{"as_of":"2026-08-14T12:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:38dccf2c3f677411e7e099531b977d004d11685329c4889f73dd2c5ebe8e225c","coverage":[{"denominator":94,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":94,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T18:53:06.664545Z","state":"measured"},{"denominator":95,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":95,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T12:20:30.366810Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-11T12:20:30.490539Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"cited_work":{"arxiv_id":"2411.11912","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.11912","snapshot_observed_at":"2026-08-11T12:20:30.490539Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","venue":"cs.CV","work_id":"a28e0c11-0328-422b-93f9-39aa8b5597df","year":2024},"citing_paper":{"arxiv_id":"2412.14424","last_updated":"2024-12-19T00:24:00Z","snapshot_observed_at":"2026-08-13T16:46:31.834754Z","submitted_at":"2024-12-19T00:24:00Z","title":"FedPIA -- Permuting and Integrating Adapters leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-11T12:20:30.366810Z"},"links":{"cited_paper":"/paper/2411.11912","citing_paper":"/paper/2412.14424"},"observation_digest":"sha256:e510128a787346de994aff3466072c6786fd84aa1c47af805b9a0835937d7de0","observation_id":"97db2297-55f4-497f-9802-58832ce468a2","resolution":{"observed_at":"2026-08-11T12:20:30.493516Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.11912/citation-record","integrity":"/paper/2411.11912/integrity","json":"/paper/2411.11912/citation-record.json","paper":"/paper/2411.11912"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T18:53:06.321282Z","title":"Ben Abacha, Vivek V","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.321282Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:e4da288e56e2267f3428f47f11ad7a221262b135fdfe87e6bd833c5c9eb58096","observation_id":"b83b062f-fa03-41b8-9f37-dfe524223089","resolution":{"observed_at":"2026-08-12T18:53:06.321282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.04263","last_updated":"2021-11-09T16:37:10Z","snapshot_observed_at":"2026-08-06T07:03:02.521207Z","submitted_at":"2021-11-08T03:58:28Z","title":"Federated Learning Based on Dynamic Regularization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.04263","snapshot_observed_at":"2026-08-12T18:53:06.326120Z","title":"Federated learning based on dynamic regular- ization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.326120Z"},"links":{"cited_paper":"/paper/2111.04263","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:64d74c1ca408b578a0f876cad1c3d1c3de84590e9322a713d2b51ed5931c64a1","observation_id":"4e594fce-65a4-43f9-b0f3-4779222eefdb","resolution":{"observed_at":"2026-08-12T18:53:06.326120Z","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":"2026-08-13T23:51:40.504761Z","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":"2026-08-12T18:53:06.330558Z","title":"Federated learning with personalization layers","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.330558Z"},"links":{"cited_paper":"/paper/1912.00818","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:72ae7e5c667db3e66cef8f36f280d429cf8e6e26087c6ff9dd9d23e8d3756200","observation_id":"ac35a29e-a497-4063-9355-71af7ef84502","resolution":{"observed_at":"2026-08-12T18:53:06.330558Z","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":"2026-08-12T18:53:06.335025Z","title":"Artificial bee colony algorithm: a survey","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.335025Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:9dd025ccff0c21c3afad2a4f9d280ad8f1cdd0c12f898e48f3faf57b45d9912c","observation_id":"87b6655c-428f-4d41-9e28-cec864f8eb5a","resolution":{"observed_at":"2026-08-12T18:53:06.335025Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.01917","last_updated":"2023-04-04T16:14:39Z","snapshot_observed_at":"2026-08-13T12:09:21.634692Z","submitted_at":"2023-04-04T16:14:39Z","title":"Strong Baselines for Parameter Efficient Few-Shot Fine-tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.01917","snapshot_observed_at":"2026-08-12T18:53:06.338788Z","title":"Strong baselines for parameter efficient few-shot fine-tuning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.338788Z"},"links":{"cited_paper":"/paper/2304.01917","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:e1c2377793c20565c3173d4968950dbf34f1a968b0c0d59b313cae9188258c1e","observation_id":"18bc4fae-ee33-413d-a9e3-744ad957b18a","resolution":{"observed_at":"2026-08-12T18:53:06.338788Z","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":"2026-08-12T18:53:06.342583Z","title":"Vqa-med: Overview of the medical visual question answering task at imageclef 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.342583Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:fb655ba274b4b85a7fe33e4b5433ae8f3c0dc9a26f5f97af493fe9fabc4872da","observation_id":"4402f1af-c0e9-48ce-a5f0-a7ec3d286b07","resolution":{"observed_at":"2026-08-12T18:53:06.342583Z","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":"2026-08-12T18:53:06.346449Z","title":"Overview of the vqa-med task at imageclef 2021: Visual question answer- ing and generation in the medical domain","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.346449Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:5b11a01226894df4633c384b01e53c77f4e797893521512db14d45a5ea919a23","observation_id":"74cc905d-6217-4f1c-8cd7-784aa97465a2","resolution":{"observed_at":"2026-08-12T18:53:06.346449Z","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":"2026-08-12T18:53:06.350294Z","title":"Bit- Fit: Simple parameter-efficient fine-tuning for transformer- based masked language-models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.350294Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:a088011a234b1c175509a5c67af98a6dfc371baca9e4b8ad9815b1b778f40870","observation_id":"386e2a21-51c5-4f01-8142-1c3d12fc1b9d","resolution":{"observed_at":"2026-08-12T18:53:06.350294Z","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":"2026-08-12T18:53:06.353808Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.353808Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:983bf7773944248ff32ce16d7b582f7e72a988cfea588090bb1f0be052efe5cd","observation_id":"70479dd8-bde1-453b-aeb7-c7c90c313e49","resolution":{"observed_at":"2026-08-12T18:53:06.353808Z","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":"2026-08-12T18:53:06.358013Z","title":"A brief introduction to the neural tan- gent kernel","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.358013Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:a0af0a75223bb3d255d46641e242b641e1722638f0958e773bf96345c2c766ca","observation_id":"1d58240c-5e2c-44c7-9b4f-8444d94d261e","resolution":{"observed_at":"2026-08-12T18:53:06.358013Z","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":"2026-08-12T18:53:06.361722Z","title":"Tinytl: Reduce memory, not parameters for efficient on-device learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.361722Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:ad6cfae29c2f020de4b6a16266215e5aeaa1a57f10e8da36d27571f07eecd1e4","observation_id":"faf86964-8728-4b5d-8bd8-03dc4267cfa8","resolution":{"observed_at":"2026-08-12T18:53:06.361722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.01198","last_updated":"2020-10-05T17:51:35Z","snapshot_observed_at":"2026-08-14T00:16:17.489339Z","submitted_at":"2019-12-03T05:34:30Z","title":"Towards Understanding the Spectral Bias of Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.01198","snapshot_observed_at":"2026-08-12T18:53:06.365147Z","title":"Towards understanding the spectral bias of deep learning","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.365147Z"},"links":{"cited_paper":"/paper/1912.01198","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:47a978d498171e16bd53514cfe4052d413ff0b54781c4ca8ee67c7494c231044","observation_id":"23b8770b-17b5-41a9-8178-092dd35914d7","resolution":{"observed_at":"2026-08-12T18:53:06.365147Z","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":"2026-08-12T18:53:06.368947Z","title":"Efficient personalized federated learning via sparse model-adaptation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.368947Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:2a19a316918eee16c73581687329ce7ee8f681fc45c45eca2d6fdd77c9ebcc80","observation_id":"74f26da8-678f-4e45-b9e2-f6618c69e6af","resolution":{"observed_at":"2026-08-12T18:53:06.368947Z","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":"2026-08-12T18:53:06.372645Z","title":"Feddat: An approach for foundation model finetuning in multi-modal heterogeneous federated learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.372645Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:c1b9ff881cbf2fd88ae6e7d1a1246937828cc0cc1f2e99a69dd2eb433eee8b8b","observation_id":"cc2f5536-eb06-414b-9cec-0ed4784e9716","resolution":{"observed_at":"2026-08-12T18:53:06.372645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.00778","last_updated":"2022-07-11T02:47:28Z","snapshot_observed_at":"2026-08-13T18:53:15.798545Z","submitted_at":"2021-07-02T00:25:48Z","title":"On Bridging Generic and Personalized Federated Learning for Image Classification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.00778","snapshot_observed_at":"2026-08-12T18:53:06.376168Z","title":"On bridging generic and personalized federated learning for image classification","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.376168Z"},"links":{"cited_paper":"/paper/2107.00778","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:60bd37f5cdf7d206cb3e70fade8f7d4fca8bcd7fe36b11084db17bb726eec738","observation_id":"bbcac1b2-7739-4abd-a71b-8082fe349fe8","resolution":{"observed_at":"2026-08-12T18:53:06.376168Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.08025","last_updated":"2022-11-15T10:16:13Z","snapshot_observed_at":"2026-08-13T13:42:42.475732Z","submitted_at":"2022-11-15T10:16:13Z","title":"FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.08025","snapshot_observed_at":"2026-08-12T18:53:06.379998Z","title":"Fedtune: A deep dive into ef- ficient federated fine-tuning with pre-trained transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.379998Z"},"links":{"cited_paper":"/paper/2211.08025","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:2951a2629110c8d00a44db31c4a2a6f0e6fac2a437cdd793dcd1c9f36c00d672","observation_id":"7b60971e-eed2-490f-ade7-c05fe7a0394e","resolution":{"observed_at":"2026-08-12T18:53:06.379998Z","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":"2026-08-12T18:53:06.383648Z","title":"Metafed: Federated learning among federations with cyclic knowledge distillation for personalized healthcare","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.383648Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:b5a7ca9e65cbf4d91a2ab9e645ad8ba2e2ea45e3688d2ae31e28b6f3a4fa92ea","observation_id":"bc962221-affa-4cfa-bb27-36ccaebc00af","resolution":{"observed_at":"2026-08-12T18:53:06.383648Z","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":"2026-08-12T18:53:06.387427Z","title":"Mopso: A proposal for multiple objective particle swarm optimiza- tion","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.387427Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:16cfd86118d2ac0ff99f46215f6bc0f3a893ac59283a5174762d36f004969b28","observation_id":"441f3076-fdd3-4fc9-afeb-6d89ac1cfd0c","resolution":{"observed_at":"2026-08-12T18:53:06.387427Z","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":"2026-08-12T18:53:06.390958Z","title":"Exploiting shared representations for personal- ized federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.390958Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:b243c6f1e9ddff5d1588da2d473e1534e82497339061507414fa3967a53943b8","observation_id":"51fa2024-133f-4bf9-a082-ca1b2507a932","resolution":{"observed_at":"2026-08-12T18:53:06.390958Z","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":"2026-08-12T18:53:06.394672Z","title":"A fast and elitist multiobjective genetic algo- rithm: Nsga-ii","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.394672Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:04b3be874e1b3b689968e054b385f3dff41b76b6e5b2b6f6faeb34782a94f67d","observation_id":"b141f5ba-b56e-416d-991f-14638eead82c","resolution":{"observed_at":"2026-08-12T18:53:06.394672Z","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":"2026-08-12T18:53:07.823212Z","title":"Ant colony optimization","venue":null,"work_id":"4690dfdd-5380-4ab0-9a82-59b159ded5dc","year":2006},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.398256Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:19684eba116291ce5871b78dd3f926ea1452d0af3fbab203c755d65ab5454945","observation_id":"cab50d9b-35ad-4d05-8a84-de4c9b4f91d7","resolution":{"observed_at":"2026-08-12T18:53:07.828544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.807306Z","title":"Resist: Layer-wise decomposition of resnets for distributed training","venue":null,"work_id":"8ac51952-6072-4fc5-988e-bd7bafb0c2fa","year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.402476Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:128ee6cadd168b66725b8837d32d58bbfe93696fee587a1eaa92eff125759125","observation_id":"826d40db-2c98-452e-ae31-5b30e21ed915","resolution":{"observed_at":"2026-08-12T18:53:07.812387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.789593Z","title":"Per- sonalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","venue":null,"work_id":"24e9cbac-9c65-4ff2-8a06-7a5b1fbf6f25","year":2020},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.406057Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:5ede80b3686b7c831429a3e7c5804ae500db1967b2185748b46f4da081bcf78b","observation_id":"eb46fcc5-cb60-4e71-bb21-ddfbf3df41ab","resolution":{"observed_at":"2026-08-12T18:53:07.794953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.774165Z","title":"Schwab, and Ari S","venue":null,"work_id":"52fb7866-1980-46b7-838e-bdc12f304b4a","year":2021},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.409564Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:8052952278ebea04f16f08a1d28431cba7ac1bbe913c638892aa6eb28c3fcf15","observation_id":"ce847ab2-a57c-4f5d-a7a2-44cff86ea619","resolution":{"observed_at":"2026-08-12T18:53:07.778780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.757866Z","title":"Promptfl: Let federated participants cooper- atively learn prompts instead of models-federated learning in age of foundation model","venue":null,"work_id":"b65f09b9-75f4-4651-a38e-e2f5a6e33739","year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.413211Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:cc46a8eff7c02f43e781c4619481eaf347b13fdc326d24fc08a570696266a21c","observation_id":"83ec9881-587f-4b4a-a1da-f38882de8995","resolution":{"observed_at":"2026-08-12T18:53:07.763123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.743377Z","title":"Learn- ing both weights and connections for efficient neural net- work","venue":null,"work_id":"861569cd-e621-409f-ae17-895d9c5542ad","year":2015},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.417209Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:839bbec8687c144d0a05d1f2fdbd48cbd35b99fd9a484ea83b60312259b8879d","observation_id":"223dd447-2ce1-4ec8-a849-d18a15954f3d","resolution":{"observed_at":"2026-08-12T18:53:07.748426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.726911Z","title":"Sensitivity-aware visual parameter-efficient fine- tuning","venue":null,"work_id":"95726ba6-d186-4d86-84fe-c16b7e53c321","year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.420561Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:3481daa158ee0cc5a2319ddec68ff353766a7bfc84d793c98346b0f21492494a","observation_id":"02db3759-c066-424d-82da-06a79c455108","resolution":{"observed_at":"2026-08-12T18:53:07.731580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.10286","last_updated":"2020-03-07T17:55:41Z","snapshot_observed_at":"2026-07-06T09:06:42.071993Z","submitted_at":"2020-03-07T17:55:41Z","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.10286","snapshot_observed_at":"2026-08-12T18:53:06.424020Z","title":"Pathvqa: 30000+ questions for medical visual question answering","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.424020Z"},"links":{"cited_paper":"/paper/2003.10286","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:13aae6644f6e12145f22274eb33657d76feb59868b1138870573c6f28533f03c","observation_id":"85a503c6-6832-4d76-b3e5-1cd36c6b5246","resolution":{"observed_at":"2026-08-12T18:53:06.424020Z","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":"2026-08-12T18:53:07.707671Z","title":"Re- view of federated learning and machine learning-based methods for medical image analysis","venue":null,"work_id":"c0dd2ed1-daf0-437b-a475-8f5dd92c5a36","year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.427735Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:d590e8aee7c9597a5c5255295ea53489eb1f781de4d3de134279bf60fd216abf","observation_id":"2c76288f-bbfc-40d0-b60e-9e3c0cd2d733","resolution":{"observed_at":"2026-08-12T18:53:07.717910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.689439Z","title":"Scaling feder- ated learning for fine-tuning of large language models","venue":null,"work_id":"dfa86485-e658-49ca-8e56-8f7414169e41","year":2021},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.431176Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:5025cc68da437e9834969cf4e1b16a4e2a3b40a28fe8b21f0e5c8b9e0469906d","observation_id":"5263f5b9-f25d-4063-86f8-f9982bcccf20","resolution":{"observed_at":"2026-08-12T18:53:07.694999Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.677147Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":"fa5e0d70-9492-4972-9f6c-4141114acd15","year":2019},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.435018Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:661a1b0f805b82fe982911ec7228512855b0bc7fe12dad7f83a01f52fc32a83d","observation_id":"0055083c-1709-429d-8961-38d6b2dba222","resolution":{"observed_at":"2026-08-12T18:53:07.681140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.662090Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":"75018205-ca0a-4067-a6e6-72a3c250efd5","year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.438752Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:e3698298ec916d59f1c6d08d94f77b6e55d94731b5e28a2ed50c837ab9cff324","observation_id":"22ef1ad6-9b81-4b92-9fee-2478a529bcfd","resolution":{"observed_at":"2026-08-12T18:53:07.667034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.645919Z","title":"Omnimedvqa: A new large-scale comprehensive evaluation benchmark for medical lvlm","venue":null,"work_id":"fe43481f-de2c-496c-b9f2-b8f91f754a22","year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.442504Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:176281c1ffa33b9c21b99c8db241ec3c36bf2e5568a47039458e6be13adddd14","observation_id":"9e12f097-4f06-4be1-8766-5a4f47fb3585","resolution":{"observed_at":"2026-08-12T18:53:07.650875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.630116Z","title":"Neu- ral tangent kernel: Convergence and generalization in neural networks","venue":null,"work_id":"6b8a899e-b026-4b80-bbbf-93d39f6c898b","year":2018},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.446428Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:9495c1a3a479e8427f5160d334ad67ba616c48aa7b7fc9ff58f2fdf1837bddd6","observation_id":"45c7fa1d-9679-4b7f-8437-4d13e479902e","resolution":{"observed_at":"2026-08-12T18:53:07.635101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.612893Z","title":"Vi- sual prompt tuning","venue":null,"work_id":"86dbed7a-4fce-471e-bf54-0d80e5c627b6","year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.449774Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:4a2bc78305292714af676605e9aae85022786c39213401fc29e81cd087c49108","observation_id":"f49d93a0-81f6-42fe-994e-ada968323929","resolution":{"observed_at":"2026-08-12T18:53:07.618022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.06354","last_updated":"2023-07-02T12:28:46Z","snapshot_observed_at":"2026-08-13T12:45:29.566599Z","submitted_at":"2023-02-13T13:38:46Z","title":"Less is More: Selective Layer Finetuning with SubTuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.06354","snapshot_observed_at":"2026-08-12T18:53:06.453273Z","title":"Less is more: Selective layer finetuning with subtuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.453273Z"},"links":{"cited_paper":"/paper/2302.06354","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:87e3050d41e741b131a50330cbeacbff92b0aba002e055282ebc43ad8e4278d3","observation_id":"a7ce9787-bf89-467f-8381-0b9a27ad6d2d","resolution":{"observed_at":"2026-08-12T18:53:06.453273Z","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":"2026-08-12T18:53:07.596575Z","title":"Scaffold: Stochastic controlled averaging for feder- ated learning","venue":null,"work_id":"afdd7535-1735-4676-8eea-b60d2203f920","year":2020},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.457030Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:9e17991bd4a511e9f36a11e5c4b77dc2c97b440c5990abc09236637d750253d1","observation_id":"9364b8f3-2f1a-499a-9de9-ff4a70385842","resolution":{"observed_at":"2026-08-12T18:53:07.601019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.583083Z","title":"Vilt: Vision- and-language transformer without convolution or region su- pervision","venue":null,"work_id":"2c0d75e9-4022-499c-af2a-65af7ae33b97","year":2021},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.460303Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:c54186833a5517a9796805c26e92a591e242e3beec30dfa213114c4fd9b15a2e","observation_id":"50bcfa2d-adec-4d7a-9d1c-0a8cb55c6c8a","resolution":{"observed_at":"2026-08-12T18:53:07.587358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08593","last_updated":"2019-09-11T16:26:37Z","snapshot_observed_at":"2026-08-14T11:56:50.742888Z","submitted_at":"2019-08-21T04:27:38Z","title":"Revealing the Dark Secrets of BERT","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08593","snapshot_observed_at":"2026-08-12T18:53:06.463483Z","title":"Revealing the dark secrets of bert.arXiv preprint arXiv:1908.08593, 2019","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.463483Z"},"links":{"cited_paper":"/paper/1908.08593","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:91c6b459e19ad0c42ac4a57d27df9d7740874792599e2f436c14404302ad4b12","observation_id":"d89c29b0-e266-45fc-8173-95ac767cdc2f","resolution":{"observed_at":"2026-08-12T18:53:06.463483Z","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":"2026-08-12T18:53:07.568258Z","title":"A dataset of clinically generated visual questions and answers about radiology images","venue":null,"work_id":"f483064e-f416-4764-99f7-29c50079b230","year":2018},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.467042Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:350c1c610637ca227df264f5119b8c64c123205bf79244ac5b4d3f3c7f301009","observation_id":"41b2717b-af88-40bb-a54e-4966cbc43761","resolution":{"observed_at":"2026-08-12T18:53:07.573529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.553493Z","title":"Mixout: Effective regularization to finetune large-scale pre- trained language models","venue":null,"work_id":"c89e1fc6-13ca-493b-a8ce-2f023a7f75e4","year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.470672Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:7358ccea4e9454db7e40698899f9bb98ca72d5f2d681310d193f58edecf4b336","observation_id":"6a4fecc5-6a5a-4783-a35a-bd8cd4bb4ed6","resolution":{"observed_at":"2026-08-12T18:53:07.557869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.03090","last_updated":"2019-11-08T07:05:20Z","snapshot_observed_at":"2026-08-11T00:43:30.125982Z","submitted_at":"2019-11-08T07:05:20Z","title":"What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.03090","snapshot_observed_at":"2026-08-12T18:53:06.474352Z","title":"What would elsa do? freezing layers during transformer fine-tuning","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.474352Z"},"links":{"cited_paper":"/paper/1911.03090","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:966cb10d6e4be0ed8ac0e9759eb91a6c13048d3e94ec2c2b07c1103a0ee7298f","observation_id":"33ced952-e8bb-45de-a1c7-b1dd8ff43b43","resolution":{"observed_at":"2026-08-12T18:53:06.474352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.02340","last_updated":"2019-02-23T07:45:29Z","snapshot_observed_at":"2026-07-06T07:06:10.289386Z","submitted_at":"2018-10-04T17:39:58Z","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.02340","snapshot_observed_at":"2026-08-12T18:53:06.478042Z","title":"Snip: Single-shot network pruning based on connec- tion sensitivity","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.478042Z"},"links":{"cited_paper":"/paper/1810.02340","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:2fdfa645be02bdde7b939b9e9caf2e1a027f0d4a65d2a3a7169a2ece25c77939","observation_id":"cfd80acb-cf87-4426-94e7-8c5a00ff609c","resolution":{"observed_at":"2026-08-12T18:53:06.478042Z","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":"2026-08-12T18:53:07.539559Z","title":"Layer- wise adaptive model aggregation for scalable federated learning","venue":null,"work_id":"1a27923d-456d-4fab-b0eb-aa9696d8cf64","year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.481742Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:2af6f7345e6ae7573fcc358a59418dd59a93e283d38ab80403579a3a7a76ebf4","observation_id":"ad47bda8-09b8-4aae-9b43-896ccbc3411c","resolution":{"observed_at":"2026-08-12T18:53:07.544516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.11466","last_updated":"2023-06-06T05:58:11Z","snapshot_observed_at":"2026-08-13T14:00:18.768665Z","submitted_at":"2022-10-20T17:59:15Z","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.11466","snapshot_observed_at":"2026-08-12T18:53:06.485009Z","title":"Surgical fine-tuning improves adaptation to distribution shifts","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.485009Z"},"links":{"cited_paper":"/paper/2210.11466","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:3d66768339839658951ace646bad9640384ee034afdfbc5cce89a668099910db","observation_id":"cd0d725b-e415-42c4-b785-a4a47f6a39e4","resolution":{"observed_at":"2026-08-12T18:53:06.485009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-06T15:24:34.790850Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08691","snapshot_observed_at":"2026-08-12T18:53:06.488529Z","title":"The power of scale for parameter-efficient prompt tuning.arXiv preprint arXiv:2104.08691","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.488529Z"},"links":{"cited_paper":"/paper/2104.08691","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:9b6233b915cc6a9585bbfa7574b290f86eb85a81e705b3ad01adcb175c8252e0","observation_id":"77ce0821-3645-4905-89e5-e398c290d1bb","resolution":{"observed_at":"2026-08-12T18:53:06.488529Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.08065","last_updated":"2020-11-16T22:13:31Z","snapshot_observed_at":"2026-07-06T09:56:22.631976Z","submitted_at":"2020-09-17T04:45:47Z","title":"Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning","version":4},"cited_work":{"arxiv_id":"2009.08065","doi":null,"metadata_source":"pith","pith_arxiv_id":"2009.08065","snapshot_observed_at":"2026-08-12T18:53:06.965527Z","title":"Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning","venue":"cs.CL","work_id":"e016c692-1ee0-4335-85fe-8a60393f5718","year":2020},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.492381Z"},"links":{"cited_paper":"/paper/2009.08065","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:bf27c040cecaeb07b9d2c576ba4e54e7772759c4ef9114f4823b44ca8b57f129","observation_id":"08e1e454-2ac5-434b-9754-b61813cecc27","resolution":{"observed_at":"2026-08-12T18:53:06.970056Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.524581Z","title":"Align before fuse: Vision and language representation learn- ing with momentum distillation","venue":null,"work_id":"ba8715dd-215a-4a05-83eb-f30b07d06f6a","year":2021},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.495989Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:45d299b53044f1caacbbad6010677f5369a48a762fc4c85acc4bf6f36cce4a19","observation_id":"ed9ba351-609f-416d-83d8-950ad66353a4","resolution":{"observed_at":"2026-08-12T18:53:07.529237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:06.499418Z","title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.499418Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:7cdb9ce179eb703b154c7be46ad693806ffc5524bca6f31d999e7699391a1805","observation_id":"d40b4abb-53c5-43ae-8cef-227702fbb8ab","resolution":{"observed_at":"2026-08-12T18:53:06.499418Z","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":"2026-08-12T18:53:06.502998Z","title":"Federated learning: Challenges, methods, and future directions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.502998Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:c2523e763280f4059d0e8d8b5a618d8b9187c1c2a6e096150e3380d38cf5404f","observation_id":"ca72d821-63cf-42da-8984-79659cd4c611","resolution":{"observed_at":"2026-08-12T18:53:06.502998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-08-12T12:37:28.207761Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-12T18:53:06.506752Z","title":"Prefix-tuning: Optimiz- ing continuous prompts for generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.506752Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:0af84e75e30dc9761cb848ab06c3dfabb630850f53e73c33c977ed9b3918315d","observation_id":"59be2553-c414-40d5-8834-51406a278853","resolution":{"observed_at":"2026-08-12T18:53:06.506752Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.08823","last_updated":"2023-01-15T10:31:33Z","snapshot_observed_at":"2026-08-13T14:03:56.606429Z","submitted_at":"2022-10-17T08:14:49Z","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.08823","snapshot_observed_at":"2026-08-12T18:53:06.510676Z","title":"Scaling & shifting your features: A new baseline for efficient model tuning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.510676Z"},"links":{"cited_paper":"/paper/2210.08823","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:83cea322db12e5d5d7ccc49edec9fd981ff14e1cd14a12d1e39be3093f7d52f2","observation_id":"3d7dda2d-fc5d-4144-b18a-687863c56b03","resolution":{"observed_at":"2026-08-12T18:53:06.510676Z","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":"2026-08-12T18:53:07.493838Z","title":"Slake: A semantically-labeled knowledge- enhanced dataset for medical visual question answering","venue":null,"work_id":"6d43aeb5-5078-467a-9eac-82debfc2eeba","year":2021},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.514975Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:a5d255a6db28bf544eda098b7a9ad91cab0f2c8097074480a124b25f4a28d2ae","observation_id":"9dc7dc55-4b58-47b2-86d6-3939aaadf14f","resolution":{"observed_at":"2026-08-12T18:53:07.498390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.481113Z","title":"Improved baselines with visual instruction tuning","venue":null,"work_id":"871268d2-f528-488c-bf82-4ff01053c798","year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.518483Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:ce749cf41e77e33819386d6aa28e3e2fad92313f24276b7cfa780717ec59b9cf","observation_id":"2cedda7c-3d48-4334-a4b6-69d146b7a369","resolution":{"observed_at":"2026-08-12T18:53:07.485151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04596","last_updated":"2024-07-17T22:11:08Z","snapshot_observed_at":"2026-08-14T04:35:16.641325Z","submitted_at":"2024-06-07T03:00:07Z","title":"Federated Representation Learning in the Under-Parameterized Regime","version":4},"cited_work":{"arxiv_id":"2406.04596","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.04596","snapshot_observed_at":"2026-08-12T18:53:06.924910Z","title":"Federated Representation Learning in the Under-Parameterized Regime","venue":"cs.LG","work_id":"175d0dd4-5ca4-4b9f-b8b8-694b963b2ca6","year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.522075Z"},"links":{"cited_paper":"/paper/2406.04596","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:d59aeeb0761c68c8be4afb227c67401b28efb9f9f12dfbca5d72c9c857890d57","observation_id":"b4e0986f-e2da-4fcd-a2a9-7a893764acd6","resolution":{"observed_at":"2026-08-12T18:53:06.929540Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.467816Z","title":"Personalized feder- ated learning with adaptive batchnorm for healthcare","venue":null,"work_id":"28c4d11c-b648-44ec-8823-fee3a7b3abfe","year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.525791Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:a22b95e68108b45fb8374bf87a6cab021313e90fb0b7fd96572e7274af13d153","observation_id":"55273a18-50d6-405b-9bc9-271ee2653779","resolution":{"observed_at":"2026-08-12T18:53:07.472340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.453345Z","title":"A gradient flow framework for analyzing network pruning","venue":null,"work_id":"59cbbcf8-e909-41e2-8e8f-f0908f287b73","year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.529316Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:38dbb5657ec872dccb579a1224bac036ba5014895419fcb74e4bf684fd50dc5e","observation_id":"05db1912-ac70-4a0e-acce-c9df1d8cf46e","resolution":{"observed_at":"2026-08-12T18:53:07.458461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.438516Z","title":"Communication- efficient learning of deep networks from decentralized data","venue":null,"work_id":"2a6a517d-b429-4a16-b125-762f63ca480f","year":2017},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.532837Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:9be7ff4dc19ea3540b58edac659dc1b4f6582e1badb02bf21598fd3a9b867cfe","observation_id":"48c06970-726d-4d03-b2c6-72f5ca3e7aad","resolution":{"observed_at":"2026-08-12T18:53:07.443364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.15387","last_updated":"2023-03-24T19:09:30Z","snapshot_observed_at":"2026-08-13T15:58:02.694761Z","submitted_at":"2022-06-30T16:18:21Z","title":"Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.15387","snapshot_observed_at":"2026-08-12T18:53:06.536308Z","title":"Where to begin? exploring the impact of pre- training and initialization in federated learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.536308Z"},"links":{"cited_paper":"/paper/2206.15387","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:c1b2a092a6fc63bda228fddf7fa34509a646197860108ab85e925a305c189ac7","observation_id":"4c5a0897-3045-4ef9-8cb3-a3e23494a7d1","resolution":{"observed_at":"2026-08-12T18:53:06.536308Z","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":"2026-08-12T18:53:07.424192Z","title":"Federated learning with partial model personalization","venue":null,"work_id":"7bec1fdc-5eb8-4b1d-b6b5-f4b843c3b32f","year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.540109Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:f6bdb90910477d472c04d14dde6c0f63ec38e442cdd8503786d1b1b9612ee18c","observation_id":"251675c1-a779-4dda-b441-95472903f974","resolution":{"observed_at":"2026-08-12T18:53:07.428300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.411316Z","title":"Winning the lottery ahead of time: Efficient early network pruning","venue":null,"work_id":"fee64ca7-01f8-4991-b663-094c2c67bd00","year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.543945Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:1752b0cab417cb0206c3a3394e9f186b5ad3a94374de95c5410bd0891b0ba648","observation_id":"fbb18ccf-c687-4749-a770-615ffccd9da1","resolution":{"observed_at":"2026-08-12T18:53:07.415871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:06.548239Z","title":"On the spectral bias of neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.548239Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:f38cba481f720800f8bbc3190d5488f90b0002861cef789cdebcfbc6a8499920","observation_id":"a6dfb6d0-24a3-4360-bd50-efec27b3900b","resolution":{"observed_at":"2026-08-12T18:53:06.548239Z","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":"2026-08-12T18:53:07.390205Z","title":"Efficient parametrization of multi-domain deep neural net- works","venue":null,"work_id":"5234b20b-59ee-4742-9e40-8f31cb88a1bd","year":2018},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.551805Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:8b7757c66bdfd74a5b40040e436f46824a53fafd642e63d74583c42a27314c0b","observation_id":"ced4d011-e4bb-4f28-ad4c-42bb724385f0","resolution":{"observed_at":"2026-08-12T18:53:07.394090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11918","last_updated":"2021-10-05T18:37:04Z","snapshot_observed_at":"2026-08-11T05:10:24.849616Z","submitted_at":"2020-10-22T17:49:42Z","title":"AdapterDrop: On the Efficiency of Adapters in Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11918","snapshot_observed_at":"2026-08-12T18:53:06.555531Z","title":"Adapterdrop: On the efficiency of adapters in transformers","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.555531Z"},"links":{"cited_paper":"/paper/2010.11918","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:471cd12c7e1774ecd20097ad43b1751aa4e369bb44e06d9a3bd375de7f9920e1","observation_id":"9ca72baf-4ee8-4bec-89fa-2137e0a635e0","resolution":{"observed_at":"2026-08-12T18:53:06.555531Z","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":"2026-08-12T18:53:07.378185Z","title":"Re- thinking semi-supervised federated learning: How to co- train fully-labeled and fully-unlabeled client imaging data","venue":null,"work_id":"87e1324a-2310-467e-a3c6-95975567219f","year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.559477Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:5eb035b96fe73e6ce9bff69aa178a2386397d1d02031e1d4b6c960694757e3c2","observation_id":"3815a67e-2213-4251-8153-82ba197ed46e","resolution":{"observed_at":"2026-08-12T18:53:07.382123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.365614Z","title":"Alison Noble","venue":null,"work_id":"139c9852-35d1-43ab-a36a-fd96b583344b","year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.563174Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:5de7c41ca91f02b5b27dabdac443b241ee8f7bed100ea9d272433d8e2840be84","observation_id":"24b34591-6c62-4b36-9d29-a72d06b6aba1","resolution":{"observed_at":"2026-08-12T18:53:07.369928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.14424","last_updated":"2024-12-19T00:24:00Z","snapshot_observed_at":"2026-08-13T16:46:31.834754Z","submitted_at":"2024-12-19T00:24:00Z","title":"FedPIA -- Permuting and Integrating Adapters leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning","version":1},"cited_work":{"arxiv_id":"2412.14424","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.14424","snapshot_observed_at":"2026-08-12T18:53:06.872735Z","title":"FedPIA -- Permuting and Integrating Adapters leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning","venue":"cs.CV","work_id":"d741c574-8d8e-4129-8034-839b5f95d97c","year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.566726Z"},"links":{"cited_paper":"/paper/2412.14424","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:158706587f9ffd2fcac90132ab0dbd24b84f77f0486227f2478a9f4dd890975e","observation_id":"ab236f6d-066f-445a-b29e-0d3428895b07","resolution":{"observed_at":"2026-08-12T18:53:06.879156Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.352786Z","title":"Partial is better than all: Revisiting fine- tuning strategy for few-shot learning","venue":null,"work_id":"1dbe1d06-108a-4f59-a4a0-404f56027482","year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.570806Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:4eb0116fa83c170d149bdcc2dfcc7ce14b388287f8c0392c401a6a833d702da5","observation_id":"55fd1160-e7f7-471f-bbff-15860dd99b9c","resolution":{"observed_at":"2026-08-12T18:53:07.357248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.339966Z","title":"Train faster, perform better: mod- ular adaptive training in over-parameterized models","venue":null,"work_id":"dc255a1b-223c-4665-ba85-a95f149b350b","year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.574263Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:c4c15da97df2ab92b3e80cc001afcabdfb99c5df7ef8f826d6b593370d4da80f","observation_id":"8ea35f4d-3cbc-4ee6-9152-d9e46f9489c1","resolution":{"observed_at":"2026-08-12T18:53:07.343975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.326928Z","title":"Exploring parameter-efficient fine-tuning for improv- ing communication efficiency in federated learning","venue":null,"work_id":"fe25002e-1b51-46c6-b01e-fbb703ccade3","year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.577840Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:60602f82516fdf8e6156fabfb43ba543855f3259ccdf1fb9eaf31a1f15cc4e88","observation_id":"87628cc8-91b9-4201-864c-7b800ee24596","resolution":{"observed_at":"2026-08-12T18:53:07.331249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.313055Z","title":"Training neu- ral networks with fixed sparse masks","venue":null,"work_id":"3617ab8b-5e5b-4ae4-919a-3d7aed4d6226","year":2021},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.581747Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:23a5969187e475d8a062d77daa410fc6dbdd87e41cb792671d3992da4e472347","observation_id":"e2c3a239-746b-42d7-82a2-eea666a47cf8","resolution":{"observed_at":"2026-08-12T18:53:07.317377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.298000Z","title":"Fedselect: Personalized fed- erated learning with customized selection of parameters for fine-tuning","venue":null,"work_id":"809c056d-0a37-4d39-98ed-547784c4d307","year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.585502Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:a418436e67ed0fb6cc453fc164bd95363edc76434ab4faccf4135bd07548ceb9","observation_id":"0d26780e-c7ff-45f1-af42-e23c5a2f07a5","resolution":{"observed_at":"2026-08-12T18:53:07.303057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.282928Z","title":"Fedproto: Federated proto- type learning across heterogeneous clients","venue":null,"work_id":"5bfc8ccd-8b88-4b14-99c3-93bb6dfbbf70","year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.588919Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:239a9de99607d31e6b3dff804c354d21faca03b8bbae63dd29d17816805a3568","observation_id":"cc8c4c1e-38c2-438a-8d1e-028e0adf2163","resolution":{"observed_at":"2026-08-12T18:53:07.287296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.270355Z","title":"Pruning neural networks without any data by iter- atively conserving synaptic flow","venue":null,"work_id":"d41789ee-5938-4f2e-9d1e-2ef8a28d7615","year":2020},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.592678Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:7f3ef63cbc0ca08d5c3405bb2d965a7b0603d13b492ecadd23f9728781c69011","observation_id":"e5c5f7da-33ac-4a45-952f-2da9ea497c37","resolution":{"observed_at":"2026-08-12T18:53:07.274581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.255860Z","title":"Three things everyone should know about vision transformers","venue":null,"work_id":"5fb7767a-34de-49bc-b9ac-eb9672a8299c","year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.596522Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:3ad3217549131d4809bfbacbd14ca9a74b109ead97d88e3434781acd97fb92e1","observation_id":"de57dfe7-32a4-4c5c-9eec-136914a07a38","resolution":{"observed_at":"2026-08-12T18:53:07.260161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.243906Z","title":"Simulated annealing","venue":null,"work_id":"399f9085-7185-41b4-8ecb-dd937237b2e7","year":1987},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.600166Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:06159df038ada06ac9382075aeac5fd225419847ab051a3ce620d95adb51b1f6","observation_id":"cc7d886a-db4d-494f-a139-1a2d4d78d077","resolution":{"observed_at":"2026-08-12T18:53:07.247745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.230589Z","title":"Post-deployment adaptation with access to source data via federated learning and source-target remote gradient alignment","venue":null,"work_id":"0a6bc16e-ecfa-495a-b4c2-61a942370ba6","year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.604109Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:f22e5e31540d07c9b3e8208ed186185924ab4ddfa3bb12f2bbe035bf3220a549","observation_id":"e264d366-71d0-4f1c-b16d-3c652d505e2f","resolution":{"observed_at":"2026-08-12T18:53:07.235399Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11636","last_updated":"2024-11-19T16:27:45Z","snapshot_observed_at":"2026-08-12T23:40:59.827407Z","submitted_at":"2024-06-17T15:16:18Z","title":"Feasibility of Federated Learning from Client Databases with Different Brain Diseases and MRI Modalities","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11636","snapshot_observed_at":"2026-08-12T18:53:06.607779Z","title":"Feasibility of federated learning from client databases with different brain diseases and mri modalities","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.607779Z"},"links":{"cited_paper":"/paper/2406.11636","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:dde3c69c2b16d53f0e7c0d0e2f6cb628242c9e87cc8dd739712c41a2778baeaa","observation_id":"0e4a8fef-dae7-4b1c-903f-85326b3b08f7","resolution":{"observed_at":"2026-08-12T18:53:06.607779Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-10T04:53:00.900945Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-12T18:53:06.611584Z","title":"Picking winning tickets before training by preserving gradient flow","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.611584Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:3c7189ed1b3ff94feb5d43371f466f76ac02011a2585e172dccea5fbabf6ec74","observation_id":"0f8c2a7d-36ae-4977-b971-bbb0c7f6a27d","resolution":{"observed_at":"2026-08-12T18:53:06.611584Z","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":"2026-08-12T18:53:06.615279Z","title":"Tackling the objective inconsistency prob- lem in heterogeneous federated optimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.615279Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:682029f7c0b287b78e6a5f6b248faea5ab854fa51c706730a2a186af6d592660","observation_id":"deb005fe-7724-4967-a9e2-bdf40f93f282","resolution":{"observed_at":"2026-08-12T18:53:06.615279Z","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":"2026-08-12T18:53:07.207257Z","title":"Federated dropout—a simple approach for enabling federated learning on resource constrained devices","venue":null,"work_id":"f3fef8af-820b-4045-b503-aa31a6529b43","year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.618704Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:8c6d07cf79398bc16a1909baf20bebc3ce56611b7475456573049af86ff8deed","observation_id":"3009da0a-ea92-4822-b449-f0196de770ee","resolution":{"observed_at":"2026-08-12T18:53:07.212771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11867","last_updated":"2023-06-20T19:58:58Z","snapshot_observed_at":"2026-08-13T11:13:03.155359Z","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":"2026-08-12T18:53:06.622471Z","title":"Personalized federated learning with feature alignment and classifier col- laboration","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.622471Z"},"links":{"cited_paper":"/paper/2306.11867","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:d33bb6c189a19105abdf84f5af24bec7f2588bbdb1509639384949b36173d678","observation_id":"6961220b-cbd0-4ea3-a6e4-6d8f6ef38593","resolution":{"observed_at":"2026-08-12T18:53:06.622471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05687","last_updated":"2021-09-13T03:39:52Z","snapshot_observed_at":"2026-08-05T01:06:28.807438Z","submitted_at":"2021-09-13T03:39:52Z","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.05687","snapshot_observed_at":"2026-08-12T18:53:06.626084Z","title":"Raise a child in large language model: Towards effective and generalizable fine-tuning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.626084Z"},"links":{"cited_paper":"/paper/2109.05687","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:6d46c20787ae1bebca09dc273df9282e39e570fe3e07ef348d16e9a0eb9bce80","observation_id":"c9261576-f3aa-489a-b7cf-02d1f3895c36","resolution":{"observed_at":"2026-08-12T18:53:06.626084Z","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":"2026-08-12T18:53:07.192841Z","title":"Exploring one-shot semi-supervised federated learning with pre-trained diffusion models","venue":null,"work_id":"727f9ccc-1be2-413f-acbd-29e587244434","year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.629929Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:008b4f22626121cadce0b81d2df5e1cb96722d64a1f835bd74f666304e225dd1","observation_id":"010c66fb-36a7-485b-900b-db03c3372c86","resolution":{"observed_at":"2026-08-12T18:53:07.197587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.179534Z","title":"Fedas: Bridg- ing inconsistency in personalized federated learning","venue":null,"work_id":"80cca48f-272b-44ee-8f9b-44bc3bcc7323","year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.633640Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:784f9911848f19b0df451442ddf4662aff76d8861dd78cf646dc430186502297","observation_id":"9d1247b9-712b-46a3-83d4-0c19c1902683","resolution":{"observed_at":"2026-08-12T18:53:07.183702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.11414","last_updated":"2024-03-19T20:04:43Z","snapshot_observed_at":"2026-08-13T11:39:03.474824Z","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":"2026-08-12T18:53:06.637278Z","title":"Federated foundation models: Privacy-preserving and collaborative learning for large models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.637278Z"},"links":{"cited_paper":"/paper/2305.11414","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:4942533175c75c881162ef4d642be88036c7c8863c9878d215fc5be6153cdcd0","observation_id":"e3ee4d4f-c413-46e7-8b5a-0d3671904afc","resolution":{"observed_at":"2026-08-12T18:53:06.637278Z","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":"2026-08-12T18:53:06.640931Z","title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.640931Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:46f31a9ce24ccea038fb1c70d032246143fa41cce7ee54636ffef0715eb37d01","observation_id":"4870dcef-24b3-4bf6-99fd-e67b0f7ad8db","resolution":{"observed_at":"2026-08-12T18:53:06.640931Z","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":"2026-08-12T18:53:07.167236Z","title":"Fedala: Adaptive local aggregation for personalized federated learning","venue":null,"work_id":"143da912-aed5-4b0c-a648-b064fce3bcca","year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.644203Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:cbd9d7c2ffa5bf013113e167a6c971db8300d97be97d8324099dacc1de33fd52","observation_id":"1051b287-414c-4c56-a7c8-bfdb8d045f27","resolution":{"observed_at":"2026-08-12T18:53:07.171167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-12T18:53:07.153708Z","title":"To- wards building the federatedgpt: Federated instruction tun- ing","venue":null,"work_id":"343f86f1-05f9-4129-95b8-d8c39355c0c8","year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.647444Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:f43100a2f24377248a1e423df968367427de246bb5825ae304be155959183398","observation_id":"bec1d67d-9e50-42b3-95e9-d28167e1ddbb","resolution":{"observed_at":"2026-08-12T18:53:07.158158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.15477","last_updated":"2023-10-24T03:08:58Z","snapshot_observed_at":"2026-08-13T05:42:34.582647Z","submitted_at":"2023-10-24T03:08:58Z","title":"CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.15477","snapshot_observed_at":"2026-08-12T18:53:06.650854Z","title":"Crash: Clustering, removing, and sharing enhance fine-tuning without full large language model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.650854Z"},"links":{"cited_paper":"/paper/2310.15477","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:867e71be75a04ba70f4b8ff117699fed38a199c7de074ba3ebe760593d68f729","observation_id":"1683f929-f7d0-4bcc-970c-c50716e43164","resolution":{"observed_at":"2026-08-12T18:53:06.650854Z","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":"2026-08-12T18:53:07.140488Z","title":"Fine-tuning global model via data-free knowledge distillation for non-iid federated learning","venue":null,"work_id":"134fa0ff-efc9-482d-abd5-11819ed06b2f","year":2022},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.654230Z"},"links":{"citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:f0ffa8b5d294d84d877cd67caa32e6fe19686b937192d08bafbde6daed96c2c9","observation_id":"82aa7c1e-e49f-4d0d-a51f-635d0738b31f","resolution":{"observed_at":"2026-08-12T18:53:07.144840Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.08565","last_updated":"2021-03-26T23:13:26Z","snapshot_observed_at":"2026-08-14T07:29:57.336992Z","submitted_at":"2020-12-15T19:30:29Z","title":"Personalized Federated Learning with First Order Model Optimization","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.08565","snapshot_observed_at":"2026-08-12T18:53:06.657448Z","title":"Personalized federated learn- ing with first order model optimization","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.657448Z"},"links":{"cited_paper":"/paper/2012.08565","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:060a47a75f6bf66d356a8c75aca2e7a53534735b3da1dabd1efd1a57068adf85","observation_id":"c307dc5a-427e-492d-92a8-0bf9688ccba6","resolution":{"observed_at":"2026-08-12T18:53:06.657448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.15567","last_updated":"2024-10-21T01:23:34Z","snapshot_observed_at":"2026-08-12T22:19:02.717022Z","submitted_at":"2024-10-21T01:23:34Z","title":"Pruning Foundation Models for High Accuracy without Retraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.15567","snapshot_observed_at":"2026-08-12T18:53:06.660997Z","title":"Pruning foundation mod- els for high accuracy without retraining","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.660997Z"},"links":{"cited_paper":"/paper/2410.15567","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:d63bfc23d832a46e10968971a3131ed0be5d2263aca79db154d12300050ac556","observation_id":"98afd9ea-93dc-4699-aa52-80f8dbe7376f","resolution":{"observed_at":"2026-08-12T18:53:06.660997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.15546","last_updated":"2025-05-04T11:24:55Z","snapshot_observed_at":"2026-08-13T11:08:18.321624Z","submitted_at":"2023-06-27T15:15:55Z","title":"When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.15546","snapshot_observed_at":"2026-08-12T18:53:06.664545Z","title":"When foundation model meets federated learning: Motiva- tions, challenges, and future directions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","version":2},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-12T18:53:06.664545Z"},"links":{"cited_paper":"/paper/2306.15546","citing_paper":"/paper/2411.11912"},"observation_digest":"sha256:ac04294e2f4be1741a9436d000f1c502d4b324844ac5f9f60d3881512d2523c2","observation_id":"b77114eb-d9e4-4d76-8ad8-fb80df2da702","resolution":{"observed_at":"2026-08-12T18:53:06.664545Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.11912","last_updated":"2025-03-30T10:30:03Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T18:47:12.448998Z","submitted_at":"2024-11-17T21:54:57Z","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics"},"reference_resolution":{"displayed":94,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":45,"verified_exact":3,"verified_fuzzy":46},"total_outbound_references":94},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 94 of 94 outbound references and 1 inbound Pith citation observation for arXiv:2411.11912."}