{"as_of":"2026-08-07T18:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e2fb4d1a5d25a564bea2c02b0c4702e3618b2a3c55da82c97c40f6e988474685","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:55:03.636394Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2507.04310/citation-record","integrity":"/paper/2507.04310/integrity","json":"/paper/2507.04310/citation-record.json","paper":"/paper/2507.04310"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1803.08375","last_updated":"2026-04-14T12:21:53Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2018-03-22T14:30:17Z","title":"Deep Learning using Rectified Linear Units (ReLU)","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.08375","snapshot_observed_at":"2026-08-06T19:55:01.857249Z","title":"Deep learning using rectified linear units (relu)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:01.857249Z"},"links":{"cited_paper":"/paper/1803.08375","citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:f0484936cd78685fc4b67bd7acd54d011d53aa8d6ca2f47e4de074108703289d","observation_id":"c3bbd5c8-d8a5-4185-a420-f4e730549497","resolution":{"observed_at":"2026-08-06T19:55:01.857249Z","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":"2026-08-06T19:55:04.742142Z","title":"Fe- drolex: Model-heterogeneous federated learning with rolling sub-model extraction","venue":null,"work_id":"b365f58a-1e51-4719-8d10-13ab8d588bf9","year":2022},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:01.959671Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:17f49615d5ad00271ed13a62bc6a69ba6d422a049c3173d33466f446273f367c","observation_id":"f2fc4968-9ebe-4348-8dcd-03927d4132f8","resolution":{"observed_at":"2026-08-06T19:55:04.748932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.726270Z","title":"Angular visual hardness","venue":null,"work_id":"0e93567a-f1ed-4c23-899f-d16885190142","year":2020},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:02.029204Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:8d0d7fbe9f0ec56e4d7cef2e990fbcbb58cc15965ebe8be4de8c7e637ee82a6a","observation_id":"bb2ca1ad-971c-4eeb-aee8-516ec3599d2f","resolution":{"observed_at":"2026-08-06T19:55:04.731376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.710522Z","title":"Tackling data heterogeneity in federated learning with class prototypes","venue":null,"work_id":"a782ef7b-48d3-4461-a1c3-c0b4b1119251","year":2023},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:02.117516Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:f669fe65d69939e04906dcc69b5549defc36122af69a01889b33868a54f609e0","observation_id":"952ca455-2c79-4412-abd7-0500530d31c6","resolution":{"observed_at":"2026-08-06T19:55:04.716129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.00891","last_updated":"2022-09-27T10:01:07Z","snapshot_observed_at":"2026-07-31T04:25:47.630062Z","submitted_at":"2018-04-03T09:57:26Z","title":"Hyperspherical Variational Auto-Encoders","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.00891","snapshot_observed_at":"2026-08-06T19:55:02.265981Z","title":"Hyperspherical variational auto-encoders","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:02.265981Z"},"links":{"cited_paper":"/paper/1804.00891","citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:fedfd925e7969b2c0830bff21b133662bbf38836c39980525003a292604a12d0","observation_id":"625b1257-3de0-4946-bd26-3d84a7206ce8","resolution":{"observed_at":"2026-08-06T19:55:02.265981Z","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":"2026-08-06T19:55:04.694761Z","title":"Arcface: Additive angular margin loss for deep face recog- nition","venue":null,"work_id":"b573cf39-d6c0-4fc9-9d40-f4a06d78c293","year":2019},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:02.380021Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:33ae4b8e0e3383d7cfa02e50a92b4fd70aea72565f3748c1736d2f26232b3734","observation_id":"2e6bb4cc-a8d9-45dd-9ac5-7f4713213ee5","resolution":{"observed_at":"2026-08-06T19:55:04.699833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01264","last_updated":"2021-12-14T04:20:42Z","snapshot_observed_at":"2026-08-07T10:05:43.970632Z","submitted_at":"2020-10-03T02:55:33Z","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01264","snapshot_observed_at":"2026-08-06T19:55:02.489080Z","title":"Heterofl: Compu- tation and communication efficient federated learning for het- erogeneous clients","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:02.489080Z"},"links":{"cited_paper":"/paper/2010.01264","citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:366db0fecafe868eac52bde932115790f7ec707e31df737ab34445ddb223cd73","observation_id":"6d50bd8c-8b61-4c4e-9ed4-3d29fc0789a6","resolution":{"observed_at":"2026-08-06T19:55:02.489080Z","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":"2026-08-06T19:55:04.679437Z","title":"Fedhp: Federated learning with hyperspherical prototypical regular- ization","venue":null,"work_id":"5da3cf6d-368b-4c83-bbda-0044e13ea65e","year":2024},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:02.630504Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:e8f14102617892759c60983e146cc243f73a24d4a2a1844b46f3c53a582c0824","observation_id":"2c13ca5b-f77a-4af0-8f50-59be7a3f3749","resolution":{"observed_at":"2026-08-06T19:55:04.685557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.662467Z","title":"Fjord: Fair and accurate federated learning under heterogeneous targets with ordered dropout","venue":null,"work_id":"671e6662-567a-4b3b-9111-8641a1e88c2d","year":2021},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:02.743467Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:59abc41a4b76a2c4feb5de7fa62ad3b455e82bd212a10c4579e386e6dc080052","observation_id":"855b2703-dd25-477e-bcbc-692e426967f0","resolution":{"observed_at":"2026-08-06T19:55:04.669731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.647000Z","title":"Personalized cross-silo federated learning on non-iid data","venue":null,"work_id":"12c40c42-ee97-415a-b710-e27796d52544","year":2021},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:02.899969Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:5081cdd26f31e334df653d6d5ec406df7859fdee736e1f9d8bf70b10fb2110cf","observation_id":"6baf5649-7def-49df-9195-482f9253722d","resolution":{"observed_at":"2026-08-06T19:55:04.652709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.11479","last_updated":"2023-10-19T14:11:11Z","snapshot_observed_at":"2026-07-06T07:17:33.790455Z","submitted_at":"2018-11-28T10:16:18Z","title":"Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.11479","snapshot_observed_at":"2026-08-06T19:55:03.028693Z","title":"Communication- efficient on-device machine learning: Federated distillation and augmentation under non-iid private data","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.028693Z"},"links":{"cited_paper":"/paper/1811.11479","citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:8aede6d452f05c804567fbc85f34f4032cb85df881374950c6e769fd304fd17b","observation_id":"45e27e4e-f956-41e0-9e92-1fabf91a6f1b","resolution":{"observed_at":"2026-08-06T19:55:03.028693Z","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":"2026-08-06T19:55:04.631366Z","title":"Balanced open set domain adaptation via centroid alignment","venue":null,"work_id":"ed4508e8-3382-48d9-9479-21b33318e344","year":2021},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.136223Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:e4707ec08f8a6020209a35b6e508b2c1e3d1849ea9d3f88f267144b67bcefbff","observation_id":"f8a5f50c-e513-400a-9f7f-45f679464982","resolution":{"observed_at":"2026-08-06T19:55:04.636558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.143386Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.143386Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:5dbbbce6bcc2063397541acbfd9a4126e89e1e15f9cf66d253ab6e8dad41dacb","observation_id":"94fafb5b-ea56-4722-97e7-de5455a69997","resolution":{"observed_at":"2026-08-06T19:55:03.143386Z","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":"2026-08-06T19:55:04.610263Z","title":"Tiny imagenet visual recognition challenge","venue":null,"work_id":"1587dae2-7ba9-45bc-9031-eef2e7986daf","year":2015},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.290879Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:7cb9c0292fe2564aefb6f6085c329e2253bba9b65d907720d8f084089de11a5a","observation_id":"5d76c9ed-fb0d-4094-8258-96394634ebdc","resolution":{"observed_at":"2026-08-06T19:55:04.614838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.03581","last_updated":"2019-10-08T18:00:00Z","snapshot_observed_at":"2026-07-06T08:27:52.322036Z","submitted_at":"2019-10-08T18:00:00Z","title":"FedMD: Heterogenous Federated Learning via Model Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.03581","snapshot_observed_at":"2026-08-06T19:55:03.419039Z","title":"Fedmd: Heterogenous fed- erated learning via model distillation","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.419039Z"},"links":{"cited_paper":"/paper/1910.03581","citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:84f8098cacc9db77b29f8a3a346ca41596337c369d9330ae175d17d50ca7b88e","observation_id":"e8a084e9-06b3-4303-9b2a-9a1b910f8c3f","resolution":{"observed_at":"2026-08-06T19:55:03.419039Z","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":"2026-08-06T19:55:04.598828Z","title":"Feder- ated learning on non-iid data silos: An experimental study","venue":null,"work_id":"f038cf9c-2a89-4fae-a465-81759de8993c","year":2022},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.508331Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:e9dd176935cd8dc0e1c2999f215fa89b0ca47ad1ad471ff21e91c373ca2a7844","observation_id":"88d77742-868d-48ed-bd86-361deea8a157","resolution":{"observed_at":"2026-08-06T19:55:04.602347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.01523","last_updated":"2020-07-14T08:12:35Z","snapshot_observed_at":"2026-08-04T05:35:18.088525Z","submitted_at":"2020-01-06T12:40:21Z","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.01523","snapshot_observed_at":"2026-08-06T19:55:03.522793Z","title":"Think locally, act globally: Fed- erated learning with local and global representations","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.522793Z"},"links":{"cited_paper":"/paper/2001.01523","citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:3b5108cf55dd06e4559619e40e1b7421d48dbf8c2540a0b973a972dcdcb1c15d","observation_id":"6a4646f4-ab41-4767-b29a-394b8940f1e6","resolution":{"observed_at":"2026-08-06T19:55:03.522793Z","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":"2026-08-06T19:55:04.587107Z","title":"Regularizing neural networks via minimizing hyperspherical energy","venue":null,"work_id":"82327461-2d1f-43af-895e-b1b468b9a1dc","year":2020},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.527498Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:a787475dd75e141b1468641d973317656a28aa28c7971e17e2e4a9658c92cb3c","observation_id":"a089de7e-b9c0-4c54-8137-0c72bf2c1d4f","resolution":{"observed_at":"2026-08-06T19:55:04.590968Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.575277Z","title":"Ensemble distillation for robust model fusion in federated learning","venue":null,"work_id":"104afff0-7c61-498f-a305-25728210536b","year":2020},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.531509Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:eae5466b58f9168d5689ea1d6a711ae987458b2fcde2e9b948254fc768dc00d3","observation_id":"0cf1aa4e-94e8-4b1f-83d6-643b70e65e44","resolution":{"observed_at":"2026-08-06T19:55:04.579267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1612.02295","last_updated":"2017-11-17T23:23:09Z","snapshot_observed_at":"2026-07-06T05:21:43.690289Z","submitted_at":"2016-12-07T15:36:11Z","title":"Large-Margin Softmax Loss for Convolutional Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.02295","snapshot_observed_at":"2026-08-06T19:55:03.535482Z","title":"Large-margin softmax loss for convolutional neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.535482Z"},"links":{"cited_paper":"/paper/1612.02295","citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:43c374cd0c3ce8e113e518bba5841df45db23b9445ceb7fd91c8bfc1b84a00de","observation_id":"e6a22575-36aa-4085-82c1-9a3401c37c10","resolution":{"observed_at":"2026-08-06T19:55:03.535482Z","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":"2026-08-06T19:55:04.563995Z","title":"Deep hyperspherical learning","venue":null,"work_id":"a09b87cc-5840-488c-80df-3617a82476e1","year":2017},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.539311Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:8fd5fac5f26e8af6075c4f0006431e0d939b0e6405c37804a7648a9c60590866","observation_id":"1445ea90-ab22-48dd-96e0-51972f2f4859","resolution":{"observed_at":"2026-08-06T19:55:04.567496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.551806Z","title":"Learning towards minimum hyper- spherical energy","venue":null,"work_id":"8740df8b-22ed-48df-bba3-28f2f67c519a","year":2018},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.542827Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:7c7db8f8fcfe0518963385b0d5278e64478e16ba8444925af518bc1c699b33a1","observation_id":"d52629af-2ce1-441c-bfe0-454632499418","resolution":{"observed_at":"2026-08-06T19:55:04.556041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.450738Z","title":"Orthogonal over-parameterized training","venue":null,"work_id":"6a3fbaeb-acd4-4ab2-9249-44966e010c2e","year":2021},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.546645Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:2e6ce7b36c5600d1a78acbd9586598a5ae56c55f4e27b6685939ed2e8ac08f86","observation_id":"284ac42d-529e-4f5b-8ab2-8013b0c3a703","resolution":{"observed_at":"2026-08-06T19:55:04.513077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.314320Z","title":"Learning with hyperspherical uniformity","venue":null,"work_id":"644f9bd7-d19a-47b4-994b-83c2e04218c3","year":2021},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.550128Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:5acbb46e6457c42b134509714ae1ab31d5588b3230eb22700292a3ccd29b6a88","observation_id":"04563e50-fa1e-4d7b-b0ed-cc1cb2e84074","resolution":{"observed_at":"2026-08-06T19:55:04.326109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.148773Z","title":"Shufflenet v2: Practical guidelines for efficient cnn architec- ture design","venue":null,"work_id":"15cbd52a-c74e-4ba8-92c7-149130a16a42","year":2018},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.553681Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:0756baff373ea9cc379131f6d12e830043e10bdd4996a1febf4700a92db5d5c8","observation_id":"885c1689-a080-45fd-8de9-0686b5764a23","resolution":{"observed_at":"2026-08-06T19:55:04.254343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.091640Z","title":"Communication- efficient learning of deep networks from decentralized data","venue":null,"work_id":"720ba84d-9a9b-4837-8f42-3c5004a433e1","year":null},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.557368Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:6253739fa8d955a2d079507dcc62fcc23eab77e6c1c2844272041fa163b8070d","observation_id":"d28e6dad-8d19-4c29-bb7e-105aa03a35e7","resolution":{"observed_at":"2026-08-06T19:55:04.099002Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.079877Z","title":"Hyper- spherical prototype networks","venue":null,"work_id":"2d779753-9007-4adf-8e66-031318ca5aa0","year":2019},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.561720Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:b0bb50d68affe84b8e47c4ef4c3a547bc5921a3aa53242f3e421a5bdda14d554","observation_id":"f09c2fea-7d5b-41b3-9d8e-cd7b6221f05b","resolution":{"observed_at":"2026-08-06T19:55:04.083153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.062307Z","title":"Automated flower classification over a large number of classes","venue":null,"work_id":"80bd79bd-2a18-484f-8070-53d4fb2706b6","year":2008},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.565051Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:e2c850161beeb70255792207f988edc486043fe5fd5de556bccd6593c4f3f604","observation_id":"03bd326b-5581-456c-b43c-e39aef0a086d","resolution":{"observed_at":"2026-08-06T19:55:04.067668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.044600Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":"12836c13-dd02-4fb0-b0e9-4998b2aa50f4","year":2018},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.569055Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:33b8fbdcfc193a98ac5a921193db284d551c849db89a8811774323b9d02fe2d6","observation_id":"f1b51850-4474-4aa8-bd1c-c908da59ba80","resolution":{"observed_at":"2026-08-06T19:55:04.051205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.16765","last_updated":"2020-09-17T06:10:24Z","snapshot_observed_at":"2026-08-06T16:08:53.133968Z","submitted_at":"2020-06-27T09:35:03Z","title":"Federated Mutual Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.16765","snapshot_observed_at":"2026-08-06T19:55:03.573369Z","title":"Feder- ated mutual learning","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.573369Z"},"links":{"cited_paper":"/paper/2006.16765","citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:87db6dc293b7b42122897e4f1af8f06e7b072781382596f8bf7645fca3e2e7e1","observation_id":"24159cb1-0e1f-4e62-81af-10606aab1cba","resolution":{"observed_at":"2026-08-06T19:55:03.573369Z","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":"2026-08-06T19:55:04.027537Z","title":"Feduv: Uniformity and variance for heterogeneous federated learning","venue":null,"work_id":"b49a3921-addc-43c5-9d29-66934f207bff","year":2024},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.577047Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:3be836ec0eae723f4e487ae674fa5db267bf28f46636fde1e1c78f920c5b226a","observation_id":"9b891ea0-1f56-43e3-ab0f-66f290e74c81","resolution":{"observed_at":"2026-08-06T19:55:04.033106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:04.010343Z","title":"Personalized federated learning with moreau envelopes","venue":null,"work_id":"7bf7436d-7155-46e0-9771-dd47ab4f264b","year":2020},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.581465Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:b704edf3b0ff219b87ae5fc9e0ea1ec5552b1cfd2b60f31fafbd6292bc37ea9c","observation_id":"604baa65-bda8-4521-ac9d-dee98acb3831","resolution":{"observed_at":"2026-08-06T19:55:04.016776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.994541Z","title":"Hyperspherical consistency regularization","venue":null,"work_id":"da26bbd3-11b3-453e-8d1f-15cf42656ee1","year":2022},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.585336Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:53624b8c560b5ef9e524089ee78a81d705d43c4399370deb6d6f7ba10cbcb643","observation_id":"da6f9c76-0f13-4fb9-8a02-7931f086fec3","resolution":{"observed_at":"2026-08-06T19:55:03.999546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.11946","last_updated":"2020-09-11T05:08:01Z","snapshot_observed_at":"2026-08-06T22:36:56.473526Z","submitted_at":"2019-05-28T17:05:32Z","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11946","snapshot_observed_at":"2026-08-06T19:55:03.589633Z","title":"Efficientnet: Rethinking model scal- ing for convolutional neural networks","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.589633Z"},"links":{"cited_paper":"/paper/1905.11946","citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:61cda682827688a2377a3b4bf8119f0bdf5e48a55eb5b6556bfb6e78ac52b19f","observation_id":"4ba90e32-1365-4980-9352-b9b533b4bdc9","resolution":{"observed_at":"2026-08-06T19:55:03.589633Z","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":"2026-08-06T19:55:03.975738Z","title":"Fedproto: Federated proto- type learning across heterogeneous clients","venue":null,"work_id":"ec715338-b7f5-42d0-8796-70eb66c98109","year":2022},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.593192Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:035f477ac781cd38ddbb388c6aca35f229f2c6fd530e6762b8ed393dc9a3ee52","observation_id":"c2a8a60d-42c0-4dbe-9116-065cf7f7c591","resolution":{"observed_at":"2026-08-06T19:55:03.983108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.960088Z","title":"Cosface: Large margin cosine loss for deep face recognition","venue":null,"work_id":"4a70fc0b-db7f-4120-87f7-9d1632df6883","year":2018},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.596574Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:3816dedb3a009a4dd22c22459f38f4b9fd70bc142b3f88f6162dc32d1b230e7d","observation_id":"abe8b4cb-84e8-4de7-8400-75b9bbecda6e","resolution":{"observed_at":"2026-08-06T19:55:03.966770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.943053Z","title":"Larger norm more transferable: An adaptive feature norm approach for unsupervised domain adaptation","venue":null,"work_id":"06991c60-6d93-48f0-8472-a7954ecdf8af","year":2019},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.600351Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:0b3b40b5b8d156dc4b0a7626ef1b63953e68c56e29a3a3d17c49b5b7954c6785","observation_id":"fd652b32-d792-4fd6-9bc5-6ee35ccd369c","resolution":{"observed_at":"2026-08-06T19:55:03.949084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.926045Z","title":"Fedgh: Heterogeneous federated learning with general- ized global header","venue":null,"work_id":"0000b67e-641a-4888-beff-d118e94cf5d1","year":2023},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.603681Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:c7a02efd59ec92f5f39467ac292b195fef6af7d48629415d998ce9c84c4e88be","observation_id":"90ad167b-bc4a-40c2-acd3-a83334082dc2","resolution":{"observed_at":"2026-08-06T19:55:03.931540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.908268Z","title":"Con- trolling update distance and enhancing fair trainable proto- types in federated learning under data and model heterogene- ity","venue":null,"work_id":"2798303e-1fa8-4396-ad5f-18178cd8f73c","year":2025},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.607863Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:5cfb6e8615822ea27e1b7f68c990aed594182d2a736da366f5bf76313f5b2288","observation_id":"bd172fb6-2943-4ac8-bf1f-ac3b8c42eb3b","resolution":{"observed_at":"2026-08-06T19:55:03.914580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.892166Z","title":"A survey on federated learning","venue":null,"work_id":"0cfcc755-2744-463a-8772-13fc7b4f0bb6","year":2021},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.611633Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:d790fa9eace611e0b21343f70195a4c2cb28c4abe0775f3c48d5c47afc35ee24","observation_id":"40155190-0cbf-4f78-aacc-3673f7ca9835","resolution":{"observed_at":"2026-08-06T19:55:03.897029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.875550Z","title":"Fedala: Adaptive local aggregation for personalized federated learning","venue":null,"work_id":"39d4822f-81c1-432d-b4d5-2b608b0759ea","year":2023},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.615612Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:4962dda5d59e43a3c49a90821da83128b7b3593c79cae291a10331930e31bee2","observation_id":"9374efec-a440-451c-9ee7-c37d52310a4a","resolution":{"observed_at":"2026-08-06T19:55:03.881585Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.856216Z","title":"Fedtgp: Trainable global prototypes with adaptive-margin-enhanced contrastive learning for data and model heterogeneity in fed- erated learning","venue":null,"work_id":"0960a000-f4cb-4c54-bdd6-6b428e368833","year":2024},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.619233Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:a730a90fc6e4d79a6033ffa79756887478a36e1bc7137da31f89f7652930de4e","observation_id":"48f0d754-250f-438b-8749-971571f04591","resolution":{"observed_at":"2026-08-06T19:55:03.863712Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.837727Z","title":"Deep mutual learning","venue":null,"work_id":"e14ffe52-cd29-4cd6-ab89-4285f8f25bf2","year":2018},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.623226Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:0428673888060f492f8df6a61b4bfcdc9ca6eeb291ca2fd2974c1ac64f49b5ea","observation_id":"a19633ab-b99c-421b-8256-dc81903e3c04","resolution":{"observed_at":"2026-08-06T19:55:03.844701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.819269Z","title":"Deep residual networks for hyperspectral image classi- fication","venue":null,"work_id":"54767947-5dfb-45e5-82d0-510dd3c02ac2","year":2017},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.627715Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:54fcc8eb51f929af844eaf3068051a866aaf2d3d9628534f64e2e9db4a6cd87a","observation_id":"65ec9312-feb9-4eb6-bd5e-3b8c17eb6352","resolution":{"observed_at":"2026-08-06T19:55:03.826295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.802179Z","title":"Data-free knowledge distillation for heterogeneous federated learn- ing","venue":null,"work_id":"13bea3cf-d2ec-4b6e-8078-51606f572ebe","year":2021},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.632244Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:37800f2c233f13598b98737078c46e212dfe58fb646621cfff253df418ac28a8","observation_id":"cbad1c27-aa4b-41e1-a5f0-1ab6600f2feb","resolution":{"observed_at":"2026-08-06T19:55:03.809186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T19:55:03.781864Z","title":"Resilient and communication efficient learning for heteroge- neous federated systems","venue":null,"work_id":"4497fb9e-0685-4d7c-88af-03f47e82a410","year":2022},"citing_paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.636394Z"},"links":{"citing_paper":"/paper/2507.04310"},"observation_digest":"sha256:5a2de809b9d680d1a6996dd5c79fe9bffa7ef03521ad349660161c9155931ffa","observation_id":"cfb32289-c2cc-43ec-9103-5984b0b4f959","resolution":{"observed_at":"2026-08-06T19:55:03.789779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.04310","last_updated":"2025-07-06T09:34:41Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T10:05:55.957193Z","submitted_at":"2025-07-06T09:34:41Z","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":0,"verified_fuzzy":36},"total_outbound_references":46},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2507.04310."}