{"as_of":"2026-08-04T13:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fdcf56d8bfff6432abf5a91f8d62b5dbd881feae5310237b5131edecdf252bfa","coverage":[{"denominator":23,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":23,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-19T08:01:36.335624Z","state":"measured"},{"denominator":23,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":23,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.23210/citation-record","integrity":"/paper/2506.23210/integrity","json":"/paper/2506.23210/citation-record.json","paper":"/paper/2506.23210"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":"f459e2ef-7725-4af3-a631-09b61f653af8","year":2017},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:d660214bc5e932a9b9401553abdaf86b8952e91fb771862cac376972be958f62","observation_id":"12837c4d-3fce-4f49-92fe-9121d3b1eca0","resolution":{"observed_at":"2026-05-19T08:02:11.632473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Catastrophic interference in connec- tionist networks: The sequential learning problem","venue":null,"work_id":"13b206f8-e02c-424b-8333-cd9d5eb8e74c","year":1989},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:80ba86d198096b9c18526df0b41aebd4c09581cc6dd91d12514c28740a8849fe","observation_id":"b6c52b71-3a6d-40dc-936b-f0f8a95cdfa9","resolution":{"observed_at":"2026-05-19T08:02:11.622579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Catastrophic forgetting in connectionist networks","venue":null,"work_id":"5315ab0b-159e-4517-88f5-47b654c8bc24","year":1999},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:9ff8ee5d0761633f0845df7625db7f956f57dbf4301e0bb2362f1f9b6938556e","observation_id":"d67279ba-d16a-491a-a614-8c88947ff672","resolution":{"observed_at":"2026-05-19T08:02:11.627797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6211","last_updated":"2015-03-04T01:43:31Z","snapshot_observed_at":"2026-07-06T03:31:33.797310Z","submitted_at":"2013-12-21T06:31:41Z","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","version":3},"cited_work":{"arxiv_id":"1312.6211","doi":"10.48550/arxiv.1312.6211","metadata_source":"pith","pith_arxiv_id":"1312.6211","snapshot_observed_at":"2026-07-10T12:07:03.480400Z","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","venue":"stat.ML","work_id":"2d7055f4-b7d2-4ddb-a9c7-481bd728d360","year":2013},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"cited_paper":"/paper/1312.6211","citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:09279277f21b83e062a80b15917b172716f604d19fe525673a21edc1ba1f7381","observation_id":"8e1d319b-94b4-4b19-b424-aff30a4e6bcc","resolution":{"observed_at":"2026-05-19T08:02:10.192380Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Reducing the hausdorff distance in medical image segmentation with convolutional neural networks","venue":null,"work_id":"5cfd4266-f180-47a6-8a23-b695ba9de10b","year":2019},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:6e377c964ed8e40090a6c8327f82c31293d3abaea859dd60ec5fbd8bec0596a8","observation_id":"57f72ad6-cf1f-4658-9724-4c10105c2e77","resolution":{"observed_at":"2026-05-19T08:02:11.561564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.04306","last_updated":"2021-02-08T16:10:50Z","snapshot_observed_at":"2026-07-06T10:39:29.945712Z","submitted_at":"2021-02-08T16:10:50Z","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","version":1},"cited_work":{"arxiv_id":"2102.04306","doi":"10.48550/arxiv.2102.04306","metadata_source":"pith","pith_arxiv_id":"2102.04306","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","venue":"cs.CV","work_id":"ffa2ac60-2755-4390-9f66-07815aa6cb27","year":2021},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"cited_paper":"/paper/2102.04306","citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:1c385e4210dc5659f2105cf165b4a962016cad69088178fde10b48a1d983185a","observation_id":"76e8b458-9260-43f5-9d17-422e3332a377","resolution":{"observed_at":"2026-05-19T08:02:10.201300Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-12T23:19:36.546402+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T23:19:36.546402+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Unetr: Transformers for 3d medical image segmentation","venue":null,"work_id":"906c0061-945f-4968-a4a1-0d4bb5d03f58","year":2022},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:f9bb7e25492d792e264a8e267a19405feadfe925bbfd32a9a0ba4aa399982b43","observation_id":"64987376-1194-4d55-804e-e3ca5df6154b","resolution":{"observed_at":"2026-05-19T08:02:11.557535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Medical lesion segmentation by combining multimodal images with modality weighted unet","venue":null,"work_id":"90e81e5b-1324-4df9-9bec-718421bc5edc","year":2022},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:e6d936396c18199d8caf3678432b98240b63e6c3518888e5ca1588708b517c56","observation_id":"44b90f03-a8ca-489e-9d7e-d0da7a384744","resolution":{"observed_at":"2026-05-19T08:02:11.553349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1604.00981","last_updated":"2017-03-21T07:44:39Z","snapshot_observed_at":"2026-07-06T04:51:42.448272Z","submitted_at":"2016-04-04T18:40:05Z","title":"Revisiting Distributed Synchronous SGD","version":3},"cited_work":{"arxiv_id":"1604.00981","doi":null,"metadata_source":"pith","pith_arxiv_id":"1604.00981","snapshot_observed_at":"2026-07-03T13:58:21.752441Z","title":"Revisiting Distributed Synchronous SGD","venue":"cs.LG","work_id":"f5e67e6f-5433-4d17-b30a-7343938c7c20","year":2016},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"cited_paper":"/paper/1604.00981","citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:0a13e93ceb31038e34b94bc1c2061a251f732d09bfb8bb358e09e3c4f495e23f","observation_id":"24cf41cc-0809-43f3-bc33-b89ec45db355","resolution":{"observed_at":"2026-05-19T08:02:10.208527Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Federated optimization in heterogeneous networks","venue":null,"work_id":"fe4f57c7-13ef-428c-b5f1-eaeb9d7ea231","year":2020},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:8845b67d93d011d1fc0b94c72a1b40818fa163b8cf0f734154a8e3ec39b319f2","observation_id":"b7427f19-8957-45c0-9624-2cf87b6781d4","resolution":{"observed_at":"2026-05-19T08:02:11.548675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Adaptive federated optimization","venue":null,"work_id":"8d5c3dd8-6e5c-4734-b240-aab41803987e","year":2021},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:a6add13e2845742917904c02b0147a71042d527323e8749d93a3ebcfdc37b455","observation_id":"f2e43a55-8291-45b2-b6f3-8628f48c0cf0","resolution":{"observed_at":"2026-05-19T08:02:11.617736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Feddyn: A dynamic and efficient federated distillation approach on recommender system","venue":null,"work_id":"e3b6b639-d20e-41c2-b6a4-8915750de282","year":2022},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:8250ba80ef5803317968e019d1e6d3c9a521f7015a8f268ba2261b8b15640caa","observation_id":"6670942d-fbc6-4730-a827-7952c732d311","resolution":{"observed_at":"2026-05-19T08:02:11.613796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Bayesian parameter-efficient fine-tuning for overcoming catastrophic forgetting","venue":null,"work_id":"ceceb974-8c3c-484a-bf24-9111489f21a5","year":2024},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:97c9404e5e76575d70c642eda58660dc5786795dde0985fccea645169cc2b15e","observation_id":"1a5da213-500d-4159-97fa-2cc9a50492b0","resolution":{"observed_at":"2026-05-19T08:02:11.609547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"A practical bayesian framework for backpropagation networks","venue":null,"work_id":"b71c9462-0442-4cc6-b3aa-bc1935e041d7","year":1992},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:0f7a42322e3c381fe5f03db61a5731267d8ced7ec118c38e9cbc1acf4bcf4070","observation_id":"93f7eded-7e09-4abb-bacd-053783782800","resolution":{"observed_at":"2026-05-19T08:02:11.604114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Explicit inductive bias for transfer learning with convolutional networks","venue":null,"work_id":"5966c04c-a10d-4819-b6bd-0b627611bb03","year":2018},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:6b95fbf2b5d186dac8122dc059f09641080a6d0a4e9e45306676113e40ad25ee","observation_id":"44611f66-4c0f-43d8-bcd8-bfd3b5e2637c","resolution":{"observed_at":"2026-05-19T08:02:11.598589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Overcoming catastrophic forgetting in neural networks","venue":null,"work_id":"3a3faa43-a001-4af2-90f9-0497a3b3e575","year":2017},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:7a11c43478f0fde40b5ec87ca7d002116c14a5865f242850d145bead8366fc37","observation_id":"71e0e7b7-ba20-4189-b0c9-846421fd6e93","resolution":{"observed_at":"2026-05-19T08:02:11.593760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Optimizing neural networks with kronecker- factored approximate curvature","venue":null,"work_id":"96ea3613-351f-4ca6-9727-a390d8361866","year":2015},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:b5c5a151d24b31517bdc4d8eaf601e4ce02701ade4702046f0ba84a633aa1caa","observation_id":"4b4e0724-ebbc-4edd-84cf-670e173ad334","resolution":{"observed_at":"2026-05-19T08:02:11.589393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Fast approximate natural gradient descent in a kronecker factored eigenbasis","venue":null,"work_id":"652d0a73-d0bd-469f-b15e-b452890c33b0","year":2018},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:68615453b3657a59f1258752945ec4aec29b1e4648c019044bc7bc8a2c593235","observation_id":"2b103d22-4514-4d91-a22a-82328528c7c3","resolution":{"observed_at":"2026-05-19T08:02:11.566651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.14390","last_updated":"2022-03-05T20:30:32Z","snapshot_observed_at":"2026-07-06T09:42:35.058716Z","submitted_at":"2020-07-28T17:59:07Z","title":"Flower: A Friendly Federated Learning Research Framework","version":5},"cited_work":{"arxiv_id":"2007.14390","doi":"10.48550/arxiv.2007.14390","metadata_source":"pith","pith_arxiv_id":"2007.14390","snapshot_observed_at":"2026-07-11T03:07:50.163620Z","title":"Flower: A Friendly Federated Learning Research Framework","venue":"cs.LG","work_id":"396ea1bf-02a2-41cf-8454-93dff73af450","year":2020},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"cited_paper":"/paper/2007.14390","citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:827f8239de634e85379fa5cfccca099b62cfeea6611d4ad754289f9d2c19866c","observation_id":"30215ff1-949d-4889-8619-232c834bce83","resolution":{"observed_at":"2026-05-22T14:07:23.126952Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Mnist handwritten digit database","venue":null,"work_id":"279a121d-df33-4ee4-95a5-5f45e16286f8","year":2010},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:cf43c65d6c46c378f8aac8be1be4b5867c86a9a4d309e2dad27477028afad143","observation_id":"12a4d6a8-6ed3-40df-8ea8-830d86924e9c","resolution":{"observed_at":"2026-05-19T08:02:11.583988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Searching for mobilenetv3","venue":null,"work_id":"c636d595-680a-40f4-819d-4e702d0a2e45","year":2019},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:b8ca6c61992e70ff850453c4fcdb986fae567eb6d11414e25707b772940e267d","observation_id":"8b592668-8d8b-417d-89a2-8092b7219265","resolution":{"observed_at":"2026-05-19T08:02:11.579272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Federated Tumor Segmentation (FeTS) 2022 Dataset","venue":null,"work_id":"7767b03d-8a32-4c7b-bd0f-1a904d29b0c0","year":2022},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:85ca6879b0939c72a6df8f11d1142a17412a8f82c35d0736175b14c72064aa26","observation_id":"83ddf7bd-7b49-4aea-afed-7910691598d9","resolution":{"observed_at":"2026-05-19T08:02:11.575443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Ridge-based vessel segmentation in color images of the retina","venue":null,"work_id":"fe63b0ae-1559-4da2-9b84-2491bcfb4f4d","year":2004},"citing_paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning","version":5},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-19T08:01:36.335624Z"},"links":{"citing_paper":"/paper/2506.23210"},"observation_digest":"sha256:2865435f0212f73318a620cca6780e2cfa4667c94f453da043d613d7735683e9","observation_id":"79b84471-a26c-4fd8-85c9-daa8f15a640f","resolution":{"observed_at":"2026-05-19T08:02:11.571494Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.23210","last_updated":"2026-04-25T02:20:43Z","latest_version":5,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T21:49:18.028734Z","submitted_at":"2025-06-29T12:41:11Z","title":"FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning"},"reference_resolution":{"displayed":23,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":4,"verified_fuzzy":19},"total_outbound_references":23},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2506.23210."}