automated flower classification over a large number of classes,","venue":null,"work_id":"a8596f80-05a6-4573-90ba-3aac51193f53","year":2008},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:50.787608Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:b280abf955401545036e070c18b4d316efc9717fe506e0bff39800f5b3e9465e","observation_id":"67dbbbdb-6dc1-4936-8d4d-cdb08ed82aab","resolution":{"observed_at":"2026-08-06T22:36:57.175947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:56.875082Z","title":"Cats and dogs,","venue":null,"work_id":"f7d767d7-b8ec-4862-92df-a7439d6f8750","year":2012},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:50.910003Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:aff04b78bfd53443fe3d51f105aa7f4a8c43c31f1fa609303fc5558bbbb7a22b","observation_id":"b7a23ce0-30df-41fd-b05a-cb2bf9401792","resolution":{"observed_at":"2026-08-06T22:36:56.965389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:56.714076Z","title":"Eurosat: A novel dataset and deep learning benchmark for land use and land cover classifica- tion,","venue":null,"work_id":"80f1124c-82ce-482b-bf36-c0c3fe908c4d","year":2019},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:51.015093Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:9393b268e938b7ed401ea85c8c868876337747b9454c88a23921f490e6c27f72","observation_id":"5baebbbd-e32f-442f-925f-7ad5c3a86aa6","resolution":{"observed_at":"2026-08-06T22:36:56.785490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.0402","last_updated":"2012-12-03T14:45:31Z","snapshot_observed_at":"2026-07-06T03:01:10.229407Z","submitted_at":"2012-12-03T14:45:31Z","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.0402","snapshot_observed_at":"2026-08-06T22:36:51.121364Z","title":"Ucf101: A dataset of 101 human actions classes from videos in the wild,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:51.121364Z"},"links":{"cited_paper":"/paper/1212.0402","citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:629237e00f6a5276a02bc2579c30e32d9dacb7ee2c5b86f277eac336bdd7d0f5","observation_id":"d3b869b4-7bf2-435f-93a9-0e04c64ca3bc","resolution":{"observed_at":"2026-08-06T22:36:51.121364Z","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":"2026-08-06T22:36:56.506326Z","title":"Describ- ing textures in the wild,","venue":null,"work_id":"213b24b8-d53e-4ac0-99bd-423b9688a87f","year":2014},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:51.224470Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:7e470fea2f6ba07ba6a374a17f6154e87e5055cda3836c48d69bcff19a44957d","observation_id":"a05d0261-da67-4a6a-9808-cad0a2844e6b","resolution":{"observed_at":"2026-08-06T22:36:56.571934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:51.330052Z","title":"The caltech-ucsd birds-200-2011 dataset,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:51.330052Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:85ece0c0f9764cc64421b5b1a8ccc818f42548c940cd016de74a562035f9fbbb","observation_id":"ac178ae0-f285-4e6c-8243-a1033a502c6f","resolution":{"observed_at":"2026-08-06T22:36:51.330052Z","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":"2026-08-06T22:36:56.308872Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":"15b9d8b6-c61a-4539-9782-8f927a8e6050","year":2009},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:51.468487Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:00f03b70fc30e3db7d9c8b0c1aeaddd73ca1d8a091eacd94e000c878f1d4c7c9","observation_id":"59ba0b1d-7a4e-4bf7-a24f-a6e0449b4208","resolution":{"observed_at":"2026-08-06T22:36:56.383552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:56.060700Z","title":"Moment matching for multi-source domain adaptation,","venue":null,"work_id":"e06d6bd4-bdb0-4142-b0e4-080df918f177","year":2019},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:51.574602Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:6a332622b3c3a6a692c4ca612d7bd63e3206bc12ca924802d29e9c8c6890ae79","observation_id":"77352613-c480-4dac-9c43-f4837b708928","resolution":{"observed_at":"2026-08-06T22:36:56.194860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:55.772257Z","title":"Geodesic flow kernel for unsupervised domain adaptation,","venue":null,"work_id":"bfb79afe-9c41-4bb4-96b7-5f1176088028","year":2012},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:51.678104Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:2a06163f10006814a735baacecbe63ec2652f65c316944296f7f17344a2926f6","observation_id":"6dcedbb0-b843-4b2c-b84b-19710cd80428","resolution":{"observed_at":"2026-08-06T22:36:55.914990Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:55.555434Z","title":"Non-local neural networks,","venue":null,"work_id":"40d48043-1b20-4923-b07a-8a61402c5051","year":2018},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:51.781577Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:a95be52aac86f7797afd32a3c8dbb66a329edc024865fba90a98fb11c06e7224","observation_id":"01fe0ffb-d34b-4761-80f5-b00a530b1592","resolution":{"observed_at":"2026-08-06T22:36:55.658355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:55.346442Z","title":"No fear of heterogeneity: Classifier calibration for federated learning with non-iid data,","venue":null,"work_id":"a9554bb8-482d-4556-b82e-c5c288a242a8","year":2021},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:51.886393Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:45770b89ee7f0b99eeff16849b0fecf7dbeb27d81e4cd810187586f37e278420","observation_id":"5caef11e-abee-4f8e-9e6d-d44db62fd426","resolution":{"observed_at":"2026-08-06T22:36:55.445019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:55.135867Z","title":"Towards under- standing and mitigating dimensional collapse in heterogeneous federated learning,","venue":null,"work_id":"e1d29aec-cafc-40a6-90d4-b56e65d76882","year":2022},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:51.999096Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:0acffa7be9042f9a66249b1dc2e38f4e56378eb537abe1be0100d87c9fa26d86","observation_id":"de23e058-6ed9-4c61-ac4b-6b9807d68d76","resolution":{"observed_at":"2026-08-06T22:36:55.232602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:54.932845Z","title":"Ditto: Fair and robust federated learning through personalization,","venue":null,"work_id":"0048e5b8-207c-4899-ba59-67e0f1acef08","year":2021},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:52.076624Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:3eed6e76e5be91806994b401e989129c91c11f8bf7cb17c2b1c2a3ea05108572","observation_id":"a61f5e47-6848-46b5-982e-4d1ecbb2e3a6","resolution":{"observed_at":"2026-08-06T22:36:55.034430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:54.832283Z","title":"Personalized federated learning with moreau envelopes,","venue":null,"work_id":"6b68f92a-f158-400f-8268-d8d835981e59","year":2020},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:52.166508Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:a73d3cf6802da85f61ebba9818e398fb8395b5790e0b616ee6348f10a97e3746","observation_id":"0f7eb68f-4299-4d00-8464-127d7114b0e1","resolution":{"observed_at":"2026-08-06T22:36:54.872878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:54.672027Z","title":"Fedcp: Separating feature information for personalized federated learn- ing via conditional policy,","venue":null,"work_id":"54b4c28a-18a2-4833-bda9-e26731648748","year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:52.270028Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:167393e03a100c5ac41919cb475c094408efa0aac7770effeaef5885f061dbf2","observation_id":"61523c34-63c6-4e03-9648-e620c47b1c63","resolution":{"observed_at":"2026-08-06T22:36:54.768932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:54.466028Z","title":"Learning federated visual prompt in null space for mri reconstruction,","venue":null,"work_id":"b79e8390-f23f-4d18-af99-7823be2a8e10","year":2023},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:52.410786Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:e22df335f761cc58d132f410f6b9d44ea47fb606eb5e548aff9cf7d5ae4242ec","observation_id":"1ec6e692-92c1-495e-bfbc-ef692ad0170e","resolution":{"observed_at":"2026-08-06T22:36:54.568141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:54.151432Z","title":"Residual attention network for image classification,","venue":null,"work_id":"b92f40b5-9be3-4e50-96b2-fad5112ee184","year":2017},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:52.564739Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:3fde45af2ef2f17a180fc5222009f798cb1291e4a0f4ef4c817c3f23d636a524","observation_id":"9de74e28-5a41-4067-a7d5-1677816d06ea","resolution":{"observed_at":"2026-08-06T22:36:54.291905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:53.912275Z","title":"Cbam: Convolutional block attention module,","venue":null,"work_id":"b35a3163-aacd-47c1-a265-5e9d9d46bfb4","year":2018},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:52.673433Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:e3dddbf58f3815ce9edae0874db6c7f5fbb2b8ce56874308d46499a8bd389455","observation_id":"13b454a8-3f59-4256-8fe4-55afd52b81eb","resolution":{"observed_at":"2026-08-06T22:36:54.029113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.01703","last_updated":"2019-12-03T22:06:05Z","snapshot_observed_at":"2026-07-06T08:41:49.632205Z","submitted_at":"2019-12-03T22:06:05Z","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.01703","snapshot_observed_at":"2026-08-06T22:36:52.750899Z","title":"Pytorch: An imperative style, high-performance deep learning library,","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:52.750899Z"},"links":{"cited_paper":"/paper/1912.01703","citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:4cd5d4154c8377a694be33e55774cf6bce33adc3c2f9953d211d520d3c20606f","observation_id":"f1aed8ec-1ddf-4c11-8f0f-bae4307536ff","resolution":{"observed_at":"2026-08-06T22:36:52.750899Z","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":"2026-08-06T22:36:53.799262Z","title":"Mixture of experts made personalized: Federated prompt learning for vision-language models,","venue":null,"work_id":"d87faeac-34de-4636-933c-39acc2732c9c","year":2025},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:52.846961Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:81b2af3255fc31364966fa628b6d5029ddd7dcc6a289bcf7a8b40c37808184c2","observation_id":"4391e099-3d84-4af0-8130-f0376f1b4609","resolution":{"observed_at":"2026-08-06T22:36:53.839861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:53.620945Z","title":"Dynamic heterogeneous federated learning with multi-level prototypes,","venue":null,"work_id":"92b3c4d1-4b0a-4993-9d4b-3fc23b1f9229","year":2024},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:52.959694Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:11679ff99b90fb7d4b29eb457b7d3504667e30c3012d12453e4b355efbe50fb6","observation_id":"2b607bb0-728a-48fa-9325-9f5ee490cdda","resolution":{"observed_at":"2026-08-06T22:36:53.716319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:36:53.486835Z","title":"Addressing skewed heterogeneity via federated prototype rectification with personalization,","venue":null,"work_id":"b5484b13-2eee-496a-94cf-37d5328d82d0","year":2021},"citing_paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:53.073061Z"},"links":{"citing_paper":"/paper/2506.21144"},"observation_digest":"sha256:a09a53e4b4f0355b6652e8c92b2f258ff825290fa256ab32c59e12da5cab2f70","observation_id":"b38a6d0f-2f51-4b44-8cf0-de1b295ee37e","resolution":{"observed_at":"2026-08-06T22:36:53.530766Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.21144","last_updated":"2025-06-26T10:59:14Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T22:30:12.940161Z","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion"},"reference_resolution":{"displayed":59,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":0,"verified_fuzzy":44},"total_outbound_references":59},"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 7 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 1 inbound Pith citation observation for arXiv:2506.21144."}