{"as_of":"2026-08-21T09:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:eff03c7874777b391a41170ff5d7605065a7cc702083466d8b2af8f64ab95b2a","coverage":[{"denominator":64,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":64,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T05:29:23.377390Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2504.21063/citation-record","integrity":"/paper/2504.21063/integrity","json":"/paper/2504.21063/citation-record.json","paper":"/paper/2504.21063"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:29:23.968599Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":"83edd521-dd18-4457-90d2-1ee7bf13450f","year":2017},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.134626Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:f3afe471cdbbe34591b76627f549d2a819a79ce6cc4da042563b90afb0bda188","observation_id":"c8bb6ddf-4006-4b7a-a5f4-d40a06c45406","resolution":{"observed_at":"2026-08-16T05:29:23.972865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.139194Z","title":"A survey on federated learning systems: Vision, hype and reality for data privacy and protection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.139194Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:5d8a3d3082666271ffb1c3b842abb2d5b56fbf8eac48d33de1ca7a63f42d2c0b","observation_id":"7067491a-c1f8-4731-8632-749d46fc22fc","resolution":{"observed_at":"2026-08-16T05:29:23.139194Z","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":"2026-08-16T05:29:23.143093Z","title":"Mixstyle neural networks for domain generalization and adaptation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.143093Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:0b78ef718708e9a25ff4991edca2d959291514ba086c0e4fb6944d485a9aad7f","observation_id":"10ed435e-40dd-4466-8b42-bba745732a6c","resolution":{"observed_at":"2026-08-16T05:29:23.143093Z","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":"2026-08-16T05:29:23.147212Z","title":"Madg: Margin-based adversarial learning for domain generalization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.147212Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:9a8beef93d34ca9390a312f7e89d65e35b5f32b323428465c3d109ecba5df6bc","observation_id":"1d9513b4-2e99-466b-bd86-8623a7cbfd7e","resolution":{"observed_at":"2026-08-16T05:29:23.147212Z","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":"2026-08-16T05:29:23.150956Z","title":"Feddg: Federated do- main generalization on medical image segmentation via episodic learn- ing in continuous frequency space,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.150956Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:2a16e111f5d1ff810cc8e00452bd5789273b4dbd8dd46c6c127df06901bf7636","observation_id":"1e7ca9e7-6ffc-47da-99d6-d080d5bab419","resolution":{"observed_at":"2026-08-16T05:29:23.150956Z","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":"2026-08-16T05:29:23.154777Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.154777Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:6e987311611da06f405225d49c87e0045f00a3b29890c9f6b74050643533d50a","observation_id":"80d5a0e1-0ed5-41f7-9b27-04f8a91fa402","resolution":{"observed_at":"2026-08-16T05:29:23.154777Z","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":"2026-08-16T05:29:23.158858Z","title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.158858Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:b6595804ec3aef0ded66a53970fce0c9e2ab623bed79af2ddd52635aaa458ab7","observation_id":"b0a3ebe6-bf21-4b43-b6f6-1d8181950349","resolution":{"observed_at":"2026-08-16T05:29:23.158858Z","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":"2026-08-16T05:29:23.162835Z","title":"Learning to prompt for vision- language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.162835Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:21b5609e27e2f5fcac8529a8af7d4d7c10fb316ae98503797adfa7a6d6fdf7f4","observation_id":"38863e4d-7a64-46a0-90d5-d7fe2739caf7","resolution":{"observed_at":"2026-08-16T05:29:23.162835Z","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":"2026-08-16T05:29:23.166273Z","title":"Maple: Multi-modal prompt learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.166273Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:5294ce44ff82f591514cf21321d1bcf86d69fadcd024d5a5f4f90afd357b6a49","observation_id":"ba9d328c-3610-4947-b587-5291dcff079b","resolution":{"observed_at":"2026-08-16T05:29:23.166273Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08506","last_updated":"2024-03-11T15:58:15Z","snapshot_observed_at":"2026-08-16T14:10:55.716884Z","submitted_at":"2024-03-11T15:58:15Z","title":"DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08506","snapshot_observed_at":"2026-08-16T05:29:23.170041Z","title":"Diprompt: Disentangled prompt tuning for multiple latent domain generalization in federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.170041Z"},"links":{"cited_paper":"/paper/2403.08506","citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:cd671981d617e476400a64517384ad025d956e507c03ba40e3ae5eec893bb9e9","observation_id":"9d5c85a5-cdc0-45d9-9b7b-634803cd613d","resolution":{"observed_at":"2026-08-16T05:29:23.170041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.10063","last_updated":"2024-11-15T09:26:00Z","snapshot_observed_at":"2026-08-16T12:15:13.130470Z","submitted_at":"2024-11-15T09:26:00Z","title":"Federated Domain Generalization via Prompt Learning and Aggregation","version":1},"cited_work":{"arxiv_id":"2411.10063","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.10063","snapshot_observed_at":"2026-08-16T05:29:23.483021Z","title":"Federated Domain Generalization via Prompt Learning and Aggregation","venue":"cs.AI","work_id":"dc7cfe64-410f-4ea5-a9f7-6b255a8f5997","year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.174070Z"},"links":{"cited_paper":"/paper/2411.10063","citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:3acc8fe760f438ebfe8d4ba59dacfadf2c85d1c98da54934b4d1b44c767826a4","observation_id":"f0d27e01-640e-45b3-8049-d025c705a613","resolution":{"observed_at":"2026-08-16T05:29:23.489508Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.178337Z","title":"Promptfl: Let federated participants cooperatively learn prompts instead of models-federated learning in age of foundation model,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.178337Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:011e7059500894df8bc2ffa505202c8b5b0b443489b0ee59235e932abd34925c","observation_id":"052f2c34-e399-4d2f-842b-b96b3af6e6fd","resolution":{"observed_at":"2026-08-16T05:29:23.178337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10114","last_updated":"2025-04-01T15:53:12Z","snapshot_observed_at":"2026-08-16T13:09:47.283002Z","submitted_at":"2024-10-14T03:05:12Z","title":"Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10114","snapshot_observed_at":"2026-08-16T05:29:23.181738Z","title":"Mixture of experts made personalized: Federated prompt learning for vision-language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.181738Z"},"links":{"cited_paper":"/paper/2410.10114","citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:19ef69ccb7264b738c8f1629f7785af6b2a0f12cca20e61e4fd4e634358ada63","observation_id":"b5cbaf2f-0b8f-406f-baa9-c2508c2dd471","resolution":{"observed_at":"2026-08-16T05:29:23.181738Z","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":"2026-08-16T05:29:23.185836Z","title":"Towards instance-adaptive inference for federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.185836Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:901c7a420863d34ce22cd070c660219218a1b2f5626d53d32130c247f2abedea","observation_id":"70b62e5e-1d8e-4342-9e5b-64b8ce1c9fa1","resolution":{"observed_at":"2026-08-16T05:29:23.185836Z","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":"2026-08-16T05:29:23.189635Z","title":"Adaptive mixtures of local experts,","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.189635Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:30917a7852bb1dfeffd0345c0a03fb4f50965d4338449e15443533b5f1e1e29c","observation_id":"c8d4bf75-cad5-43a8-b22a-7b98cb482563","resolution":{"observed_at":"2026-08-16T05:29:23.189635Z","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":"2026-08-16T05:29:23.882785Z","title":"Deepseekmoe: Towards ultimate expert special- ization in mixture-of-experts language models,","venue":null,"work_id":"902faae0-9b72-481c-9033-5bc02a984502","year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.193183Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:d1e151b602dd6400bfb275bb80f66f4acbcee7bd530ca44b408a6c196ed6c96a","observation_id":"7bed6595-d518-4b3b-beb8-4cd9a6395f35","resolution":{"observed_at":"2026-08-16T05:29:23.886874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.871580Z","title":"Mixture-of-prompt-experts for multi-modal semantic understanding,","venue":null,"work_id":"4cabfc88-2f0e-4210-9b12-d6f3bbf5481a","year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.197088Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:e33acbc455afcd756114eca8d5202c72d36070f3be2e42d57071aa475acf0285","observation_id":"3d373832-2acd-4285-bfd4-af6df01d508c","resolution":{"observed_at":"2026-08-16T05:29:23.875596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.860996Z","title":"M ´emoire sur la th ´eorie des d ´eblais et des remblais,","venue":null,"work_id":"737f3291-7865-4f4c-9006-09b451e38af9","year":null},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.200715Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:a518295f89ff1d8eee9ccf027beba0fbf8cd93984ea7e361ea614d90c2acbf30","observation_id":"2d8eeb22-7fe5-4072-8105-d1c5a25b2ed1","resolution":{"observed_at":"2026-08-16T05:29:23.864752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.204588Z","title":"Self-regulating prompts: Foundational model adaptation without forgetting,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.204588Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:cb7633b143073097357fb75d8cd4c72dfaff6688897aad7b643e588a712a7216","observation_id":"57cb0e2e-1145-48f1-92f1-73b80ce3c2a5","resolution":{"observed_at":"2026-08-16T05:29:23.204588Z","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":"2026-08-16T05:29:23.208505Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.208505Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:6b2abe85592a9e83ee209d0c9ff573ed5f1560daecb57aa302907b5857623c72","observation_id":"58341889-bb49-48ef-ba3b-4f45f6258491","resolution":{"observed_at":"2026-08-16T05:29:23.208505Z","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":"2026-08-16T05:29:23.836100Z","title":"Fedfame: A data augmentation free framework based on model contrastive learning for federated semi-supervised learning,","venue":null,"work_id":"93142bb1-a9fd-4adc-bf42-44b2dbfb4b00","year":2023},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.212233Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:b289db9b8b12980d46bef6698362b0658651490b97bd86c1a917cc18fd53be26","observation_id":"cbca5f6b-b697-4c24-af90-bb179400dbcc","resolution":{"observed_at":"2026-08-16T05:29:23.840110Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.216102Z","title":"Scaffold: Stochastic controlled averaging for federated learn- ing,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.216102Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:bf825ff2b548364249a50bb2a07f11c589c4ac73f8cd5d6861a28c3aecbcf8e6","observation_id":"b72a191b-0226-448c-ba1d-914411378493","resolution":{"observed_at":"2026-08-16T05:29:23.216102Z","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":"2026-08-16T05:29:23.817545Z","title":"Federated learning with matched averaging,","venue":null,"work_id":"8702e820-0ab5-4744-abfb-ecc00b908549","year":2020},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.219851Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:8da1340314523ad92e30df120676ec09e59815db580f05d94c9c8be20361a228","observation_id":"96e24867-cc38-4482-a5a5-bf84ee0a095e","resolution":{"observed_at":"2026-08-16T05:29:23.821539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.224285Z","title":"Tackling the objective inconsistency problem in heterogeneous federated optimiza- tion,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.224285Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:001548010947051f7a21fcf41497ffef65e66af8a1033af4b535f8e7ddd927fb","observation_id":"6cdd74a6-4a92-4c3b-9e0a-9bf9aaaa5579","resolution":{"observed_at":"2026-08-16T05:29:23.224285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.07623","last_updated":"2021-05-11T14:21:00Z","snapshot_observed_at":"2026-08-16T18:45:28.385746Z","submitted_at":"2021-02-15T16:04:10Z","title":"FedBN: Federated Learning on Non-IID Features via Local Batch Normalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.07623","snapshot_observed_at":"2026-08-16T05:29:23.228099Z","title":"Fedbn: Feder- ated learning on non-iid features via local batch normalization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.228099Z"},"links":{"cited_paper":"/paper/2102.07623","citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:1ee460d35e52c05000ae025c59952354f38366ac21261898061248f6e7368eb0","observation_id":"a5ce0814-cb86-4b47-be2d-361f747fce02","resolution":{"observed_at":"2026-08-16T05:29:23.228099Z","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":"2026-08-16T05:29:23.232207Z","title":"Fair federated learning under domain skew with local consistency and domain diversity,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.232207Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:4fe72396e0e8e0b1e0256e64b955381b08c7e99525951702ab4933295b10e8ee","observation_id":"fcc83223-38ae-4e52-bd05-eabec35af69c","resolution":{"observed_at":"2026-08-16T05:29:23.232207Z","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":"2026-08-16T05:29:23.235804Z","title":"Domain generalization with adversarial feature learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.235804Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:183628fc63720bf17604ab4076fc22fb35057e185c5674fe376b207e30b883dc","observation_id":"baa8348c-5a3e-49f6-ab85-464a1900b59a","resolution":{"observed_at":"2026-08-16T05:29:23.235804Z","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":"2026-08-16T05:29:23.239538Z","title":"Unified deep supervised domain adaptation and generalization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.239538Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:7041a09d9f713119c5b0d034a58a8c6ddd131a68c732dd447554023932eea77a","observation_id":"70d14b56-2c58-48b2-90b9-7fb921a216f9","resolution":{"observed_at":"2026-08-16T05:29:23.239538Z","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":"2026-08-16T05:29:23.243025Z","title":"Domain generalization with mixstyle,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.243025Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:c8f3c7da9656c0319b9fe0522218e7a51dacfd8d16257862d0aa0c5d8ee61f3e","observation_id":"17d68d69-8970-45b9-b3d9-4acbc43e8fc6","resolution":{"observed_at":"2026-08-16T05:29:23.243025Z","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":"2026-08-16T05:29:23.247122Z","title":"Learning to optimize domain specific normalization for domain generalization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.247122Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:24571ceb5db0f0bf2397fe59780d0f1ab05007683357cbe54e481d817f5091bb","observation_id":"696907ae-cc32-49a2-a5e6-4d471c0c84d0","resolution":{"observed_at":"2026-08-16T05:29:23.247122Z","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":"2026-08-16T05:29:23.250663Z","title":"Learning to generalize: Meta-learning for domain generalization,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.250663Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:453d459e9c87a5979ffe6d24e5a4f151233e4b13d0dd6054962c333af9d05673","observation_id":"e4e1e409-97ce-48e4-a870-379ed65607dd","resolution":{"observed_at":"2026-08-16T05:29:23.250663Z","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":"2026-08-16T05:29:23.254529Z","title":"Do- main generalization via model-agnostic learning of semantic features,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.254529Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:5d8b6a8c0459f7079f2d4cb2fd5e1a01f46fa1713c07b7dc135d8e0dfebeaf3c","observation_id":"71c0f7d6-f9cd-4ecd-bdd6-a532c0c45697","resolution":{"observed_at":"2026-08-16T05:29:23.254529Z","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":"2026-08-16T05:29:23.258239Z","title":"Federated domain generaliza- tion for image recognition via cross-client style transfer,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.258239Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:8c7a90e03e8c44f0b661f920211fa20772eceff6ad5e69fa13331e495a492f4f","observation_id":"c5ddcf60-43de-4597-826a-c1ed288652bf","resolution":{"observed_at":"2026-08-16T05:29:23.258239Z","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":"2026-08-16T05:29:23.744390Z","title":"Stablefdg: style and attention based learning for federated domain generalization,","venue":null,"work_id":"e4945b5f-9435-4694-9d81-98ad6e4945d9","year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.261851Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:7468ac149865679bff16a1df8b9caa3bd538235f088b6c83ac1261875be1f615","observation_id":"e53161d8-4c22-48a9-854f-7fc62080636e","resolution":{"observed_at":"2026-08-16T05:29:23.748019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.733312Z","title":"Rethinking federated learning with domain shift: A prototype view,","venue":null,"work_id":"23409ef1-4ea4-4042-88cf-a653145ff831","year":2023},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.265299Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:b5cb6c3dababf0c444e9c011081f96fe468a5b0ebd285fd25e95f71062ee37a7","observation_id":"e44af33d-bd33-42cd-b6d3-ce93a5a133fd","resolution":{"observed_at":"2026-08-16T05:29:23.737397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.269347Z","title":"Federated domain generalization with generalization adjustment,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.269347Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:3fa2a671eb41e01c204bbf5c49b62f960fb4271a8b4efd79088452fe2a0f9b69","observation_id":"66e24f3e-a624-48c9-b3e9-2ff631499832","resolution":{"observed_at":"2026-08-16T05:29:23.269347Z","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":"2026-08-16T05:29:23.272742Z","title":"Conditional prompt learning for vision-language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.272742Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:f01bab6248b449e6e8ec787a0a76b6b28a59c10fd433aa2acf5e7c3dd59c673c","observation_id":"91b2cf5e-c299-44b8-87f9-64550c174541","resolution":{"observed_at":"2026-08-16T05:29:23.272742Z","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":"2026-08-16T05:29:23.708281Z","title":"Plot: Prompt learning with optimal transport for vision-language models,","venue":null,"work_id":"5b30f244-a276-4eab-a499-49a0e2422c6a","year":null},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.276102Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:6690f42ecc945f2a6e3f3d611c7fd19b39b36b162352e84dd9e72558e53df4d6","observation_id":"e93af431-6f30-4191-8f5e-840b390b6264","resolution":{"observed_at":"2026-08-16T05:29:23.711972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.695982Z","title":"Tuning multi-mode token-level prompt alignment across modalities,","venue":null,"work_id":"9b3f597d-fc3e-44a5-a133-8a96a975758e","year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.279947Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:f465114f4376ca4e6fac2ca2fd53e2c9ef4811240688b7c39950dabcbe4e7de4","observation_id":"d2564603-2087-488f-a421-e5b46e97acb9","resolution":{"observed_at":"2026-08-16T05:29:23.700918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.283636Z","title":"Global and local prompts coop- eration via optimal transport for federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.283636Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:2aa56850043e3f35109bfc37547851cdd472987e3cb4ba5f63daf2481f105ee1","observation_id":"0ca1f131-1973-4e2a-8a8b-95c5dab5ad6e","resolution":{"observed_at":"2026-08-16T05:29:23.283636Z","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":"2026-08-16T05:29:23.287594Z","title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.287594Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:6edc3080597a56f30efd48fbbbb2d52017a8e3d2b45819c9a7cb40fd5067eb23","observation_id":"56ad461b-b02b-453c-a3ed-c86608a5615f","resolution":{"observed_at":"2026-08-16T05:29:23.287594Z","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":"2026-08-16T05:29:23.670647Z","title":"Mixture of lora experts,","venue":null,"work_id":"660bce92-1a37-4ee9-893c-97d3ff1f9824","year":null},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.291469Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:3c488ae6618ef99fd1bf5759035aae39fbc497c50021905c1fcec5592648b996","observation_id":"2631e3d6-7961-46c9-85f3-76ab68c58776","resolution":{"observed_at":"2026-08-16T05:29:23.674484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.658531Z","title":"Nonlinear models using dirichlet process mixtures","venue":null,"work_id":"494f6902-ffab-46b9-bdfe-0a68fb3b82f6","year":2009},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.295279Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:45843952909868944fc82fbd32b5e354820f88b24fab155c8698e52be88d854e","observation_id":"95a16564-5cfb-4503-88fc-84682d31b577","resolution":{"observed_at":"2026-08-16T05:29:23.662985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1701.06538","last_updated":"2017-01-23T18:10:00Z","snapshot_observed_at":"2026-08-19T12:32:00.517027Z","submitted_at":"2017-01-23T18:10:00Z","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.06538","snapshot_observed_at":"2026-08-16T05:29:23.299306Z","title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.299306Z"},"links":{"cited_paper":"/paper/1701.06538","citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:cbdc67a27f0d9702e649033bf97e4de8883ba4a6b693d4b5736afed0f81d8e7c","observation_id":"797ab968-3a85-4187-bb85-51a22436b57f","resolution":{"observed_at":"2026-08-16T05:29:23.299306Z","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":"2026-08-16T05:29:23.646031Z","title":"Fedjets: Efficient just-in-time personalization with federated mixture of experts,","venue":null,"work_id":"975a4cb6-b4e2-4903-a18d-abc857aa1692","year":2023},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.303714Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:aacf8814a4a880ee6b607e15efe8fac5f2346b34d94f78c0fc93ee8425b514d6","observation_id":"42ae2bae-0c51-4ae9-aa57-19c15009df61","resolution":{"observed_at":"2026-08-16T05:29:23.650444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.06724","last_updated":"2021-07-14T14:15:24Z","snapshot_observed_at":"2026-08-16T21:38:51.918793Z","submitted_at":"2021-07-14T14:15:24Z","title":"Federated Mixture of Experts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.06724","snapshot_observed_at":"2026-08-16T05:29:23.307399Z","title":"Federated mixture of experts,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.307399Z"},"links":{"cited_paper":"/paper/2107.06724","citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:86d2e6590fa0b1523c2e139f8f73d5a2c557b4153a722e59e32725431a7c1ec8","observation_id":"a5ac8f59-7d61-49f5-bea0-8794079da3a4","resolution":{"observed_at":"2026-08-16T05:29:23.307399Z","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":"2026-08-16T05:29:23.312502Z","title":"Language models are unsupervised multitask learners,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.312502Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:21d6ee27a7fd22a86036063c3c67a8bcbf752f3eb9f4a351ed41e445846bdf4a","observation_id":"eada9bf5-1a11-4ee5-b498-fd377810f40f","resolution":{"observed_at":"2026-08-16T05:29:23.312502Z","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":"2026-08-16T05:29:23.317057Z","title":"The hungarian method for the assignment problem,","venue":null,"work_id":null,"year":1955},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.317057Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:94060f4f83c99ed09f367a6a79e59a65ddeacedd3f565379deb931aa962b12f6","observation_id":"77a26196-fb68-4d42-a0db-3934b9404085","resolution":{"observed_at":"2026-08-16T05:29:23.317057Z","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":"2026-08-16T05:29:23.321103Z","title":"Deeper, broader and artier domain generalization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.321103Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:8b9dd41f14f9aeaf51327232613e85cb08d0663d19b406b82c31b82a3e88f6fb","observation_id":"c3cd9b5f-065a-465d-a7e5-e93b3b821498","resolution":{"observed_at":"2026-08-16T05:29:23.321103Z","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":"2026-08-16T05:29:23.324541Z","title":"Deep hashing network for unsupervised domain adaptation,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.324541Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:af94cb55f48d379ef9b9c4efcc70058a0a33821637a117d1330ce4cef3004790","observation_id":"b6b7dafd-fe56-4611-b937-7a296f6936bf","resolution":{"observed_at":"2026-08-16T05:29:23.324541Z","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":"2026-08-16T05:29:23.328214Z","title":"Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.328214Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:a02433549605f95784d4858b36be6279e048e7e04b997bfa08a63199aae1b032","observation_id":"4674f48f-7cef-431f-92b3-02f91c13c2e2","resolution":{"observed_at":"2026-08-16T05:29:23.328214Z","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":"2026-08-16T05:29:23.332278Z","title":"Moment matching for multi-source domain adaptation,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.332278Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:866dcec31ec63b58a8f1fc6349145b5aba5b94ff8cc658b468dba5b17c271001","observation_id":"208919a3-be3d-407a-aa28-4eec3c513c46","resolution":{"observed_at":"2026-08-16T05:29:23.332278Z","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":"2026-08-16T05:29:23.336111Z","title":"Self-challenging im- proves cross-domain generalization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.336111Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:69db686fbade3c1e95c55754595875aaddaac3683da7134b91b99c597b31c3bb","observation_id":"b39edf9c-b4b5-4af3-a517-85188562a118","resolution":{"observed_at":"2026-08-16T05:29:23.336111Z","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":"2026-08-16T05:29:23.339900Z","title":"A fourier-based framework for domain generalization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.339900Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:6813088fa0807ca363740a2ff90599471b0deb086f802f4b654d12b498e09697","observation_id":"5846d471-6cc6-4042-965d-bbf37290cf80","resolution":{"observed_at":"2026-08-16T05:29:23.339900Z","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":"2026-08-16T05:29:23.343804Z","title":"Swad: Domain generalization by seeking flat minima,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.343804Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:ee04d0c4a2699781c301e90c7b99ab74c592299c561698c1ef41185bf2bf12be","observation_id":"4d65205d-8eae-40b3-9d77-7e513e9a6588","resolution":{"observed_at":"2026-08-16T05:29:23.343804Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.08914","last_updated":"2022-08-18T15:34:13Z","snapshot_observed_at":"2026-08-20T20:26:51.236612Z","submitted_at":"2022-08-18T15:34:13Z","title":"Prompt Vision Transformer for Domain Generalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.08914","snapshot_observed_at":"2026-08-16T05:29:23.347477Z","title":"Prompt vision transformer for domain generalization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.347477Z"},"links":{"cited_paper":"/paper/2208.08914","citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:c31a6a3dd07234053565dd509ff67593619c65787172998be9c573daa4d4ddd4","observation_id":"5d8901d4-ffaa-42eb-bf92-d4c6727274cc","resolution":{"observed_at":"2026-08-16T05:29:23.347477Z","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":"2026-08-16T05:29:23.571014Z","title":"Hcvp: Leveraging hierarchical contrastive visual prompt for domain generalization,","venue":null,"work_id":"4a5a826c-f011-4677-a240-f4f859e1b62e","year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.351390Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:8b7c2de2cfc1c457b4fd4eb612a9a90a056e4378d5b636c72bc31e52e34bd3e0","observation_id":"2192cd5e-648a-463e-af39-514e31faae21","resolution":{"observed_at":"2026-08-16T05:29:23.575912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.355009Z","title":"Fedsr: A simple and effective domain generalization method for federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.355009Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:e7f145e20c8c18aec26aab36b9eb76646a7b36d03499f4b5c415c1c2bc482885","observation_id":"1bf50f20-9b94-4268-8afe-4c66597dcd44","resolution":{"observed_at":"2026-08-16T05:29:23.355009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.10487","last_updated":"2023-01-07T04:15:38Z","snapshot_observed_at":"2026-08-16T17:40:33.793598Z","submitted_at":"2021-11-20T01:02:36Z","title":"Federated Learning with Domain Generalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.10487","snapshot_observed_at":"2026-08-16T05:29:23.358607Z","title":"Federated learning with domain generalization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.358607Z"},"links":{"cited_paper":"/paper/2111.10487","citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:7f13b382ef0d69d3b05449dbbfbb29b474a47e27b35bc99c3a72d654c4f1a939","observation_id":"c5774b09-a74e-413c-b078-e5770920a959","resolution":{"observed_at":"2026-08-16T05:29:23.358607Z","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":"2026-08-16T05:29:23.362744Z","title":"Fedclip: Fast generalization and personalization for clip in federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.362744Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:52c3fd30106b436ac0d1819206bc4908fd5658aa74b838e43aaaf8d8f922e329","observation_id":"441992f3-0808-471b-8c7a-bc1d0e959c99","resolution":{"observed_at":"2026-08-16T05:29:23.362744Z","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":"2026-08-16T05:29:23.366439Z","title":"Federated adaptive prompt tuning for multi-domain collaborative learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.366439Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:9e3deb47f820786474ea6ddbd0611699aec487fdcf89c7798538d2994df35eef","observation_id":"c2ad7ddc-36c9-42ac-8910-2b8ab9fd2d5d","resolution":{"observed_at":"2026-08-16T05:29:23.366439Z","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":"2026-08-16T05:29:23.370150Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.370150Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:0c0df1a17be62ee41cfb7e25fab6a7558cf579f2b709d4b2991c75f7d110e10c","observation_id":"e07c9e75-41bf-4878-ae5e-5612a3437f1c","resolution":{"observed_at":"2026-08-16T05:29:23.370150Z","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":"2026-08-16T05:29:23.524043Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization,","venue":null,"work_id":"01fcc9b8-1ff9-46fc-b012-bc7bc7200cff","year":2017},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.373683Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:e3692748290b777827be4cd6de55e441930501bf35364ca0f5be01e0997cf0d3","observation_id":"19afa56e-72df-41f1-aeb7-c80fc8679650","resolution":{"observed_at":"2026-08-16T05:29:23.528411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T05:29:23.511056Z","title":null,"venue":null,"work_id":"b1f59a85-eb7f-411a-abc7-5cdc8a78a3d6","year":null},"citing_paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-16T05:29:23.377390Z"},"links":{"citing_paper":"/paper/2504.21063"},"observation_digest":"sha256:91b588d3adc0fb8e601c52e1606fe68113d598d21490ca44bd0306ad9b69ac95","observation_id":"5058db04-b116-4a28-a3c9-7896ee7e8633","resolution":{"observed_at":"2026-08-16T05:29:23.515784Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2504.21063","last_updated":"2025-04-29T11:06:03Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T16:57:08.394366Z","submitted_at":"2025-04-29T11:06:03Z","title":"Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalization"},"reference_resolution":{"displayed":64,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":48,"verified_exact":1,"verified_fuzzy":15},"total_outbound_references":64},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2504.21063."}