{"as_of":"2026-08-19T23:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:966a2038ad5e5788b285bf6656af19676b91df2c316b5cad8b8e22621afdd620","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T00:03:29.800883Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T13:40:35.795292Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T04:47:37.956236Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"cited_work":{"arxiv_id":"2508.04470","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.04470","snapshot_observed_at":"2026-07-03T04:47:37.956236Z","title":null,"venue":null,"work_id":"378361a2-3a83-4b9b-9c13-6e893697d0f0","year":2025},"citing_paper":{"arxiv_id":"2606.11480","last_updated":"2026-06-09T22:14:16Z","snapshot_observed_at":"2026-08-17T15:53:43.745743Z","submitted_at":"2026-06-09T22:14:16Z","title":"Accurate and Resource-Efficient Federated Continual Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-06-27T13:40:35.795292Z"},"links":{"cited_paper":"/paper/2508.04470","citing_paper":"/paper/2606.11480"},"observation_digest":"sha256:7b2cca913780b99cb4ea13c7b3fd70665c171218220ba7a32255df99b0bdf2bc","observation_id":"98e11c00-8351-455e-ad39-5a9f3f024033","resolution":{"observed_at":"2026-07-03T04:47:37.957769Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2508.04470/citation-record","integrity":"/paper/2508.04470/integrity","json":"/paper/2508.04470/citation-record.json","paper":"/paper/2508.04470"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T00:03:38.209799Z","title":"FairFed: Improving fairness and efficiency of contribution evaluation in federated learning via cooperative shapley value,","venue":null,"work_id":"3a8c0a1e-7efa-425c-8b53-a0fca7dc93d3","year":2024},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:26.222764Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:e8a08b869e63fbb64df997e4b39b8d14585eae126f99d55f686338ac24084c80","observation_id":"a5fe8be6-4e0a-4699-8413-a8866af32816","resolution":{"observed_at":"2026-08-06T00:03:38.360834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:26.292086Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:26.292086Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:e147b26b6047adde059b4f4db4e38613da653e9b88f03a41855a19fa31fa03f8","observation_id":"1b91f719-186c-49a1-be7d-27b1fef03707","resolution":{"observed_at":"2026-08-06T00:03:26.292086Z","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":"2026-08-06T00:03:26.357013Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:26.357013Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:a0ec7bb01223f564f09b90ec4ccc7b8a3aa858cd8ce3b775629ad129d6a33101","observation_id":"cf62e7d5-94a4-4630-9285-acdeaaa661d8","resolution":{"observed_at":"2026-08-06T00:03:26.357013Z","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":"2026-08-06T00:03:37.825983Z","title":"Towards personalized federated learning,","venue":null,"work_id":"003a370a-e4cc-4b27-b942-81d32a36b7a2","year":2022},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:26.458142Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:c43d34c51d51f9bf3e2cf29fa1ddbd7cda4b7a7e7b79be79f70c85a5d4146d1b","observation_id":"e33bc528-bcb8-4931-97d2-92a33a8c900b","resolution":{"observed_at":"2026-08-06T00:03:38.002313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:37.644409Z","title":"Ditto: Fair and robust federated learning through personalization,","venue":null,"work_id":"64f7a142-41cc-440b-bad2-6149f944cf90","year":2021},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:26.518385Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:633b61af7e94e03c457fff709caea5a0663dfa1dcb54b00a62f7fb8cc576869d","observation_id":"1e6e507e-023e-4173-97f8-1e2acf5382f3","resolution":{"observed_at":"2026-08-06T00:03:37.731358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:37.353814Z","title":"FedALA: Adaptive local aggregation for personalized federated learn- ing,","venue":null,"work_id":"55f924a9-1128-49db-bb09-bca3c08bc1ce","year":2023},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:26.612367Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:4b1c8955419ffcff59d36b78a7ab660ace1a8062a0c9c7e3c30e0155b9320c12","observation_id":"d5d679a4-4913-44f3-b481-5f3cd9dfd2b3","resolution":{"observed_at":"2026-08-06T00:03:37.490000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:37.088647Z","title":"FedLFP: Communication-efficient personalized federated learning on non-iid data in mobile edge computing environments,","venue":null,"work_id":"09360bbd-eda9-4b54-a448-df7aa48da08e","year":2025},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:26.703186Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:0b7885e743f3c54bfeccac863738f76bd68aa7667cd0aa6b5bd55f622c78d6cc","observation_id":"c76e2a05-e5d3-48bf-af39-a604525edf82","resolution":{"observed_at":"2026-08-06T00:03:37.237215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:36.702782Z","title":"Personalized federated learning with model-contrastive learning for multi-modal user modeling in human-centric metaverse,","venue":null,"work_id":"1c609699-ac78-4bf1-97a9-40274842fe33","year":2024},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:26.803782Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:0cb91ad7e04a66b27a80dbd75a9e2cc64999627702cd91c16a3ee9373c37bf6d","observation_id":"9b3666fb-e2db-4b0e-ab06-75a7c3d23616","resolution":{"observed_at":"2026-08-06T00:03:36.915788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:36.423123Z","title":"Multi-level person- alized federated learning on heterogeneous and long-tailed data,","venue":null,"work_id":"4e985c18-f557-4c63-9f0c-74e26dcf352c","year":2024},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:26.936941Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:47a6f243906348abba2194319f7ccb97c94b614143a9455a5db388d8e2a8f3c7","observation_id":"e07bc8a4-4c09-4a34-b8ef-aa83271757f1","resolution":{"observed_at":"2026-08-06T00:03:36.570770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:36.177223Z","title":"Federated learning while providing model as a service: Joint training and inference optimization,","venue":null,"work_id":"f1824b5c-020c-4a0f-9e3a-462ceb3cb71b","year":2024},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:27.023533Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:054dd08a4f89ab95b8945f69b8a8657784cc28bb12e8170dedabb99560cb7313","observation_id":"abf207dd-49a6-40a1-a5d0-f0094aaafba1","resolution":{"observed_at":"2026-08-06T00:03:36.299774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:35.957685Z","title":"CPDZ: A credibility-aware and privacy-preserving data collection scheme with zero-trust in next-generation crowdsensing networks,","venue":null,"work_id":"7ed3b3c5-2124-40f4-a8ed-971b77073f9d","year":2025},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:27.135536Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:41b327b02ea3a300869925fe0d9182a2a0e94d23fe7fbf49438b5ccc87bfd7ca","observation_id":"2c1e7142-28fc-4f37-94cd-00331f7c3d5d","resolution":{"observed_at":"2026-08-06T00:03:36.075472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:35.724219Z","title":"QLP-DCS: A quality-aware, low-cost, and privacy- preserving data collection service for mobile crowd sensing,","venue":null,"work_id":"114598e2-7de4-4109-bbaa-077f4e15e75b","year":2025},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:27.251789Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:87854d1f7c08abeb256b0e495da4d2f921520ef9d84d74ae4a622c15c0416ed0","observation_id":"e840d91d-9f7b-4684-9345-e18edbaf1a4b","resolution":{"observed_at":"2026-08-06T00:03:35.834000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:35.471816Z","title":"RMDF-CV: A reliable multi-source data fusion scheme with cross validation for quality service construction in mobile crowd sensing,","venue":null,"work_id":"eba4eaa6-3166-46b0-9f6d-68cba83e8372","year":2025},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:27.391707Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:f4917557f38a3880f6f047c447a391e58b74eb86570dc84b5defc5df08875a0a","observation_id":"8f8619c9-923a-4cf5-9037-99279df9cb78","resolution":{"observed_at":"2026-08-06T00:03:35.586885Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:35.266227Z","title":"Pseudoinverse learning algo- rithm for feedforward neural networks,","venue":null,"work_id":"4bf2192f-4c0b-4816-bb9f-6bd8b013cbb1","year":2001},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:27.471685Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:be5fd60067885a7d68a647338ec793809bafa82596846e5fe9e434663d4415b9","observation_id":"77d0d1a7-3dbc-40ee-b6ae-13f12a601150","resolution":{"observed_at":"2026-08-06T00:03:35.356267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:35.067283Z","title":"GKEAL: Gaussian kernel embedded analytic learning for few-shot class incremental task,","venue":null,"work_id":"d4203339-d56a-4cc5-b0dc-f27925d7d179","year":2023},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:27.573745Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:6fa3b564cc19d70b8c15d46a5e0d37061b3bae7e093911c2ba25264ec7033606","observation_id":"bdec1553-1b17-4b46-90b3-8ae1aed94f51","resolution":{"observed_at":"2026-08-06T00:03:35.156718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:34.810543Z","title":"ACIL: Analytic class-incremental learning with absolute memorization and privacy protection,","venue":null,"work_id":"7f841f6d-2829-4ae6-a105-7e4a79e64172","year":2022},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:27.658177Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:252adab61654c07b52bbd5be1e78ecac1393b769a4436241c7571a3191cc7369","observation_id":"fc3f3b9b-897c-433a-9cd3-ac58e1de2258","resolution":{"observed_at":"2026-08-06T00:03:34.937716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:34.596793Z","title":"A progressive stacking pseudoinverse learning framework via active learning in random sub- spaces,","venue":null,"work_id":"dd84722b-e98a-4673-97ae-d198227aa0bc","year":2024},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:27.769200Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:e314b177104dce46fc1b8102dd126c9c7ddd80124973e1d778f748092d7ec3e8","observation_id":"ae6a9f24-c844-473c-bcf2-df1694fe4efa","resolution":{"observed_at":"2026-08-06T00:03:34.706376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:34.350645Z","title":"Bayesian pseudoinverse learners: From uncertainty to deterministic learning,","venue":null,"work_id":"29926e31-9240-4db4-a75f-bcb2cc1f7636","year":2022},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:27.843969Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:a1a640fbf6441abc1aad70b58e6a483ffa90decdbdfdb476dd2026900fe471ca","observation_id":"aec51504-a289-4d8a-a666-e19c634a81b3","resolution":{"observed_at":"2026-08-06T00:03:34.453884Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:34.130292Z","title":"Universal approximation using radial-basis- function networks,","venue":null,"work_id":"a8b42c6f-8e79-4a07-8ef4-04e0f1231f96","year":1991},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:27.939274Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:5218554d4ead794edd52a187662796e31652de4488ebb22ea5c499fa28ddd5c4","observation_id":"9075756f-232b-4042-ab90-c25ec81fc56b","resolution":{"observed_at":"2026-08-06T00:03:34.222402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:33.872521Z","title":"Learning from the kernel and the range space,","venue":null,"work_id":"f975030d-94ba-40f8-bc26-a3d4809d9d3c","year":2018},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:28.047501Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:c671c2ea45eb01aa186ad685883b3c6541564b3444bea94c86f4c7fe50c0d0cc","observation_id":"70c0762b-e66f-413a-9127-5eb136b2cb60","resolution":{"observed_at":"2026-08-06T00:03:34.008326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:33.647962Z","title":"Noniterative deep learning: Incorporating restricted boltzmann machine into multilayer random weight neural networks,","venue":null,"work_id":"9583dd12-af05-41f0-876c-26a33278f3d5","year":2017},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:28.163901Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:ea1c3ff546f76369dfe3fc1aafd30c32916a627327dc553186821cd11e4c7380","observation_id":"e0e1ea2b-a9a9-451d-8a20-130cca45e34b","resolution":{"observed_at":"2026-08-06T00:03:33.771127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:33.469190Z","title":"An analytic formulation of convolutional neural network learning for pattern recognition,","venue":null,"work_id":"d8cde495-267a-4929-9e76-1836c34159cb","year":2025},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:28.300981Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:03b3c4e34e947f2d1355974ea37fd646899d83dc79697523db4379ad5099bd46","observation_id":"6e4faa46-c819-422d-ad28-9a5e82053d68","resolution":{"observed_at":"2026-08-06T00:03:33.544219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:33.234492Z","title":"Densepilae: a feature reuse pseudoinverse learning algorithm for deep stacked autoencoder,","venue":null,"work_id":"a68c98b0-8f9c-4d0b-a2f7-70bb165f3569","year":2022},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:28.399173Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:d73cc1c4f44c29ad835f6d153004bedf35c74d0aa5f03a126ebe555b73b79701","observation_id":"679246ee-f8de-42b9-933e-18ad1ca0054b","resolution":{"observed_at":"2026-08-06T00:03:33.358183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:33.016097Z","title":"Blockwise recursive moore–penrose inverse for network learning,","venue":null,"work_id":"7c55c750-e549-4203-819d-8f5db6ca98e2","year":2021},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:28.479004Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:5f22d37239afad22334c6369abb3d1d8d2bd31104e5ad7618edb1b1833e30316","observation_id":"c4ea7005-b330-4371-ac32-2dd7676dca81","resolution":{"observed_at":"2026-08-06T00:03:33.140795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:32.809048Z","title":"CALM: A ubiquitous crowdsourced analytic learning mechanism for continual service construction with data privacy preservation,","venue":null,"work_id":"f83d91f6-afd5-4c9c-a3f8-eb663f42d767","year":2025},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:28.565316Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:27087a5629aa1cd98bf8ced71f99269ccfd5b3d66bbd30dcfb71ce8326b3bc94","observation_id":"34ecb4da-8420-478f-947d-ab56ab6a770e","resolution":{"observed_at":"2026-08-06T00:03:32.893767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:32.601637Z","title":"AFL: A single-round analytic approach for federated learing with pre-trained models,","venue":null,"work_id":"5f538161-e79e-4074-9884-bc2d3498b2cf","year":2025},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:28.623642Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:1a7ce00866eb1bee8679a80ddb41d8af9ecf3d3c87508574bd99263b6c7f4e1e","observation_id":"262a31d4-2a75-453a-be28-c8549df513c4","resolution":{"observed_at":"2026-08-06T00:03:32.714605Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:32.387868Z","title":"Locality sensitive sparse encoding for learning world models online,","venue":null,"work_id":"7ca4f15e-f581-4298-9267-61eeda803e6d","year":2024},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:28.677360Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:e7a47c4e90947dddf650ffb2b5de70d9a04372c63be7f6630973e8ecbcdb0e4e","observation_id":"ea68d8b0-0a0f-4c84-a6b3-bd5e9ea052c9","resolution":{"observed_at":"2026-08-06T00:03:32.480177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:32.148634Z","title":"Masked au- toencoders are scalable vision learners,","venue":null,"work_id":"da0371c9-9c6c-4892-9f2b-7e2e0b44de4a","year":2022},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:28.767498Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:2e8a09fb54157f820761a61d0778e8c1476ff2db34581564a3a89acc5cf6d920","observation_id":"12920f81-539a-4faa-a9b9-de2198ebfbcb","resolution":{"observed_at":"2026-08-06T00:03:32.271336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:31.919739Z","title":"Where to begin? on the impact of pre-training and initialization in federated learning,","venue":null,"work_id":"2f8f6eab-e23f-4ea1-9d8c-b24bce950e40","year":2023},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:28.851664Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:a9dc030e4cef86c7380ac8103a7563ec3908ef22ad256cf631f8023cffcf9f46","observation_id":"1d1ab36c-7b2e-4789-ab83-790af477a4e7","resolution":{"observed_at":"2026-08-06T00:03:32.027821Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:31.715400Z","title":"On the importance and applicability of pre-training for federated learning,","venue":null,"work_id":"9f1594d8-cb42-472b-b1dd-d0cebb337d4b","year":2023},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:28.977683Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:3a932d0705485038b13b6a659666336e0411600381250a7b642d1a4b1b7ee217","observation_id":"e9033b7d-1f19-4699-8bf3-80ec0913a7cb","resolution":{"observed_at":"2026-08-06T00:03:31.815545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:31.526647Z","title":"FedBERT: When federated learning meets pre-training,","venue":null,"work_id":"c91df39f-1b8d-4cb2-af2d-3d12f98fafe4","year":2022},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:29.046029Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:a8b8b223938b900d45088d760457f1f52cf2b5e1ad8cea3c2ee24fb73ad8e3cf","observation_id":"659f6feb-f7f2-46b0-90dc-e64033d8a079","resolution":{"observed_at":"2026-08-06T00:03:31.612193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:31.296430Z","title":"AugFL: Aug- menting federated learning with pretrained models,","venue":null,"work_id":"493bc902-2146-47a9-a66b-1125d393cf8e","year":2025},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:29.110796Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:55f5eb39e6ff9a07ecc2ce3c182e119c355dd4a5673382e3da85b90cd80f8144","observation_id":"9665840f-1cfc-497e-a2ff-72390593a294","resolution":{"observed_at":"2026-08-06T00:03:31.436540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:31.107841Z","title":"FedDAT: An approach for foundation model finetuning in multi-modal heterogeneous federated learning,","venue":null,"work_id":"2ae63c11-2fb7-469b-9f01-53d8d0aaa293","year":2024},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:29.221914Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:e4339f71538508557c5964548bf19fa883c0c10b1ed17de590a831b48d00b88f","observation_id":"ce77ebf3-677a-4504-9adc-ad96c5dd895d","resolution":{"observed_at":"2026-08-06T00:03:31.188737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:30.913582Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":"82ccccff-395f-4a59-9b24-f02f54b685d6","year":2009},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:29.330659Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:96a79ffcda455fd1e503bcc7da175f67768dcc0b7037d83437995cd4c1b87e35","observation_id":"6b41b684-aded-41bb-852a-e1c2f2779c1e","resolution":{"observed_at":"2026-08-06T00:03:31.003609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:29.415884Z","title":"The many faces of robustness: A critical analysis of out-of-distribution generalization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:29.415884Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:775007570c87f016e42d72832368c41b576586723239219f7056f90037b57006","observation_id":"6a7d327b-b9e8-44da-b946-90ddd1a99f23","resolution":{"observed_at":"2026-08-06T00:03:29.415884Z","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":"2026-08-06T00:03:30.723797Z","title":"Eliminating domain bias for federated learning in representa- tion space,","venue":null,"work_id":"2cadf451-f2a9-4fc8-950f-5ea80f9cdd23","year":2023},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:29.494588Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:a0078661374861189c07b23815807b727d25f88338d2e0370386ff3ff9830038","observation_id":"6cc8d20d-6217-4c9a-bc99-39a04a225a25","resolution":{"observed_at":"2026-08-06T00:03:30.833929Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:30.524956Z","title":"FedAS: Bridging inconsistency in personalized federated learning,","venue":null,"work_id":"84480a3d-60cd-40b6-a7df-7764f3c37557","year":2024},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:29.578631Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:f32060923ad4e8490f1cefc1d2675637417352b658d4b6e39379a10340ee0cb0","observation_id":"0a0c64b9-1403-4abf-a70b-ca372ac1f7d6","resolution":{"observed_at":"2026-08-06T00:03:30.634289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:30.351266Z","title":"Federated learning from pre-trained models: A contrastive learning approach,","venue":null,"work_id":"b1d92cb1-f550-4e96-9339-4ffa7b0d7ce0","year":2022},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:29.657266Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:f3fb1e5ede1d01604b64af4ef9b1b8b997f2829ed40d978de99f3fb9e7f0fbbd","observation_id":"2eba1061-6e5b-4dae-b608-f8b119739287","resolution":{"observed_at":"2026-08-06T00:03:30.449841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:30.116142Z","title":"FedSelect: Personalized federated learning with customized selection of parameters for fine-tuning,","venue":null,"work_id":"7c777db6-49de-49e2-97e8-4229da0c3732","year":2024},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:29.721955Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:f848843e996cac83fdbbb9806605f4223218fb28e39a374561ba2d7a5e51a50a","observation_id":"829876da-4df7-43fb-bcd8-35b74b20a488","resolution":{"observed_at":"2026-08-06T00:03:30.247904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T00:03:29.944151Z","title":null,"venue":null,"work_id":"9f48cfaa-d41e-42cc-9f8b-bd821de2dc12","year":2013},"citing_paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions","version":1},"reference_index":2008,"source":"pdf_text","source_observed_at":"2026-08-06T00:03:29.800883Z"},"links":{"citing_paper":"/paper/2508.04470"},"observation_digest":"sha256:27bac1eb950fef308ccc187d1fa684f8ca59f743d630a033eefd883ebf64c13c","observation_id":"ddb5b7ae-4667-404e-acdc-e599fe56936b","resolution":{"observed_at":"2026-08-06T00:03:30.030354Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.04470","last_updated":"2025-08-06T14:15:57Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T04:49:10.357137Z","submitted_at":"2025-08-06T14:15:57Z","title":"FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":36},"total_outbound_references":40},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 1 inbound Pith citation observation for arXiv:2508.04470."}