{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:E4HUIJUNZ2LBAXPIHOJL3RMM7S","short_pith_number":"pith:E4HUIJUN","canonical_record":{"source":{"id":"2301.08968","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-21T16:20:57Z","cross_cats_sorted":[],"title_canon_sha256":"5204537cb41bd404e182382f5ed56c9f86c8c336c93184e564fa7ebb68c615ce","abstract_canon_sha256":"52079d7d527a726196af2f14a32f6fac0668fef4a1865e0c1f59bbc1872c446b"},"schema_version":"1.0"},"canonical_sha256":"270f44268dce96105de83b92bdc58cfca2ccddd6e7478d1df4e7d8d2765250b0","source":{"kind":"arxiv","id":"2301.08968","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08968","created_at":"2026-07-05T05:59:06Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08968v2","created_at":"2026-07-05T05:59:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08968","created_at":"2026-07-05T05:59:06Z"},{"alias_kind":"pith_short_12","alias_value":"E4HUIJUNZ2LB","created_at":"2026-07-05T05:59:06Z"},{"alias_kind":"pith_short_16","alias_value":"E4HUIJUNZ2LBAXPI","created_at":"2026-07-05T05:59:06Z"},{"alias_kind":"pith_short_8","alias_value":"E4HUIJUN","created_at":"2026-07-05T05:59:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:E4HUIJUNZ2LBAXPIHOJL3RMM7S","target":"record","payload":{"canonical_record":{"source":{"id":"2301.08968","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-21T16:20:57Z","cross_cats_sorted":[],"title_canon_sha256":"5204537cb41bd404e182382f5ed56c9f86c8c336c93184e564fa7ebb68c615ce","abstract_canon_sha256":"52079d7d527a726196af2f14a32f6fac0668fef4a1865e0c1f59bbc1872c446b"},"schema_version":"1.0"},"canonical_sha256":"270f44268dce96105de83b92bdc58cfca2ccddd6e7478d1df4e7d8d2765250b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:06.098399Z","signature_b64":"JnNvyBSwTyP7I/gWgTN2HZpqCXdwqYS9OEUC85nAHaDqY1zHZX5lDuiE+muH722IrRIhIbCfTrsPCM+wMlIiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"270f44268dce96105de83b92bdc58cfca2ccddd6e7478d1df4e7d8d2765250b0","last_reissued_at":"2026-07-05T05:59:06.097899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:06.097899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.08968","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:59:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxWoht39f+mzcf2yQmARxMTgjo8Dr5CQch2hI7RUvJuF9rooghBQqdNEQEPu95ip563/ojxCpUYyfd9xlGY6Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:04:58.609792Z"},"content_sha256":"f026227d69f5edceb8c5bf612479970f00ce4b76ae396faa16fec7079e315779","schema_version":"1.0","event_id":"sha256:f026227d69f5edceb8c5bf612479970f00ce4b76ae396faa16fec7079e315779"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:E4HUIJUNZ2LBAXPIHOJL3RMM7S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haris Vikalo, Huancheng Chen, Johnny (Chaining) Wang","submitted_at":"2023-01-21T16:20:57Z","abstract_excerpt":"Heterogeneity of data distributed across clients limits the performance of global models trained through federated learning, especially in the settings with highly imbalanced class distributions of local datasets. In recent years, personalized federated learning (pFL) has emerged as a potential solution to the challenges presented by heterogeneous data. However, existing pFL methods typically enhance performance of local models at the expense of the global model's accuracy. We propose FedHKD (Federated Hyper-Knowledge Distillation), a novel FL algorithm in which clients rely on knowledge disti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08968","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2301.08968/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:59:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XHRWBHcmtljMXMZbkUSI0h/DV40t8SRVFDceRVef+tLWLPaJY5IdkIW09+qnI5Q3UwixuRduz7JtMp/hprr2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:04:58.610396Z"},"content_sha256":"ffb4f238bc2682886bd72ee17879e2b97ba641fd56cb56999b0e3d71e70b9e3b","schema_version":"1.0","event_id":"sha256:ffb4f238bc2682886bd72ee17879e2b97ba641fd56cb56999b0e3d71e70b9e3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E4HUIJUNZ2LBAXPIHOJL3RMM7S/bundle.json","state_url":"https://pith.science/pith/E4HUIJUNZ2LBAXPIHOJL3RMM7S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E4HUIJUNZ2LBAXPIHOJL3RMM7S/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T10:04:58Z","links":{"resolver":"https://pith.science/pith/E4HUIJUNZ2LBAXPIHOJL3RMM7S","bundle":"https://pith.science/pith/E4HUIJUNZ2LBAXPIHOJL3RMM7S/bundle.json","state":"https://pith.science/pith/E4HUIJUNZ2LBAXPIHOJL3RMM7S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E4HUIJUNZ2LBAXPIHOJL3RMM7S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E4HUIJUNZ2LBAXPIHOJL3RMM7S","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":"52079d7d527a726196af2f14a32f6fac0668fef4a1865e0c1f59bbc1872c446b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-21T16:20:57Z","title_canon_sha256":"5204537cb41bd404e182382f5ed56c9f86c8c336c93184e564fa7ebb68c615ce"},"schema_version":"1.0","source":{"id":"2301.08968","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08968","created_at":"2026-07-05T05:59:06Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08968v2","created_at":"2026-07-05T05:59:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08968","created_at":"2026-07-05T05:59:06Z"},{"alias_kind":"pith_short_12","alias_value":"E4HUIJUNZ2LB","created_at":"2026-07-05T05:59:06Z"},{"alias_kind":"pith_short_16","alias_value":"E4HUIJUNZ2LBAXPI","created_at":"2026-07-05T05:59:06Z"},{"alias_kind":"pith_short_8","alias_value":"E4HUIJUN","created_at":"2026-07-05T05:59:06Z"}],"graph_snapshots":[{"event_id":"sha256:ffb4f238bc2682886bd72ee17879e2b97ba641fd56cb56999b0e3d71e70b9e3b","target":"graph","created_at":"2026-07-05T05:59:06Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2301.08968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Heterogeneity of data distributed across clients limits the performance of global models trained through federated learning, especially in the settings with highly imbalanced class distributions of local datasets. In recent years, personalized federated learning (pFL) has emerged as a potential solution to the challenges presented by heterogeneous data. However, existing pFL methods typically enhance performance of local models at the expense of the global model's accuracy. We propose FedHKD (Federated Hyper-Knowledge Distillation), a novel FL algorithm in which clients rely on knowledge disti","authors_text":"Haris Vikalo, Huancheng Chen, Johnny (Chaining) Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-21T16:20:57Z","title":"The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08968","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f026227d69f5edceb8c5bf612479970f00ce4b76ae396faa16fec7079e315779","target":"record","created_at":"2026-07-05T05:59:06Z","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":"52079d7d527a726196af2f14a32f6fac0668fef4a1865e0c1f59bbc1872c446b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-21T16:20:57Z","title_canon_sha256":"5204537cb41bd404e182382f5ed56c9f86c8c336c93184e564fa7ebb68c615ce"},"schema_version":"1.0","source":{"id":"2301.08968","kind":"arxiv","version":2}},"canonical_sha256":"270f44268dce96105de83b92bdc58cfca2ccddd6e7478d1df4e7d8d2765250b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"270f44268dce96105de83b92bdc58cfca2ccddd6e7478d1df4e7d8d2765250b0","first_computed_at":"2026-07-05T05:59:06.097899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:06.097899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JnNvyBSwTyP7I/gWgTN2HZpqCXdwqYS9OEUC85nAHaDqY1zHZX5lDuiE+muH722IrRIhIbCfTrsPCM+wMlIiBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:06.098399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.08968","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f026227d69f5edceb8c5bf612479970f00ce4b76ae396faa16fec7079e315779","sha256:ffb4f238bc2682886bd72ee17879e2b97ba641fd56cb56999b0e3d71e70b9e3b"],"state_sha256":"6b0042a6c31e5ad6def5301700ad1f0eef733b7fa01e5b871628043c5b6c57ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D2apHzjosY26AUEAMdGapglUIfQrasEqHj92m7t4SQXbaP2Mr0e+m2KYZNIV6Cy75TLzttR4kjKHzHK8dqbyAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:04:58.614966Z","bundle_sha256":"4c7832b3317940908c9acd08fd3646b717967e5c6e60e149d6ab30acdb2ade15"}}