{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JC3BMPH4F7VKIOE6ECLJZ7M7X5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e275fcd8e2594af598ec74a40670d98ccc5b857a4b42cd81479f0d2c576feed5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T13:01:17Z","title_canon_sha256":"9b20bcc00b31ee7d534a365f5943e681d1fe1ab3e2e3983be80dd4d006f482ae"},"schema_version":"1.0","source":{"id":"2605.13475","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13475","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13475v1","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13475","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"JC3BMPH4F7VK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"JC3BMPH4F7VKIOE6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"JC3BMPH4","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:e3bf83b79027950401321b2d96ae5804d73facf75ebffc48d2ffcb26d420139d","target":"graph","created_at":"2026-05-18T02:44:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"hyper-prototypes produce a more semantically consistent global signal, and FedHPro achieves state-of-the-art performance on several benchmark datasets under diverse heterogeneous scenarios."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That matching gradients computed on real client samples will align hyper-prototypes more reliably than averaging local prototypes, without introducing new privacy leakage or optimization instability."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"FedHPro introduces gradient-matched hyper-prototypes plus mutual-contrastive learning to produce semantically consistent global signals and reach state-of-the-art accuracy on heterogeneous image benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Hyper-prototypes aligned by gradient matching from client samples reduce semantic drift in federated prototype learning."}],"snapshot_sha256":"73c7775217d26fde24604929157ff595b8e06f2484f2c39e73f1ef52fe8417fe"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"543ef28dff658b3cec64dfa8e2d373a2576919cce2fc5e0ed023d3fed296c362"},"paper":{"abstract_excerpt":"Federated Learning (FL) enables collaborative training of distributed clients while protecting privacy. To enhance generalization capability in FL, prototype-based FL is in the spotlight, since shared global prototypes offer semantic anchors for aligning client-specific local prototypes. However, existing methods update global prototypes at the prototype-level via averaging local prototypes or refining global anchors, which often leads to semantic drift across clients and subsequently yields a misaligned global signal. To alleviate this issue, we introduce hyper-prototypes, defined by a set of","authors_text":"Di Wu, Guansong Pang, Haoran Li, Huan Wang, Jun Shen, Jun Yan, Ousman Manjang, Yanlong Zhai, Zhenyu Yang","cross_cats":[],"headline":"Hyper-prototypes aligned by gradient matching from client samples reduce semantic drift in federated prototype learning.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T13:01:17Z","title":"FedHPro: Federated Hyper-Prototype Learning via Gradient Matching"},"references":{"count":14,"internal_anchors":0,"resolved_work":14,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Geodesic flow kernel for unsupervised domain adaptation","work_id":"30078da4-5702-4a95-b330-9b6301ace13e","year":2066},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Learning support and trivial prototypes for interpretable image classification","work_id":"3f34da05-f0b7-4392-b5ea-30fb79842983","year":2062},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"12 FedHPro: Federated Hyper-Prototype Learning via Gradient Matching A. Algorithm Pseudo-code Flow In this section, we describe the pseudo-code of our FedHPro in Algorithm 1: 1)Server-Side: we optimiz","work_id":"cb75084a-2f4e-4297-b7a1-619b6b206eaa","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"for the TinyImageNet dataset. The label skew heterogeneity level of clients is controlled by the standard deviation α of the Dirichlet distribution, and the quantity skew heterogeneity level is contro","work_id":"08a17d60-2f9c-40f2-84a3-f6a4f704bbef","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"is used for skin lesion classification and contains 8,912 training samples and 1,103 testing samples with 7 categories, and each sample’s size is scaled to224∗224 . Then, based on (Kaidi et al., 2019)","work_id":"240b0b88-c1f8-430d-9032-d066a7b7ebd2","year":2019}],"snapshot_sha256":"a2362fba15b17627156b60fc7ae93c8e4c91c4648703dc75cb5d55c004a6c21b"},"source":{"id":"2605.13475","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:21:59.453163Z","id":"caa6e760-881e-4e95-a58d-e6bf01719f99","model_set":{"reader":"grok-4.3"},"one_line_summary":"FedHPro introduces gradient-matched hyper-prototypes plus mutual-contrastive learning to produce semantically consistent global signals and reach state-of-the-art accuracy on heterogeneous image benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Hyper-prototypes aligned by gradient matching from client samples reduce semantic drift in federated prototype learning.","strongest_claim":"hyper-prototypes produce a more semantically consistent global signal, and FedHPro achieves state-of-the-art performance on several benchmark datasets under diverse heterogeneous scenarios.","weakest_assumption":"That matching gradients computed on real client samples will align hyper-prototypes more reliably than averaging local prototypes, without introducing new privacy leakage or optimization instability."}},"verdict_id":"caa6e760-881e-4e95-a58d-e6bf01719f99"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e3f3d8d6dbe7e185a532d5ceca4cb2cf02e8d33c874d4eebbbde6a7591a12623","target":"record","created_at":"2026-05-18T02:44:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e275fcd8e2594af598ec74a40670d98ccc5b857a4b42cd81479f0d2c576feed5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T13:01:17Z","title_canon_sha256":"9b20bcc00b31ee7d534a365f5943e681d1fe1ab3e2e3983be80dd4d006f482ae"},"schema_version":"1.0","source":{"id":"2605.13475","kind":"arxiv","version":1}},"canonical_sha256":"48b6163cfc2feaa4389e20969cfd9fbf483a104e2bb38e2ddf1b6beb37e36200","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48b6163cfc2feaa4389e20969cfd9fbf483a104e2bb38e2ddf1b6beb37e36200","first_computed_at":"2026-05-18T02:44:41.477777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:41.477777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vLbrJ+1ew0nvIt2YAIkX9zMvpiYuPsWaad2l/t0SsH0q9kaiq3+oufNg3vqyjpIsPVjuwnVV3Pfaf9UqoikjAA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:41.478493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13475","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3f3d8d6dbe7e185a532d5ceca4cb2cf02e8d33c874d4eebbbde6a7591a12623","sha256:e3bf83b79027950401321b2d96ae5804d73facf75ebffc48d2ffcb26d420139d"],"state_sha256":"f64a6dfd11cc1973a3c4a4aa45e1e9992c280ee11018a0b27744b3e77ad0ef3a"}