{"as_of":"2026-08-09T06:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4c945d015473335fa313e1eb550500e21cb53b44867bfabbba7f90b6163c3d16","coverage":[{"denominator":63,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":63,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T06:02:19.317608Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T19:21:36.579610Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-05T19:21:36.636161Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"cited_work":{"arxiv_id":"2502.03092","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.03092","snapshot_observed_at":"2026-08-05T19:21:36.636161Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","venue":"cs.LG","work_id":"e62e5e87-8b73-4d3e-83e1-5d1505d2b102","year":2025},"citing_paper":{"arxiv_id":"2508.12670","last_updated":"2025-08-18T07:10:10Z","snapshot_observed_at":"2026-08-09T02:54:48.717037Z","submitted_at":"2025-08-18T07:10:10Z","title":"Discerning and quantifying high frequency activities in EEG under normal and epileptic conditions","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-05T19:21:36.579610Z"},"links":{"cited_paper":"/paper/2502.03092","citing_paper":"/paper/2508.12670"},"observation_digest":"sha256:9c1ca436ba31986929466d6693425c50e422bbeaa897acf8a1d03a1ac2745813","observation_id":"f69c06de-620b-42ed-a305-0f0d9bc6863f","resolution":{"observed_at":"2026-08-05T19:21:36.674749Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.03092/citation-record","integrity":"/paper/2502.03092/integrity","json":"/paper/2502.03092/citation-record.json","paper":"/paper/2502.03092"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T06:02:19.015505Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.015505Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:23a9e308112c4578d25be630dfd7045c16d88e2a002b78a3794ff8aae0da589a","observation_id":"15c6555a-ec33-4fa6-8f31-a39f3f18df60","resolution":{"observed_at":"2026-08-09T06:02:19.015505Z","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":"2026-08-09T06:02:20.327518Z","title":"A review of applications in federated learning,","venue":null,"work_id":"c9d934bc-41ca-4d35-8a04-118e77529ad1","year":2020},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.020895Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:6cf285f0a4458cb90ccd05d1fb1dc5231c1d17020c64571e2116ec05649ca9ce","observation_id":"e1906a9d-2f2a-4798-9696-ad3194f4ee91","resolution":{"observed_at":"2026-08-09T06:02:20.332588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.025630Z","title":"Large scale distributed deep networks,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.025630Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:dd61739c4b0ba6bac9a874dcd0744f6c2e97c1dcb00356fd422467d748b7b6b9","observation_id":"64c0f0ed-89df-4ea9-85d6-6706538213f1","resolution":{"observed_at":"2026-08-09T06:02:19.025630Z","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":"2026-08-09T06:02:20.301910Z","title":"Demystifying parallel and distributed deep learning: An in-depth concurrency analysis,","venue":null,"work_id":"e064a1b6-905a-43cf-b7a4-33ed9ed3dec1","year":2019},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.030549Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:7827357f2a4e7cce583fb45ef17131f51fb99c56c21bde12be33c6d5e9a295fa","observation_id":"33940e02-edc9-48dc-a6ea-b5fd7b1d4aad","resolution":{"observed_at":"2026-08-09T06:02:20.307155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:20.286204Z","title":"Prior: Personalized prior for reactivating the information overlooked in federated learning,","venue":null,"work_id":"f9d7e0e1-2a56-4311-a6ac-7246725b5553","year":2023},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.035062Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:6c0c388e2438bf6bece0d6dbbed486291a2ecb8f2863b27316111c9cedf75c82","observation_id":"ab0bd9f0-17c5-46c3-a825-7b41d3bcf922","resolution":{"observed_at":"2026-08-09T06:02:20.291244Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:20.270571Z","title":"Defta: A plug-and-play peer-to-peer decentralized federated learning framework,","venue":null,"work_id":"c9236820-b372-42be-8b8d-896087461594","year":2024},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.039579Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:9a5157acb213c55ed726da573946c483488e09ba39fdf18ddc33c3b3a57f3ef9","observation_id":"77729d10-a5f5-42fa-9f42-76227660ebdc","resolution":{"observed_at":"2026-08-09T06:02:20.275574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.044586Z","title":"Robust and communication-efficient federated learning from non-iid data,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.044586Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:a24eefe0542e2bfd8ec74914af2b7a32509f05d1e85a92abb0e0bcc746c8ee07","observation_id":"791481c9-7c59-49f3-9fa7-9e62ac16872b","resolution":{"observed_at":"2026-08-09T06:02:19.044586Z","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":"2026-08-09T06:02:20.245339Z","title":"Communication-efficient federated learning with compensated overlap-fedavg,","venue":null,"work_id":"d74af5ad-b74d-403a-9e19-98420b946976","year":2021},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.048741Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:54c106d2d2be25e38110b43b7dd9ab373c661f0ae18e29a4ed1027ebffee1d8e","observation_id":"c045cebb-3fd2-4c3f-abee-ddffd706c641","resolution":{"observed_at":"2026-08-09T06:02:20.250336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.053410Z","title":"Advances and open problems in federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.053410Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:a81297246caf6f119a42877951f675d9bcce1b527f7079599206811246a5a36c","observation_id":"936526ef-2adb-4b82-8a99-b9ff5d5e7c80","resolution":{"observed_at":"2026-08-09T06:02:19.053410Z","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":"2026-08-09T06:02:19.058514Z","title":"Language mod- els are few-shot learners,","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.058514Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:cd778c6ffec3bb8d36b45ff0522b48704b98fe1c90ebd2350cb440a485e3365e","observation_id":"49f9d938-282f-488e-a577-b7e11b2ec9a3","resolution":{"observed_at":"2026-08-09T06:02:19.058514Z","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":"2026-08-09T06:02:20.208808Z","title":"An empirical study of parameter efficient fine-tuning on vision-language pre-train model,","venue":null,"work_id":"b4c2bec2-ee8a-4ec6-974e-1d62a7749f46","year":2024},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.063305Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:5e3adff1d3f65a6a2db2f200de2abab003af5ee91b2bc489ec00d769c01c4c6d","observation_id":"7bafffc4-7293-4da1-b1bb-c48d4d7eab8d","resolution":{"observed_at":"2026-08-09T06:02:20.214034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:20.192704Z","title":"UNITE: multitask learning with sufficient feature for dense prediction,","venue":null,"work_id":"13fa8e04-c287-423e-a599-f0e065c2cec6","year":2024},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.067974Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:8c6c3c25d4fa69cf9a2bf9a66e3d53d62167e8944d4ee79836966186864bb444","observation_id":"545f38d1-6a40-4aaa-8ede-84c913a31467","resolution":{"observed_at":"2026-08-09T06:02:20.197828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.072688Z","title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.072688Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:713ab03a5f6657c869acf27ff9b2cb8e0218b0220f95ad39ab2db691bd7814c3","observation_id":"80afe1fe-ada7-4b0e-8c0e-ce6cd979a284","resolution":{"observed_at":"2026-08-09T06:02:19.072688Z","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":"2026-08-09T06:02:20.167234Z","title":"Towards federated learning at scale: System design,","venue":null,"work_id":"023f4239-ee1b-4b88-b65c-24cd4e271ee5","year":2019},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.077214Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:9cbf94e678478fb7dda3a63936e704b95adc9c1cd4e6be9348d0681cf6fb1794","observation_id":"836c3b76-8d46-4da8-ab34-a7bae951f576","resolution":{"observed_at":"2026-08-09T06:02:20.171497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:20.152497Z","title":"Scalable distributed dnn training using commodity gpu cloud computing,","venue":null,"work_id":"55950226-b58e-4e0b-8919-e27b5a3df88d","year":2015},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.082151Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:22c5a0ba16ea721638499f5060ba4fd6513206ce93becd9ecaa5cedf913ec575","observation_id":"ca46bb68-85b1-4bf5-95c0-4a544a3762e7","resolution":{"observed_at":"2026-08-09T06:02:20.156985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.01887","last_updated":"2020-06-23T03:28:30Z","snapshot_observed_at":"2026-08-07T09:53:59.286406Z","submitted_at":"2017-12-05T19:48:11Z","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.01887","snapshot_observed_at":"2026-08-09T06:02:19.086968Z","title":"Deep gradient compression: Reducing the communication bandwidth for distributed training,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.086968Z"},"links":{"cited_paper":"/paper/1712.01887","citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:25c62d0f5e635c8c46541b65a48bfff4fbca13ba5ef4c5fd76ccea9429bb710c","observation_id":"6ddfb64d-eaf0-4243-93af-79fef21a54a4","resolution":{"observed_at":"2026-08-09T06:02:19.086968Z","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":"2026-08-09T06:02:20.136272Z","title":"Gradient sparsification for communication-efficient distributed optimization,","venue":null,"work_id":"0c355848-6cf7-4c67-be1b-08fa9e8b1d40","year":2018},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.092216Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:874e551d6056c1817a7bb3e861280d932864308054834f5f3a014c5aa32189a8","observation_id":"bc39ec3b-7034-4785-951d-96afa5dbef34","resolution":{"observed_at":"2026-08-09T06:02:20.141718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.097159Z","title":"Qsgd: Communication-efficient sgd via gradient quantization and encoding,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.097159Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:b0176079dcc1e83e56a8e1ceda07980c8b420383fa71d9e2dbfff9144a5c3301","observation_id":"dc619a45-c6ed-4009-8f6f-02994a924cf0","resolution":{"observed_at":"2026-08-09T06:02:19.097159Z","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":"2026-08-09T06:02:20.109623Z","title":"signsgd: Compressed optimisation for non-convex problems,","venue":null,"work_id":"427fa174-2723-4c73-9b8e-847a930fb18e","year":2018},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.101785Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:ae46c72bf1269f252d3ba155fd344639a7e29c9752d3290a93026326fd22f6ea","observation_id":"be5c0f8c-1f5d-4fef-9ee4-a9f69089891b","resolution":{"observed_at":"2026-08-09T06:02:20.114987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:20.093635Z","title":"Error feedback fixes signsgd and other gradient compression schemes,","venue":null,"work_id":"ea0326eb-f0f5-4bed-955f-3b394112b447","year":2019},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.106715Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:b1032f6c4eca4c42972436e75f200961f43c7386a5526a1b64edd5fb49f2c242","observation_id":"cbf80a20-b2f8-47b9-9f35-d646ec39999c","resolution":{"observed_at":"2026-08-09T06:02:20.098803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:20.077594Z","title":"Knowledge distillation: A survey,","venue":null,"work_id":"f4e7d009-f2d9-42bc-a449-4fddab594778","year":2021},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.111675Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:90acbf04c8a31d55a8ce7d89a5ab7384a3a59496c8e80c388cc91c152c23e043","observation_id":"158b911b-1b6b-40ed-b31a-69e20b16289a","resolution":{"observed_at":"2026-08-09T06:02:20.082791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.04489","last_updated":"2020-09-26T17:54:35Z","snapshot_observed_at":"2026-08-07T19:03:13.258257Z","submitted_at":"2020-08-11T02:41:12Z","title":"Federated Learning via Synthetic Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.04489","snapshot_observed_at":"2026-08-09T06:02:19.116812Z","title":"Federated learning via synthetic data,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.116812Z"},"links":{"cited_paper":"/paper/2008.04489","citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:dfc7070faebc6912329b59a3a1d2eec7f9f9051128d2baefa0eaee2a1a53b9af","observation_id":"b2f3a10a-a9d6-4015-b01d-c02076735a68","resolution":{"observed_at":"2026-08-09T06:02:19.116812Z","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":"2026-08-09T06:02:19.122425Z","title":"Communication-efficient federated learning based on compressed sensing,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.122425Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:dd0481e838c3303c92606337d23c1378732adaa3b128278d1736d06716ea7d86","observation_id":"bc109933-2dfc-4b4b-8d4a-4628e326ae8f","resolution":{"observed_at":"2026-08-09T06:02:19.122425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.01273","last_updated":"2022-04-04T06:47:20Z","snapshot_observed_at":"2026-07-06T12:56:14.589413Z","submitted_at":"2022-04-04T06:47:20Z","title":"FedSynth: Gradient Compression via Synthetic Data in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.01273","snapshot_observed_at":"2026-08-09T06:02:19.127231Z","title":"Fedsynth: Gradient compression via synthetic data in federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.127231Z"},"links":{"cited_paper":"/paper/2204.01273","citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:e01a73e5a63beb6bb8c586b258a42a10984cbeaca6b61eaa1b000fda4df57a72","observation_id":"dcd43125-ed41-4abb-b73f-03b4c0a1ee62","resolution":{"observed_at":"2026-08-09T06:02:19.127231Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.05021","last_updated":"2017-07-24T21:47:51Z","snapshot_observed_at":"2026-08-04T09:45:17.283224Z","submitted_at":"2017-04-17T16:32:02Z","title":"Sparse Communication for Distributed Gradient Descent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.05021","snapshot_observed_at":"2026-08-09T06:02:19.132555Z","title":"Sparse communication for distributed gradient descent,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.132555Z"},"links":{"cited_paper":"/paper/1704.05021","citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:fad4de6cab99977543a4b20662465e05a8eed2849b4f39dae0219ea38f98dec4","observation_id":"3f1b672f-64aa-465c-867c-de75addea1fa","resolution":{"observed_at":"2026-08-09T06:02:19.132555Z","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":"2026-08-09T06:02:20.051844Z","title":"z-signfedavg: A unified stochastic sign-based compression for federated learning,","venue":null,"work_id":"530dc1f9-3bf6-4524-82e3-f0f83a8be3af","year":2024},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.138072Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:5676e9f005464656a7b16d539eeef8b89ee2735ad79dd36624d241986695aa2f","observation_id":"6727b842-914c-4514-9dd5-a8f404d6d03c","resolution":{"observed_at":"2026-08-09T06:02:20.056837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.142718Z","title":"Optimization methods for large- scale machine learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.142718Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:3dbaa3ce44976f7ad3a16f1c5670e1a4823e3c9962385ed5ce4e1b49db1259d2","observation_id":"6b227f03-5842-4dda-8377-725a13772a3e","resolution":{"observed_at":"2026-08-09T06:02:19.142718Z","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":"2026-08-09T06:02:19.147593Z","title":"Deep leakage from gradients,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.147593Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:e37ebe901bd8c9b849db27459618eee46698f4914e27ac8be4482471e5eb0f5c","observation_id":"b8c77cd3-9f6e-4536-aa42-21eb9325830c","resolution":{"observed_at":"2026-08-09T06:02:19.147593Z","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":"2026-08-09T06:02:20.015290Z","title":"Sparsified sgd with memory,","venue":null,"work_id":"b508e15f-ab42-49e9-804e-aa126f8a810f","year":2018},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.152326Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:0af031770595cfd898d6d430dd42562989797ef3419d2249f81eecf9fe6e87d7","observation_id":"25e7154a-bd1b-44d6-a900-3a6d339fc1e2","resolution":{"observed_at":"2026-08-09T06:02:20.020225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.999247Z","title":"A theoretical study of dataset distillation,","venue":null,"work_id":"631d55db-9455-4919-9ad2-ac8aca18a160","year":2023},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.156840Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:36ddcaa657b1698e50d50edaece3069824c7697c92236b48eab504cb925e0438","observation_id":"13e6d908-a0b2-465b-9447-20523f334d58","resolution":{"observed_at":"2026-08-09T06:02:20.004148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-09T06:02:19.161709Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.161709Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:48dc1325dab0b0e354a6a1c141af6b1247fe151e41574470be3b3aa54fafa8d0","observation_id":"b13b8eb4-e7ed-4e26-9507-8d535cee2538","resolution":{"observed_at":"2026-08-09T06:02:19.161709Z","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":"2026-08-09T06:02:19.983178Z","title":"The convergence of sparsified gradient methods,","venue":null,"work_id":"d757a4f0-cd70-454c-bb5f-f58cbd1732ec","year":2018},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.167132Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:342b1807f150342d6318ef9d1222bb0180fcc9eebdb75d9b473a00cebbc6fea4","observation_id":"9efe9e5f-0159-4c36-9f61-6a89cd1e6f6e","resolution":{"observed_at":"2026-08-09T06:02:19.988394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.966550Z","title":"Communication- efficient federated learning with single-step synthetic features compres- sor for faster convergence,","venue":null,"work_id":"cb6858b8-ed9b-4d5c-93ac-bdbfb9902689","year":2023},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.172318Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:19b08bfdd372ce40129c77e5375fa3f788413057e131aebc832229174f3fa5f2","observation_id":"401a1c7d-0c3b-48cf-abb1-c3735f4738cb","resolution":{"observed_at":"2026-08-09T06:02:19.971682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.177677Z","title":"Communication-efficient federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.177677Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:2798f392238d27c60bc068faefd5f8e008beb00b6b3fbb82dcbcc0d25ef33767","observation_id":"18b93623-218d-47d5-a143-3be8bf6519ae","resolution":{"observed_at":"2026-08-09T06:02:19.177677Z","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":"2026-08-09T06:02:19.939588Z","title":"Rethinking gradient sparsification as total error minimiza- tion,","venue":null,"work_id":"ffd2835d-9c63-45ef-b9f7-4130cd69147f","year":2021},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.181878Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:00c4ddbf25ef6a5eedfa3608ee0b011954bc1ac17145fc9b4cfd224f9ea3b360","observation_id":"192e44cb-f255-4c8c-948a-8b9b666cf453","resolution":{"observed_at":"2026-08-09T06:02:19.944666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.923528Z","title":"Pre- dicting parameters in deep learning,","venue":null,"work_id":"ef8fbe9e-2b34-48a4-a485-6fdf49fa82ff","year":2013},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.186327Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:88ca85695d0bab2f9cbe4764c3484270e1f2944c4ab49daeac870330d51387a8","observation_id":"df2947ae-22fa-4fb4-99c7-ef78e4b3ebca","resolution":{"observed_at":"2026-08-09T06:02:19.928639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.906384Z","title":"1-bit stochastic gradient descent and its application to data-parallel distributed training of speech dnns,","venue":null,"work_id":"47730214-7bc8-4f6f-bfc4-417972d5e579","year":2014},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.190891Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:d1b8fa5fe665dee51eefa6ae1a599999d5e14209f09a7e152b50e1a34cfb08a8","observation_id":"aca6fbc7-bb61-4c4e-8ad2-dca5eb2ba807","resolution":{"observed_at":"2026-08-09T06:02:19.911760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.780881Z","title":"Communication-efficient federated learning via knowledge distillation,","venue":null,"work_id":"9f1b9bbb-0782-462f-a1ac-d72441aba5c8","year":2022},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.195807Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:d6bc4a3130e079821fb07f0f819ba738014a35e926ab152558c66eaffac49b3b","observation_id":"02ab8997-a6e0-460b-b323-ef4a558baccc","resolution":{"observed_at":"2026-08-09T06:02:19.785426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.766431Z","title":"Communication-efficient federated deep learning with layerwise asynchronous model update and temporally weighted aggregation,","venue":null,"work_id":"2264653c-8789-4938-8e5e-b2803d94c7fc","year":2019},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.200442Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:ddfbeaa8db695dfad1f38c35645b9027eb8beedb7ccee228af9fd1b356829944","observation_id":"f275a4fc-0fd4-4197-9038-f67269e690a1","resolution":{"observed_at":"2026-08-09T06:02:19.771039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.751198Z","title":"A convergence theory for deep learn- ing via over-parameterization,","venue":null,"work_id":"ffadeee9-4945-46fa-99f7-03e99aa08746","year":2019},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.204987Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:f2d680c96fba05d732311f30fef39cff3f67fe5c91c6e5861198f5185509f12a","observation_id":"02abc050-822c-4680-ab1c-2e19c664d7eb","resolution":{"observed_at":"2026-08-09T06:02:19.756001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.734879Z","title":"A systematic review on overfitting control in shallow and deep neural networks,","venue":null,"work_id":"c251d23e-3195-4bdd-8e82-f8e1f535ed27","year":2021},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.209463Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:72ee184030fd00c02e2a7edba62452ca04ab5920f73158ce33a80e6d68637b21","observation_id":"6300ec58-2f8e-4cc7-9c7f-25a01f266f0a","resolution":{"observed_at":"2026-08-09T06:02:19.739880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.02610","last_updated":"2020-01-08T16:45:09Z","snapshot_observed_at":"2026-08-06T23:49:37.129499Z","submitted_at":"2020-01-08T16:45:09Z","title":"iDLG: Improved Deep Leakage from Gradients","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.02610","snapshot_observed_at":"2026-08-09T06:02:19.213773Z","title":"idlg: Improved deep leakage from gradients,","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.213773Z"},"links":{"cited_paper":"/paper/2001.02610","citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:44e0a6419e35eb86f62a7bd84f9c805995b884d4d1a10c8db0c81bf46d5aabcb","observation_id":"367010bd-da7f-44ca-bf99-55597acc56c7","resolution":{"observed_at":"2026-08-09T06:02:19.213773Z","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":"2026-08-09T06:02:19.718679Z","title":"Gradient leakage attacks in federated learning: Research frontiers, taxonomy and future directions,","venue":null,"work_id":"8262ec7b-c97b-4b44-ad80-a1988aed8058","year":2023},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.219401Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:5d14c29c4ed4a6bdd86f862e5e06741b1be92e22a7ad3ce193c4a72fdd5d3d3a","observation_id":"a997ebeb-fdad-4506-95be-8f0063f8b0c6","resolution":{"observed_at":"2026-08-09T06:02:19.723883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.224677Z","title":"The mnist database of handwritten digit images for machine learning research,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.224677Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:c624c1eb77255d0eb3a5fe9182d9c80a112ce45db47fe02a89e61ece31775d50","observation_id":"f1903465-f583-459b-957e-fc45f9eb5e46","resolution":{"observed_at":"2026-08-09T06:02:19.224677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-07-06T05:56:41.814255Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-09T06:02:19.229196Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.229196Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:bd1bae6056a47d4e79a508977a485e7008eeba06b850c0cfb0787b546c8128a0","observation_id":"07ff2d1d-76a6-44f4-98ef-0c914a926827","resolution":{"observed_at":"2026-08-09T06:02:19.229196Z","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":"2026-08-09T06:02:19.234310Z","title":"Emnist: Extending mnist to handwritten letters,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.234310Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:310bf4f5d4b5bf3aea33f0bb1e88a532ed14d4aa3abe3b2006d75d8e7b5283fa","observation_id":"8bc23374-6a7a-4a99-8332-451afb06b29f","resolution":{"observed_at":"2026-08-09T06:02:19.234310Z","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":"2026-08-09T06:02:19.239005Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.239005Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:b472011d232b3415653d5d2255010d8f014dbb3e52630238c57a04e5dd77d046","observation_id":"94847c9b-aeeb-4c7e-95b2-12f4ac0a0c59","resolution":{"observed_at":"2026-08-09T06:02:19.239005Z","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":"2026-08-09T06:02:19.243766Z","title":"Character-level convolutional net- works for text classification,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.243766Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:1e84edd2edbf409e58a4451603063096dd4a6cda7839590a138f8e5bc4b31543","observation_id":"ea2e3162-0435-455e-88c2-117e63795b38","resolution":{"observed_at":"2026-08-09T06:02:19.243766Z","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":"2026-08-09T06:02:19.663874Z","title":"Maximum likelihood estimation of dirichlet distribution parameters,","venue":null,"work_id":"5db7dadd-8e79-42b6-9f40-0fe8d7076b43","year":2005},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.248818Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:3af017432488595d55641d60635ddf56ad2a5d6827f2d4422ade1225734f567e","observation_id":"958c80f8-0934-4491-940c-f032de269c63","resolution":{"observed_at":"2026-08-09T06:02:19.668693Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.253770Z","title":"Tackling the objective inconsistency problem in heterogeneous federated optimiza- tion,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.253770Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:709b8a4f3360b535db0f1226e28a72b0bc580fdbd0e8222088f05b0f77348a4c","observation_id":"7170dec1-4b8d-424a-ab58-758c1a80ef18","resolution":{"observed_at":"2026-08-09T06:02:19.253770Z","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":"2026-08-09T06:02:19.638346Z","title":"Federated learning on non-iid data silos: An experimental study,","venue":null,"work_id":"bcc34d66-977f-4904-9d6e-8acebbacec77","year":2022},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.258897Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:b51e79825779620cd090f8761cb7ebc7f47b34a355e93288ff4bff4fd020b0d6","observation_id":"8d800b55-f7ac-49f8-a658-4cfe938e8bbc","resolution":{"observed_at":"2026-08-09T06:02:19.643303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.264026Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.264026Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:74be5e546eba0068a54477afdc9c580cccfdf9cb3faddb268bb190105a6d7a78","observation_id":"4ac4e0b3-bfbd-43c8-bc72-a51ace22f156","resolution":{"observed_at":"2026-08-09T06:02:19.264026Z","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":"2026-08-09T06:02:19.268907Z","title":"Designing network design spaces,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.268907Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:1f71a61067d9e60cd4f622e277653cd4f9bb26a1c7675a922103fbe9dfc96583","observation_id":"79f58300-6356-4d0b-8a35-859b5ce08f5e","resolution":{"observed_at":"2026-08-09T06:02:19.268907Z","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":"2026-08-09T06:02:19.603064Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift,","venue":null,"work_id":"76748933-48f1-4828-910f-7f19cc70766f","year":2015},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.273868Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:cfd7e95156496f25dd2e1875cd94af12e25c48873c0c4683bb9e4d06738e411d","observation_id":"9d7c34d5-18e5-4136-bb0e-0dcfcc3568d4","resolution":{"observed_at":"2026-08-09T06:02:19.607985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.278671Z","title":"Dropout: a simple way to prevent neural networks from over- fitting,","venue":null,"work_id":null,"year":1929},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.278671Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:428055ad0df5f2f69b2f6a81e5bf326c3971402f32d35d9061df850e58905f53","observation_id":"91301748-0a49-481e-89ef-022d55ba642f","resolution":{"observed_at":"2026-08-09T06:02:19.278671Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.02982","last_updated":"2023-11-09T11:56:46Z","snapshot_observed_at":"2026-07-06T14:38:24.361106Z","submitted_at":"2023-01-08T05:24:12Z","title":"Why Batch Normalization Damage Federated Learning on Non-IID Data?","version":3},"cited_work":{"arxiv_id":"2301.02982","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.02982","snapshot_observed_at":"2026-08-09T06:02:19.374813Z","title":"Why Batch Normalization Damage Federated Learning on Non-IID Data?","venue":"cs.LG","work_id":"52690e7a-611d-4fa2-9a74-669b16b30381","year":2023},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.283292Z"},"links":{"cited_paper":"/paper/2301.02982","citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:f3a4e045d2c2857038985ce4cb3c68cdcdc63490f6fd6bb477dbd13ad835e40c","observation_id":"90966e57-4605-4b35-b502-d9e394cb16b3","resolution":{"observed_at":"2026-08-09T06:02:19.382181Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.288186Z","title":"Personalized federated learning with moreau envelopes,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.288186Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:70e2e0b9df233a35fd87e5efa0e925b331ba7caa101d16dda29eafda20e98d5b","observation_id":"937c0ac2-97ee-4006-8089-a38300759cd4","resolution":{"observed_at":"2026-08-09T06:02:19.288186Z","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":"2026-08-09T06:02:19.566402Z","title":"Federated cinn clustering for accurate clustered federated learning,","venue":null,"work_id":"e36afac0-978c-441c-b22e-d9e5066a488e","year":2024},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.292944Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:ab733963faa75cb583420098950a7105be75d8c2e2f1995fb303287da59de2a9","observation_id":"2464d4cb-119e-4d3a-8fb5-3d57cb7dbd4c","resolution":{"observed_at":"2026-08-09T06:02:19.571115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.550742Z","title":"Step-ahead error feedback for distributed training with compressed gradient,","venue":null,"work_id":"19245998-f930-44c6-a89c-bf15c2da23e3","year":2021},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.297577Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:92ff5e44b2b1623d0991f7cfa3c1c7a555f8de8729346ee6ea667b00797533e2","observation_id":"ff11bd00-46eb-4aba-a029-91c486bf1242","resolution":{"observed_at":"2026-08-09T06:02:19.555675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.535281Z","title":"Detached error feedback for distributed sgd with random sparsification,","venue":null,"work_id":"81e6ab07-2033-4f98-95c2-c81cdeee0dfc","year":2022},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.302319Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:145a28dbc0a3cc6e11855fa0b0505d9bc9947a5d5d0170539442ddc9bc9fab20","observation_id":"5325efdb-1fca-4bf1-b06d-07555f7c2e97","resolution":{"observed_at":"2026-08-09T06:02:19.539719Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.11887","last_updated":"2021-10-24T19:02:03Z","snapshot_observed_at":"2026-07-06T11:41:48.795143Z","submitted_at":"2021-08-26T16:22:49Z","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.11887","snapshot_observed_at":"2026-08-09T06:02:19.306937Z","title":"Federated reinforcement learning: Techniques, applications, and open challenges,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.306937Z"},"links":{"cited_paper":"/paper/2108.11887","citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:b76aed1129695ba39916f6eeaf87d6eff3d8c1a1be9b7c75e6d55e9b732217b3","observation_id":"1e10963c-02c2-4a66-8a54-6f1245d838d7","resolution":{"observed_at":"2026-08-09T06:02:19.306937Z","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":"2026-08-09T06:02:19.521130Z","title":null,"venue":null,"work_id":"c37da411-968d-46c2-919a-8d6d154ea2e8","year":null},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.312671Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:48bf3c017560723a3ee2a8d3ac2568915713277bb174710f7769b562aff7ca8b","observation_id":"99dde919-f6a0-4b64-a445-8cf1aae320c6","resolution":{"observed_at":"2026-08-09T06:02:19.525436Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-09T06:02:19.506115Z","title":null,"venue":null,"work_id":"04fe3482-7db9-4f63-b1a3-f5dbbaeb0b66","year":null},"citing_paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-09T06:02:19.317608Z"},"links":{"citing_paper":"/paper/2502.03092"},"observation_digest":"sha256:68a249524eae3ffaae076b98be476454d81d596fbc624d01ae3692154463de95","observation_id":"098ac7d8-94b0-41ba-9e45-f49a871f1977","resolution":{"observed_at":"2026-08-09T06:02:19.510921Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.03092","last_updated":"2025-02-05T11:31:21Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T05:54:20.763649Z","submitted_at":"2025-02-05T11:31:21Z","title":"E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing"},"reference_resolution":{"displayed":63,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":1,"verified_fuzzy":32},"total_outbound_references":63},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 1 inbound Pith citation observation for arXiv:2502.03092."}