{"as_of":"2026-08-16T01:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:482f90c60971caee0d841276cbc186eb2cd0bbdf52da51f80b62f3a48d2e7f5b","coverage":[{"denominator":88,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":88,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T11:45:59.210161Z","state":"measured"},{"denominator":88,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":88,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2507.22488/citation-record","integrity":"/paper/2507.22488/integrity","json":"/paper/2507.22488/citation-record.json","paper":"/paper/2507.22488"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T11:45:58.794350Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.794350Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:468132def0614f8a826e01c2c08f3ee264f0a42dab6256b1b658e29ac5c22656","observation_id":"422c5dee-27f4-4e1d-9003-0e70a570cd86","resolution":{"observed_at":"2026-08-06T11:45:58.794350Z","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":"2026-08-06T11:45:58.798890Z","title":"Federated learning for privacy- preserving ai,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.798890Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:255203363dd6d9e432a76c107f36e3c20ae6198746002ac078199187f0373697","observation_id":"281543f7-ce4d-4bec-8c4b-4b2113b8d22d","resolution":{"observed_at":"2026-08-06T11:45:58.798890Z","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":"2026-08-06T11:45:58.803005Z","title":"Federated machine learning: Concept and applications,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.803005Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:4b76cfc4209861fc68c6ca098fe603625b97221e3cf085ca637547b844f91cd0","observation_id":"094b823d-405b-44ea-aa7d-479ad873ceba","resolution":{"observed_at":"2026-08-06T11:45:58.803005Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.12814","last_updated":"2023-09-28T01:29:46Z","snapshot_observed_at":"2026-08-13T13:36:10.204208Z","submitted_at":"2022-11-23T10:00:06Z","title":"Vertical Federated Learning: Concepts, Advances and Challenges","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.12814","snapshot_observed_at":"2026-08-06T11:45:58.807763Z","title":"Vertical federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.807763Z"},"links":{"cited_paper":"/paper/2211.12814","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:cd3d2203a7611923241b38b5eb79849036d5497fbb3008e861dc50048b76d5fe","observation_id":"9e4da73f-9bf0-40c9-8da5-9c4cb997bf7e","resolution":{"observed_at":"2026-08-06T11:45:58.807763Z","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":"2026-08-06T11:45:58.812731Z","title":"Federated learning in mobile edge networks: A comprehensive survey,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.812731Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:501df57cb75ae0e8079a8f2ffa255064a7ff424c0ff45cdafcb98c29c7b1877d","observation_id":"c9b6fb58-1d2f-4c83-b88a-fa07b4d80963","resolution":{"observed_at":"2026-08-06T11:45:58.812731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.16270","last_updated":"2023-03-30T00:42:31Z","snapshot_observed_at":"2026-08-13T12:14:33.413329Z","submitted_at":"2023-03-28T19:30:23Z","title":"Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.16270","snapshot_observed_at":"2026-08-06T11:45:58.816502Z","title":"Communication-efficient vertical federated learning with limited overlapping samples,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.816502Z"},"links":{"cited_paper":"/paper/2303.16270","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:0f2313fa4faa09d3380d64eaf8ba877dd7dee29f809070d715a8ebba3a2acb24","observation_id":"c037080a-fd27-44f7-ab5f-f0a18611a71e","resolution":{"observed_at":"2026-08-06T11:45:58.816502Z","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":"2026-08-06T11:45:58.820702Z","title":"Fedcvt: Semi-supervised vertical federated learning with cross-view training,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.820702Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:043cc3475b8dc4809af70874bbf608fd5c2d79fe2c49c444d2dd1f9494a10ed6","observation_id":"733d0272-7c7c-40be-8293-2da4b44a3b74","resolution":{"observed_at":"2026-08-06T11:45:58.820702Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.04309","last_updated":"2024-08-05T12:58:37Z","snapshot_observed_at":"2026-08-12T07:53:52.860990Z","submitted_at":"2022-02-09T06:56:41Z","title":"Vertical Federated Learning: Challenges, Methodologies and Experiments","version":2},"cited_work":{"arxiv_id":"2202.04309","doi":null,"metadata_source":"pith","pith_arxiv_id":"2202.04309","snapshot_observed_at":"2026-08-06T11:46:00.209310Z","title":"Vertical Federated Learning: Challenges, Methodologies and Experiments","venue":"cs.LG","work_id":"7b482082-e806-4ec8-acb0-b08d0ca69f79","year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.824795Z"},"links":{"cited_paper":"/paper/2202.04309","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:570a150d33c89141bc659e8c39445c7af183897b9cfa036f73693955b05312f8","observation_id":"c86e6f2b-9c3d-4ac7-9ba4-89b39406ea34","resolution":{"observed_at":"2026-08-06T11:46:00.275809Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:45:58.828602Z","title":"Semi-supervised federated heterogeneous transfer learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.828602Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:ff581eca3b390c19b7423ac7876c95acefb851a5044a0d5fbcdd91f61f22e9b4","observation_id":"24f4df2a-6237-488e-8aad-f978fc1c8f81","resolution":{"observed_at":"2026-08-06T11:45:58.828602Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.08934","last_updated":"2023-06-08T10:05:43Z","snapshot_observed_at":"2026-08-13T14:43:12.743615Z","submitted_at":"2022-08-18T16:15:15Z","title":"A Hybrid Self-Supervised Learning Framework for Vertical Federated Learning","version":2},"cited_work":{"arxiv_id":"2208.08934","doi":null,"metadata_source":"pith","pith_arxiv_id":"2208.08934","snapshot_observed_at":"2026-08-06T11:45:59.912820Z","title":"A Hybrid Self-Supervised Learning Framework for Vertical Federated Learning","venue":"cs.LG","work_id":"29fd7c6b-8f31-4852-8b9f-36af2548a1a1","year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.832411Z"},"links":{"cited_paper":"/paper/2208.08934","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:a247329dff94d3ab490a1d3f09c48fb6a9aa6885c72d38a2b0bb4470fd25a07c","observation_id":"4f8e1d83-22db-42a6-8836-c8c805e381b1","resolution":{"observed_at":"2026-08-06T11:46:00.052989Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.11896","last_updated":"2021-02-18T02:23:50Z","snapshot_observed_at":"2026-08-09T23:16:03.077290Z","submitted_at":"2021-01-28T09:57:30Z","title":"Self-supervised Cross-silo Federated Neural Architecture Search","version":2},"cited_work":{"arxiv_id":"2101.11896","doi":null,"metadata_source":"pith","pith_arxiv_id":"2101.11896","snapshot_observed_at":"2026-08-06T11:45:59.679083Z","title":"Self-supervised Cross-silo Federated Neural Architecture Search","venue":"cs.LG","work_id":"9f1d233e-eba6-4344-8b77-7ee50848c4eb","year":2021},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.836682Z"},"links":{"cited_paper":"/paper/2101.11896","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:b2277bd835bac414b25c9ef466f29bc4b88bf54444f11b8ef974676e14747936","observation_id":"48408368-0131-4342-8c62-a10bfbc7e27f","resolution":{"observed_at":"2026-08-06T11:45:59.766579Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:45:58.840915Z","title":"Self-supervised vertical feder- ated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.840915Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:2c13813ab614dc0d47236ed2f31b8bde5a0be045421322df3533bdd7801605b0","observation_id":"1babcd15-d9ed-487e-b75e-dbef93618381","resolution":{"observed_at":"2026-08-06T11:45:58.840915Z","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":"2026-08-06T11:45:58.845009Z","title":"Vertical semi- federated learning for efficient online advertising,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.845009Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:7503805ffc8fe608a6636eebbe9a1eb5490e0054c98591e1928c1c1a694669d5","observation_id":"2f1d9969-731a-4cf6-8ec4-f5b102697006","resolution":{"observed_at":"2026-08-06T11:45:58.845009Z","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":"2026-08-06T11:45:58.848072Z","title":"Multi-view federated learning with data collaboration,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.848072Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:e3caac9db39fad927c94d19857840963ece23da820b82e47052ceb407977399c","observation_id":"2307e8f4-8691-4774-9302-748fcb666a7e","resolution":{"observed_at":"2026-08-06T11:45:58.848072Z","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":"2026-08-06T11:46:01.051729Z","title":"Vertical federated learning-based feature selection with non- overlapping sample utilization,","venue":null,"work_id":"87d8be71-f4b5-492d-9f3b-e6d4a5449f84","year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.851532Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:6e72cfc76d4a41c977a9ac27e005abb27caf5154c9e65817aaa05a0a0b407abc","observation_id":"00ce1846-c076-413d-a302-aa5147b19065","resolution":{"observed_at":"2026-08-06T11:46:01.054855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:01.042404Z","title":"Practical vertical federated learning with unsupervised representation learning,","venue":null,"work_id":"5f40d2e6-600a-4872-bc10-0838929a551e","year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.856522Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:6f95a3be4ef560ed756b759606ebcbd631294a34b130f7e00e3a4a3cf842a63a","observation_id":"8770ab97-bf49-428b-9499-f70cb9b2e92f","resolution":{"observed_at":"2026-08-06T11:46:01.045513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:01.031925Z","title":"A review of the oversampling techniques in class imbalance problem,","venue":null,"work_id":"90d46a9c-00d1-460e-894b-087993574793","year":2021},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.859966Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:aeb6e7133edb856b75f33ada4dc6635a65a73a818f44e083c4a95ce1cf7f6c35","observation_id":"68cefc2f-12e2-4976-9f86-6dc16350d738","resolution":{"observed_at":"2026-08-06T11:46:01.035480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:01.022012Z","title":"A review on imbalanced data handling using undersampling and oversampling technique,","venue":null,"work_id":"5fea1e41-998f-4efb-b029-b629423b0f7e","year":2017},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.863382Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:9906e337d451c56e6a8c96bd4133298e4cc46f48d4b44d8076b492e4cd81f9f2","observation_id":"84a1e2d4-2d4e-48d4-b02a-57acb5f03ce5","resolution":{"observed_at":"2026-08-06T11:46:01.025094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08300","last_updated":"2020-06-23T02:12:29Z","snapshot_observed_at":"2026-08-08T16:23:37.332912Z","submitted_at":"2020-01-22T22:28:47Z","title":"Overcoming Noisy and Irrelevant Data in Federated Learning","version":2},"cited_work":{"arxiv_id":"2001.08300","doi":null,"metadata_source":"pith","pith_arxiv_id":"2001.08300","snapshot_observed_at":"2026-08-06T11:45:59.417975Z","title":"Overcoming Noisy and Irrelevant Data in Federated Learning","venue":"cs.LG","work_id":"2f035ecb-ff0d-4f25-b7d7-d4d7f915bdbc","year":2020},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.867102Z"},"links":{"cited_paper":"/paper/2001.08300","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:3534f2e03dfd36012c551db57d55a2eda4abf05e44a9d58e88708b7c5c1e7a96","observation_id":"a3ee2bd1-dc5f-4cb9-a0c2-74686f8a28dd","resolution":{"observed_at":"2026-08-06T11:45:59.538352Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.10619","last_updated":"2020-07-19T21:02:14Z","snapshot_observed_at":"2026-08-14T14:47:02.797260Z","submitted_at":"2020-02-25T01:36:43Z","title":"Three Approaches for Personalization with Applications to Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.10619","snapshot_observed_at":"2026-08-06T11:45:58.871376Z","title":"Three approaches for personalization with applications to federated learning,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.871376Z"},"links":{"cited_paper":"/paper/2002.10619","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:458861f06b5ca0a1528a9fd028e816a05f7745ac473abf26f7863c2ba3a26e7e","observation_id":"294525c7-8d89-4c6a-b1f8-b641b253d10d","resolution":{"observed_at":"2026-08-06T11:45:58.871376Z","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":"2026-08-06T11:46:01.012051Z","title":"Attribute-based classifi- cation for zero-shot visual object categorization,","venue":null,"work_id":"117c5742-3c19-47d7-9475-0ed1aeeceb1d","year":2013},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.875700Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:238d80567b2d02052696d69680ccc1dd53f3e85d3cc5f94efc04aa031de78e79","observation_id":"95d3a178-ae30-414c-bb40-c21edd52b231","resolution":{"observed_at":"2026-08-06T11:46:01.015340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:01.002065Z","title":"Zero-data learning of new tasks","venue":null,"work_id":"2889915b-cfad-4035-9178-82bd73f7ba9e","year":2008},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.879609Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:39c125a057c42d84c316933cd441d02ba8faca37c99397df169b862d8bd38f7b","observation_id":"ce3ccc6b-68e3-4686-9d74-5d66f16b402a","resolution":{"observed_at":"2026-08-06T11:46:01.005230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.992122Z","title":"Learning hypergraph-regularized attribute predictors,","venue":null,"work_id":"ef7f0a7d-40d5-477d-8634-374462d475e6","year":2015},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.883221Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:6f89755fa4ba10dc8caad7c30b484ad0e49497df47f4a169584a0ff31390a489","observation_id":"f2c68f2c-a0b6-4ee4-88a6-24c89e97d36a","resolution":{"observed_at":"2026-08-06T11:46:00.995658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.981078Z","title":"Learning multimodal latent attributes,","venue":null,"work_id":"71b22a8e-1149-4155-935c-d94131de1d23","year":2014},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.886689Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:c720af90e7442d3ae5bacf35193468e369d1fac58bfed8e4e9b0a970e7d78b7d","observation_id":"56b87a91-c277-4faa-b49d-8373b01ee3eb","resolution":{"observed_at":"2026-08-06T11:46:00.984563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.971584Z","title":"Zero-shot recognition with unreliable attributes,","venue":null,"work_id":"e7ddd32f-7526-41a9-b3ce-3f27dce65377","year":2024},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.890506Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:6895d912518096d0da73e6ef96eec43a851d282450428a6720bce44a863dc0aa","observation_id":"6626cc98-1d2f-4439-93b2-5d3e3864f8a7","resolution":{"observed_at":"2026-08-06T11:46:00.974443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.951285Z","title":"Attribute-based classifi- cation for zero-shot visual object categorization,","venue":null,"work_id":"19e8fd1d-137e-4ccc-8454-8c1543541faa","year":2014},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.898293Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:bb1d42ee65ae48ad3e6ec9819014c5ad85fbf76ca190fa9c6e1cf797b9cb6286","observation_id":"b23733fb-7208-40d6-97f8-22ce5334dadf","resolution":{"observed_at":"2026-08-06T11:46:00.954977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.940143Z","title":"Generative zero-shot learning via low- rank embedded semantic dictionary,","venue":null,"work_id":"e85a698a-ae0f-4ec7-9c1b-948893dc30d3","year":2019},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.901908Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:0425e3e8b9953843af3ca1205ba642af10b9bdaf9f7769c0f7200d9f1032994a","observation_id":"88719f2c-22e2-4386-8213-4f01eed3d471","resolution":{"observed_at":"2026-08-06T11:46:00.944657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.928616Z","title":"Zero-shot learning via latent space encoding,","venue":null,"work_id":"fb24e7a1-029f-4137-8e2b-f3e1330616b3","year":2019},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.905110Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:6e692605396f83ac4f3e6f96cd2b9fa0b3da9c96e42222bc54da0c65bf6fc6dc","observation_id":"29f32135-ae8f-4824-a039-743acacc3210","resolution":{"observed_at":"2026-08-06T11:46:00.932657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.916887Z","title":"Transduc- tive zero-shot learning with a self-training dictionary approach,","venue":null,"work_id":"4672c7f5-50e3-42cc-b7a5-190a96bd3a8b","year":2018},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.908449Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:36fccaf9066a961a17224c046cbf306b0148677e6a0d2515760d5a390d140d1f","observation_id":"c5690373-c836-4ac2-96cd-ffcf823c5e25","resolution":{"observed_at":"2026-08-06T11:46:00.920295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.00981","last_updated":"2018-04-12T12:17:47Z","snapshot_observed_at":"2026-08-14T20:07:18.305244Z","submitted_at":"2017-12-04T10:00:40Z","title":"Feature Generating Networks for Zero-Shot Learning","version":2},"cited_work":{"arxiv_id":"1712.00981","doi":null,"metadata_source":"pith","pith_arxiv_id":"1712.00981","snapshot_observed_at":"2026-08-06T11:45:59.370289Z","title":"Feature Generating Networks for Zero-Shot Learning","venue":"cs.CV","work_id":"57c7781e-6c8a-4b06-a692-e1c53615e955","year":2017},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.912054Z"},"links":{"cited_paper":"/paper/1712.00981","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:dbe16b4253cddec316a1d103547bc47bb858ae24b8f97e0a48785ab8352375e7","observation_id":"12b28cb3-8e3e-4b2c-adf1-f2fcc38c220f","resolution":{"observed_at":"2026-08-06T11:45:59.382184Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.906298Z","title":"General- ized zero- and few-shot learning via aligned variational autoencoders,","venue":null,"work_id":"f5fa701c-a23a-4153-a193-831e7d89c90a","year":2019},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.915575Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:6a3f12cdf9646ae7f1eede3673e9f4a90930d593825d08888b2498579abaf6a4","observation_id":"a34c8a0b-5668-4f24-9b9d-54ba5fb38237","resolution":{"observed_at":"2026-08-06T11:46:00.909701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.895786Z","title":"Fedproto: Federated prototype learning across heterogeneous clients,","venue":null,"work_id":"df081a25-ba85-4825-bb96-b347eefdfa96","year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.918636Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:43ea0e0e45edf6a4b44ada77a2fe87310bde73ab4336eaafc2f7b90b6862389b","observation_id":"028886ef-a747-457e-803a-28d5f34c7387","resolution":{"observed_at":"2026-08-06T11:46:00.899359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.886241Z","title":"Fedfa: Federated learning with feature anchors to align features and classifiers for heterogeneous data,","venue":null,"work_id":"6fe680c6-6134-4b78-b589-79b655a2c175","year":2023},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.922440Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:3b7d1f1f07aa9fbfc22062109f01ad9f8815a33a97c74c64c3a947a122a98669","observation_id":"1e4f6cb6-9d30-41da-8566-bd1db8723822","resolution":{"observed_at":"2026-08-06T11:46:00.889706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11867","last_updated":"2023-06-20T19:58:58Z","snapshot_observed_at":"2026-08-13T11:13:03.155359Z","submitted_at":"2023-06-20T19:58:58Z","title":"Personalized Federated Learning with Feature Alignment and Classifier Collaboration","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.11867","snapshot_observed_at":"2026-08-06T11:45:58.925905Z","title":"Personalized federated learning with feature alignment and classifier collaboration,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.925905Z"},"links":{"cited_paper":"/paper/2306.11867","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:1c5624d573c44195a5d780dd68a46bae62a8cb573f1f7fbaca9ec57e0645469a","observation_id":"e0e4ccfc-75a6-4a18-9d6d-eb3a86e5ef0d","resolution":{"observed_at":"2026-08-06T11:45:58.925905Z","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":"2026-08-06T11:46:00.876084Z","title":"Tackling data heterogeneity in federated learning with class prototypes,","venue":null,"work_id":"d4f45dbd-263a-4a80-b3a5-44083bbc433e","year":2023},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.930807Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:ead93b50cf9e7b4352acc3438044ba49dcb133c29b3a6feade73fc164448f0b8","observation_id":"7512860c-5ca1-4e9e-8683-e19d47f936d4","resolution":{"observed_at":"2026-08-06T11:46:00.879518Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:45:58.934167Z","title":"Fedproc: Prototypical contrastive federated learning on non-iid data,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.934167Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:89c8c7ed2ec5a517a8191035b1ef446b48c93cd9a205139ca933b9a5f1830dd6","observation_id":"7d2bf1fb-8626-4dfa-9bb5-7a83744a9013","resolution":{"observed_at":"2026-08-06T11:45:58.934167Z","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":"2026-08-06T11:46:00.860184Z","title":"Contrastive-enhanced domain generalization with federated learning,","venue":null,"work_id":"b26604c8-8a18-4cff-b903-0e9419b2f21b","year":2023},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.937189Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:f4962a99a155b988d9b32848f457b69f2b9e2c20fee3722fd7b59b9753c1ff9f","observation_id":"56672f37-b571-483f-ae45-e1bf670bd333","resolution":{"observed_at":"2026-08-06T11:46:00.863718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.850755Z","title":"Vertical federated knowledge trans- fer via representation distillation for healthcare collaboration networks,","venue":null,"work_id":"7eacddd4-b697-4abd-aa27-4ce96f40fb75","year":2023},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.940698Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:318d19acadf399f2d5ce15fe1c0a63660c9935c9734fc98a56d3a364aaf3ccd6","observation_id":"4e20427e-9249-4e11-bbc8-20f7168b1de3","resolution":{"observed_at":"2026-08-06T11:46:00.854083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.841797Z","title":"Improving availability of vertical federated learning: Relaxing inference on non-overlapping data,","venue":null,"work_id":"e1acdcf6-53c3-4b5a-955f-48e69e402b1c","year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.943987Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:5c051a5d4aa1f3e25b9ee70a603e7b8b1d030f871c417d5138812677c85bdd6e","observation_id":"078a5084-47b1-4647-aee6-dc9261be3e85","resolution":{"observed_at":"2026-08-06T11:46:00.844718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.04035","last_updated":"2018-03-20T21:46:12Z","snapshot_observed_at":"2026-08-14T19:37:21.484112Z","submitted_at":"2018-03-11T20:53:18Z","title":"Entity Resolution and Federated Learning get a Federated Resolution","version":2},"cited_work":{"arxiv_id":"1803.04035","doi":null,"metadata_source":"pith","pith_arxiv_id":"1803.04035","snapshot_observed_at":"2026-08-06T11:45:59.325553Z","title":"Entity Resolution and Federated Learning get a Federated Resolution","venue":"cs.DB","work_id":"45a7713d-f69e-420e-871a-d81e65eaadc1","year":2018},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.947223Z"},"links":{"cited_paper":"/paper/1803.04035","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:be391156d85d2920b5d221bc62a5b5c96b5d6575fe0c2b71ffa74ab3ac95d073","observation_id":"be3f8c53-9628-4b4c-ba89-56cac966b8e4","resolution":{"observed_at":"2026-08-06T11:45:59.336513Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.10677","last_updated":"2017-11-29T04:29:29Z","snapshot_observed_at":"2026-08-14T20:09:03.266453Z","submitted_at":"2017-11-29T04:29:29Z","title":"Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.10677","snapshot_observed_at":"2026-08-06T11:45:58.950694Z","title":"Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.950694Z"},"links":{"cited_paper":"/paper/1711.10677","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:b40fd5b88b94193744ef749126a5fdc74281e4431ecef8f42c1621b5429d3587","observation_id":"047fdd2e-f266-4baf-b8db-394023011103","resolution":{"observed_at":"2026-08-06T11:45:58.950694Z","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":"2026-08-06T11:46:00.830915Z","title":"Opti- mal transport based one-shot federated learning for artificial intelligence of things,","venue":null,"work_id":"da6a3caf-1f8c-4857-85b0-5bf32a9c0455","year":2023},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.954326Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:79638fc40a3cab02193c44686bafcf78f33314a35fcd403e4b3e38d5becd3559","observation_id":"7be908fa-58c8-4f05-a5eb-7df8b756a83a","resolution":{"observed_at":"2026-08-06T11:46:00.833898Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.821939Z","title":"Global and local prompts coop- eration via optimal transport for federated learning,","venue":null,"work_id":"edf950b2-d021-431e-aae6-43d107515578","year":2024},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.957674Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:079b7c621170a3fc4cb2735e50700667d90dfc0c1c9d055243efc1693ec0d3b7","observation_id":"5905b1b4-ec77-40b7-8c3d-ebd24334b6fc","resolution":{"observed_at":"2026-08-06T11:46:00.825143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.812422Z","title":"Spectr: Fast speculative decoding via optimal transport,","venue":null,"work_id":"99c253de-a251-4530-bace-3bb0bf09c402","year":2024},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.961207Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:29858832cb3ccce52f2d8d21f810d7028a9d57e009af6283229577cf25259bb7","observation_id":"69a7c1d5-49cb-4d73-8500-e927d8f9bb4c","resolution":{"observed_at":"2026-08-06T11:46:00.815545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.803228Z","title":"Bayes’ theorem,","venue":null,"work_id":"734d5919-4364-40c5-9e49-6ff60ff888db","year":2003},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.964982Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:b08199ddfcfbd7270f7711b24e0e983164a99b31bb7bdbcbbd089812c4c5fda0","observation_id":"eb848160-65db-491a-b872-923da3cd13cc","resolution":{"observed_at":"2026-08-06T11:46:00.806347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.10288","last_updated":"2017-11-28T13:39:10Z","snapshot_observed_at":"2026-08-14T20:09:22.524247Z","submitted_at":"2017-11-28T13:39:10Z","title":"Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.10288","snapshot_observed_at":"2026-08-06T11:45:58.968465Z","title":"Minimal-entropy correlation alignment for unsupervised deep domain adaptation,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.968465Z"},"links":{"cited_paper":"/paper/1711.10288","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:f6b72ad7ad1817b311374a4714ec5ee3b33dddefe4fa5b10474ee8ce507cbeb5","observation_id":"9125c0be-3310-4f42-854e-c7b0f917bbbc","resolution":{"observed_at":"2026-08-06T11:45:58.968465Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.01690","last_updated":"2020-02-05T09:13:19Z","snapshot_observed_at":"2026-08-08T04:03:50.002729Z","submitted_at":"2020-02-05T09:13:19Z","title":"Entropy Minimization vs. Diversity Maximization for Domain Adaptation","version":1},"cited_work":{"arxiv_id":"2002.01690","doi":null,"metadata_source":"pith","pith_arxiv_id":"2002.01690","snapshot_observed_at":"2026-08-06T11:45:59.264674Z","title":"Entropy Minimization vs. Diversity Maximization for Domain Adaptation","venue":"cs.LG","work_id":"25920b00-155a-4e8b-95d0-b164821b0724","year":2020},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.972623Z"},"links":{"cited_paper":"/paper/2002.01690","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:75e7db8f91c03a85e887182c1fe460a9287eb9b7e982d64e94228413a19f4076","observation_id":"da953bc6-5be2-4a06-a35a-50eab2e385b0","resolution":{"observed_at":"2026-08-06T11:45:59.286075Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.792741Z","title":"von liebig’s law of the minimum and plankton ecology (1899–1991),","venue":null,"work_id":"4ead63ab-d023-44d6-8d96-2cdfeabb6d83","year":1991},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.977138Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:a405399466fcb495f56a044ec6ccee54171912fe5426667a1df10f88bec9b473","observation_id":"454f8b5c-fc58-415e-8d99-abd022a4fd1e","resolution":{"observed_at":"2026-08-06T11:46:00.795918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.782860Z","title":"Enhancing supervised learning with unlabeled data,","venue":null,"work_id":"2992255f-3175-4b29-b7e3-ddc5e4308f4c","year":2000},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.981297Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:ddfabe3118f11c3b02c573cddf1f3385a9f59de53335b81e7f3b00fa6301f53b","observation_id":"0926fba9-0aa8-40d0-834a-88250c07d6d7","resolution":{"observed_at":"2026-08-06T11:46:00.786160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.772496Z","title":"Adjusting the outputs of a classifier to new a priori probabilities: a simple procedure,","venue":null,"work_id":"e390c998-973f-44bd-b2a5-6767c858a803","year":2002},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.078476Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:868cdb773fc43e831fdd3c62c271974442d1e90087d2dcb7dcfcd09f702d03d1","observation_id":"f89f11f6-6188-44cc-8fe3-02ad37a6553e","resolution":{"observed_at":"2026-08-06T11:46:00.776028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.762795Z","title":"A unified solution for privacy and communication efficiency in vertical federated learning,","venue":null,"work_id":"50622bb9-e226-4782-8a10-796ecfeef69b","year":2024},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.083448Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:d08dedfc17f317524648b03a584d3ebbd9a71630ba365862d0ca29cfbfe3dc3e","observation_id":"e34ba576-d6b6-4477-86bb-a9b1ffb64dc8","resolution":{"observed_at":"2026-08-06T11:46:00.765928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.752903Z","title":"Flexible vertical federated learning with heterogeneous parties,","venue":null,"work_id":"f5899149-6d88-46c9-b29c-29d5c3a794af","year":2023},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.087756Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:a7d7dee5d502d1c0033d8c66065d3c2242139a2235a2142327c549347dd7e9de","observation_id":"89519635-eeb9-489e-96fa-97594ca69e8f","resolution":{"observed_at":"2026-08-06T11:46:00.756524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.742584Z","title":"Twenty years of mixture of experts,","venue":null,"work_id":"87fae87d-22ef-4754-beca-8d9c0b8541a2","year":2012},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.091675Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:986c24c78549a72946a7b1d33e36fe0b822b4db3d2021a8e7d57cf66e3a36c6c","observation_id":"18b257ab-f8e8-4b36-bc2d-b945c221a355","resolution":{"observed_at":"2026-08-06T11:46:00.745262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.733911Z","title":"Less-vfl: Communication-efficient feature selection for vertical federated learning,","venue":null,"work_id":"6a8db6ae-4c66-4d9e-ab0c-06f84579389a","year":2023},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.095130Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:2d276ea855540bb0c92638179b65895c1443465c46c13c4952c5877af0ca4c34","observation_id":"0abe2e64-7f0d-4ad6-b798-c347f1f2fa93","resolution":{"observed_at":"2026-08-06T11:46:00.737160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.724736Z","title":"Label inference attacks against vertical federated learning,","venue":null,"work_id":"175060b7-179b-4fe3-8b38-909de08dc4a2","year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.098127Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:a5be26799214d3f808ce4286aadadb9d3f3b2acf3ff6fb5d4a8bc10b664020a2","observation_id":"21f16f50-06a8-4467-90c6-a9c56ab4dfe8","resolution":{"observed_at":"2026-08-06T11:46:00.727589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.715795Z","title":"Practical feature inference attack in vertical federated learning during prediction in artificial internet of things,","venue":null,"work_id":"4eab0233-51cf-4b5f-b7e4-7d81a9ec9092","year":2023},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.102573Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:443e6de71f894f0912945967047f3969d7a585e34fde0329411e1b4cff15d1a0","observation_id":"24186fcb-dd01-4492-8785-aadc5fa4f3df","resolution":{"observed_at":"2026-08-06T11:46:00.718738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.02246","last_updated":"2018-02-06T22:10:14Z","snapshot_observed_at":"2026-08-14T19:48:10.374742Z","submitted_at":"2018-02-06T22:10:14Z","title":"Approximation Methods for Bilevel Programming","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.02246","snapshot_observed_at":"2026-08-06T11:45:59.105558Z","title":"Approximation methods for bilevel program- ming,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.105558Z"},"links":{"cited_paper":"/paper/1802.02246","citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:bc5955e180e6b685f43919dc712eb4b7d504e8740eee784233a2b96f73b3b0f7","observation_id":"e16d27f0-9bc4-4e9a-92e1-f7038bd7981f","resolution":{"observed_at":"2026-08-06T11:45:59.105558Z","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":"2026-08-06T11:46:00.707083Z","title":"Convergence of meta- learning with task-specific adaptation over partial parameters,","venue":null,"work_id":"5d7bc94e-4939-4a4a-8575-a2af9c563986","year":2020},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.109948Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:d8c7ff821171c35940e0da92c2c1c3ccad59bcd93b6b93f9c212d21b655ff9c2","observation_id":"ea56169b-28b7-46da-8e9a-111ef43a392b","resolution":{"observed_at":"2026-08-06T11:46:00.710210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.697246Z","title":"Closing the convergence gap of sgd without replacement,","venue":null,"work_id":"53731150-1f4b-4b97-b1a2-8612a409dc4f","year":2020},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.113139Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:dbbd717aefba6ef7d4118d761cbdb6f0524789eaea3058e8c90a6aaba87c848c","observation_id":"4368138e-24d9-4c55-aac1-9f19d201ec17","resolution":{"observed_at":"2026-08-06T11:46:00.700527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.687247Z","title":"Bilevel optimization: Convergence analysis and enhanced design,","venue":null,"work_id":"1d4ffd0e-5ee9-4911-9f9d-26e6d0d473fd","year":2021},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.116347Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:7c5b19e812525bccefe7c563436cade710117ce1006532acceed594749bb7b44","observation_id":"45b31715-1114-41d4-a1fb-3d02a8ad6b9e","resolution":{"observed_at":"2026-08-06T11:46:00.691274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.677126Z","title":"Fastslowmo: Federated learning with combined worker and aggregator momenta,","venue":null,"work_id":"e13012cd-0116-427e-b504-fa3d30fad6e0","year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.119717Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:3acde119e36630e05610391efdea576b538547d45b4dc640335b816c38db1384","observation_id":"d3c34287-9655-4ff1-bed3-aa87bbe1b75b","resolution":{"observed_at":"2026-08-06T11:46:00.681377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.666276Z","title":"General data protection regulation,","venue":null,"work_id":"debc037b-0be6-4c3f-90d4-e325fa3b98bb","year":2020},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.124306Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:590abcee1b2cb9f1846b50782213e7dec8d18aeb6748a3b03773a3003a5913c5","observation_id":"c46b0ed9-77a0-4165-8951-8719be90e846","resolution":{"observed_at":"2026-08-06T11:46:00.670160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.656980Z","title":"Inverting gradients-how easy is it to break privacy in federated learning?","venue":null,"work_id":"225b89e6-3e4e-4b60-87ff-84227b8e363c","year":2020},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.128335Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:47cf22bbe3486df6580a4bbd166f95badb3cda0107557bb54a8c663254a0cf0e","observation_id":"d42d6f06-4732-4492-96dc-d6284f8f3486","resolution":{"observed_at":"2026-08-06T11:46:00.660286Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.646295Z","title":"3d shapenets: A deep representation for volumetric shapes,","venue":null,"work_id":"d4f9327a-dba8-4bdc-ab93-246f6387a894","year":2015},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.131786Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:74c0827b28137bc73e1a97e1920aa32d1c0bbf37bf78a20bbb22d4b13e955527","observation_id":"29fe5cda-d171-4cb6-a0ad-849f3809af1b","resolution":{"observed_at":"2026-08-06T11:46:00.649497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.637372Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms,","venue":null,"work_id":"5166a5e8-88de-443f-9366-2c1c53f01219","year":2017},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.135075Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:99da2e5a5b3c3a73f40db31bf63c8358a2a95202302697061d5ea6cbf99e8519","observation_id":"9bb2134f-58a5-4e83-a376-a6c2e9574202","resolution":{"observed_at":"2026-08-06T11:46:00.640292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:45:59.138329Z","title":"Default of Credit Card Clients,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.138329Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:0df23780bf1bce608f53eb28683b772db5ded30d24113cf40ff4a2e4b39bab87","observation_id":"699b0aee-af7f-4cd0-9495-54dae02250df","resolution":{"observed_at":"2026-08-06T11:45:59.138329Z","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":"2026-08-06T11:45:59.141691Z","title":"Becker and R","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.141691Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:ddb722a5f0b33bfb68ad456aba89f470159675779a2b7ca455af17270bd72b96","observation_id":"8394728a-7454-41c4-8fee-6755f68f958b","resolution":{"observed_at":"2026-08-06T11:45:59.141691Z","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":"2026-08-06T11:46:00.627829Z","title":"A method for stochastic optimization,","venue":null,"work_id":"63e9a74a-6fad-48a0-99ec-47edb78b3439","year":2015},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.145393Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:ed693001d264e27561eea4d7ee1a7f5b83f7c1547dd483b5d2c713df86a3df91","observation_id":"7c161396-f952-47ac-9aba-2105dcc9c2e7","resolution":{"observed_at":"2026-08-06T11:46:00.631350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.617516Z","title":"An experimental study of class imbalance in federated learning,","venue":null,"work_id":"c7be5e13-0cc3-4e8d-bb2c-cb9e8a87449a","year":2021},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.148700Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:5e4dcdf2e434164f51d4bff5f79cdbe44339b3404acfb1cf9b868f449dd7d445","observation_id":"7e3a88c6-a518-4b11-b794-4c1adc3d9bd3","resolution":{"observed_at":"2026-08-06T11:46:00.621369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.607065Z","title":"Semantic cosine similar- ity,","venue":null,"work_id":"d013bdd2-9562-4116-8d2b-8d0e5d26d578","year":2012},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.152063Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:9dc23e47028f40b4bdb729a6ee2db531f10efd35f1cd581bba452940846bbda6","observation_id":"d94b314f-711a-476f-966b-50cca4dcdd0b","resolution":{"observed_at":"2026-08-06T11:46:00.610542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.596165Z","title":"Learning with a wasserstein loss,","venue":null,"work_id":"70e84c73-6cc2-4c2e-bf2c-4e874760b4d0","year":2015},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.155451Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:d229533ce2de63383934cbdff8c24e506e918e8f1ccdeb8cc3d53f07dad59cd4","observation_id":"610503d5-692c-4398-ab78-273ad32134cf","resolution":{"observed_at":"2026-08-06T11:46:00.599979Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.585462Z","title":"Semi-supervised cross-silo advertising with partial knowledge transfer,","venue":null,"work_id":"2d7787a7-f67d-4c5d-9a10-90fd84995045","year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.158317Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:f6fc936c753573df442783e3e3129ee06d6ace7b12d9b4032dd4c9c9b8bc7c00","observation_id":"c9adcccb-5f1a-44b6-8ee9-2723b46912da","resolution":{"observed_at":"2026-08-06T11:46:00.589168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.576133Z","title":"Differential privacy,","venue":null,"work_id":"a58fd3e4-0e0f-4cac-bc21-e2c7b6650a94","year":2006},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.161590Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:4e1a85d3ce46487c88d4e998c8e0faedb47ecc7a95a86290e14dba30eb7331a0","observation_id":"934502b1-c3b4-4bd7-9aee-b45eaf202f5b","resolution":{"observed_at":"2026-08-06T11:46:00.579434Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.565909Z","title":"Semi-supervised learning by entropy minimization,","venue":null,"work_id":"bae6bd06-947b-4a94-86fd-f5b851039447","year":2004},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.165380Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:f924b9628ab9b563b48df996768d9f7b8a42f880f5c121e90a9fb8dec92d731b","observation_id":"f1064a29-d076-4c9a-9f69-af57d51ca604","resolution":{"observed_at":"2026-08-06T11:46:00.569428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.555515Z","title":"Semi- supervised domain adaptation via minimax entropy,","venue":null,"work_id":"ce062899-c89e-49a7-aa8a-a8d4321952ca","year":2019},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.168595Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:e7a905ba3725cadba4201e40b95a36a69bdd152abcdc432ea86a37514025bcab","observation_id":"ba42142a-c51f-4479-8dd7-e56532c18544","resolution":{"observed_at":"2026-08-06T11:46:00.558884Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.546026Z","title":"Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation,","venue":null,"work_id":"c5db7e03-36e1-4a2f-8c67-3484964f37ec","year":2019},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.171962Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:6a3363685c3fdce8e6bce55853924dad88ceed790b3a3582fb4a415b6f356292","observation_id":"4c2ca93e-9288-4da4-a3b8-569e690f5a97","resolution":{"observed_at":"2026-08-06T11:46:00.549028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.535067Z","title":"Universal domain adaptation through self supervision,","venue":null,"work_id":"c23a533e-3301-4652-926d-855bb78b5c32","year":2020},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.175500Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:baf65f8de74c6ed9dbf37c117f09fa99f4fbe6d46929ffdf82f8b8407e1fe22e","observation_id":"3b2d5537-c8f3-4b35-ab71-786a90911e12","resolution":{"observed_at":"2026-08-06T11:46:00.538800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.524423Z","title":"Robust optimal transport with applications in generative modeling and domain adaptation,","venue":null,"work_id":"248d8811-cf58-45b2-acbd-329e58489310","year":2020},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.178716Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:98c3a5a4f5bda2d7f5f0ce0650f5c41d5abcd8c1c9ffb80cb174d34334c8226f","observation_id":"76fb7c29-a8c1-4451-8a82-74a5eec436a9","resolution":{"observed_at":"2026-08-06T11:46:00.528156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.514616Z","title":null,"venue":null,"work_id":"57da1d07-a207-4f74-b0ca-aaf93ca73c67","year":2005},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.181936Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:57d9ec5ad39aed3722f5e00be89b672edcee62b1ba8c457a8c360c0a7755ee09","observation_id":"db0b67c7-ed31-4617-8d50-3336323db867","resolution":{"observed_at":"2026-08-06T11:46:00.518146Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.504249Z","title":"Cross-silo federated neural architecture search for heterogeneous and cooperative systems,","venue":null,"work_id":"5253792b-ddca-443d-b78e-ebc28eea1856","year":2022},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.184772Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:66e1fa2fc82d31c9dfccb7e624d009f6a33fd0901a8756e4c26489786b4f3cc6","observation_id":"a39fc52f-6778-40d5-b619-8e0870c5e110","resolution":{"observed_at":"2026-08-06T11:46:00.507715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.492253Z","title":"Likelihood","venue":null,"work_id":"ec819a9a-8f92-47c1-a1d9-7f470cbff938","year":2024},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.188171Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:ba892bf37df97bcf75590e741beccffe8632d33f855c527195051aca7c65b7be","observation_id":"be6ed47d-da7d-44d8-a1d6-c188ea5a20e3","resolution":{"observed_at":"2026-08-06T11:46:00.495859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.481128Z","title":"The target label of each data point, Y m,n, can not be directly obtained by observation","venue":null,"work_id":"e07f896b-e970-47a4-b01d-d390d3373a9d","year":null},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.191944Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:bac1127ee5975419aff99f3eabff271e10f94a04b506eaec401b5003bfdb370f","observation_id":"3665db38-f513-4277-bf51-242c649f5a7c","resolution":{"observed_at":"2026-08-06T11:46:00.484764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.470792Z","title":"To show the smooth property of F (Θ), we first introduce the following lemma which is proposed in [57]","venue":null,"work_id":"2e3954d9-1086-44d1-acb1-028ceb493174","year":2024},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.195741Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:d7782c1ee27803f75d3af37508bab1d8e248d34231bef8a6a13d6f6d9b5de69f","observation_id":"07d2ecd9-54e2-474a-b35d-29f19a23a14a","resolution":{"observed_at":"2026-08-06T11:46:00.473807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.460248Z","title":"Other nota- tions involved Bj or Bj such as ∇Θ∇E llocal(Θ0 t , E j−1 t ; Bj−1) have similar meanings","venue":null,"work_id":"0ec9f864-6b90-495c-9a21-6ed1a3702c8a","year":2024},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.199282Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:ebc53df0f6c517ac7093de34f8d06bd2bfc79d8812999c3bdf9fd0dfaaf28085","observation_id":"200e3c51-f475-40b8-9af4-8ea09b7d55fb","resolution":{"observed_at":"2026-08-06T11:46:00.463598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.446933Z","title":"(77) This is a more general result of Theorem 1","venue":null,"work_id":"6be0d97d-a001-4a49-825d-1d61d86ee609","year":2024},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.202678Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:745ef20e33eaeca826b4dd3a346660a64ab1644f51851edb971e548d6cfac76e","observation_id":"08aa53b7-1b6f-4e91-81c3-82e27c188bd2","resolution":{"observed_at":"2026-08-06T11:46:00.452610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.434373Z","title":null,"venue":null,"work_id":"62529bb6-d03d-4d7b-830e-5a420ac8492e","year":null},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.206279Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:bc967bbf135b0c5c41747fba33d68c99622e9c0131ebd169f5f1fe5249241b8c","observation_id":"57d2adfc-6e09-42a1-956a-64e9dd591437","resolution":{"observed_at":"2026-08-06T11:46:00.438702Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.349060Z","title":"nc represents the number of samples in class z","venue":null,"work_id":"ab23a5b8-04ad-4292-b7a4-521b180ed5fe","year":null},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:59.210161Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:d36a629f2a18c2be4668fcc922dbcc2a7c0aa5d6ea220cf0cc09f74210b4c992","observation_id":"caa86502-f348-4c7a-8469-d7915e487488","resolution":{"observed_at":"2026-08-06T11:46:00.388302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T11:46:00.961809Z","title":"Available: https://proceedings.neurips.cc/paper files/ paper/2014/file/1f1baa5b8edac74eb4eaa329f14a0361-Paper.pdf","venue":null,"work_id":"57003a34-64db-407b-854e-f33b3d892a44","year":2014},"citing_paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-06T11:45:58.894203Z"},"links":{"citing_paper":"/paper/2507.22488"},"observation_digest":"sha256:23f128eed83c027405b1d417eb6626d783f1ee6b7b8ca4b0289a421621ef1297","observation_id":"f34ad314-74a7-42aa-8ac2-6a49df8c75bc","resolution":{"observed_at":"2026-08-06T11:46:00.964883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.22488","last_updated":"2025-07-30T08:48:33Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T09:43:57.385655Z","submitted_at":"2025-07-30T08:48:33Z","title":"Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data"},"reference_resolution":{"displayed":88,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":7,"verified_fuzzy":60},"total_outbound_references":88},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 88 of 88 outbound references and 0 inbound Pith citation observations for arXiv:2507.22488."}