{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:F4YQDDWW5YQHK7H6IYOO6F7IBN","short_pith_number":"pith:F4YQDDWW","canonical_record":{"source":{"id":"2207.11447","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-23T07:20:22Z","cross_cats_sorted":[],"title_canon_sha256":"081135fa04d2f83aa35d71cd847b74730cb57d4ecc3da25df20419ddc3bb9380","abstract_canon_sha256":"94ce7070de624c3b1d6823441b4c9ecc7f1b3f484d4d1b8e352530cb0ef8dfc1"},"schema_version":"1.0"},"canonical_sha256":"2f31018ed6ee20757cfe461cef17e80b5734d899a140c407a5a2066eb378e4c5","source":{"kind":"arxiv","id":"2207.11447","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.11447","created_at":"2026-07-05T06:57:19Z"},{"alias_kind":"arxiv_version","alias_value":"2207.11447v2","created_at":"2026-07-05T06:57:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.11447","created_at":"2026-07-05T06:57:19Z"},{"alias_kind":"pith_short_12","alias_value":"F4YQDDWW5YQH","created_at":"2026-07-05T06:57:19Z"},{"alias_kind":"pith_short_16","alias_value":"F4YQDDWW5YQHK7H6","created_at":"2026-07-05T06:57:19Z"},{"alias_kind":"pith_short_8","alias_value":"F4YQDDWW","created_at":"2026-07-05T06:57:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:F4YQDDWW5YQHK7H6IYOO6F7IBN","target":"record","payload":{"canonical_record":{"source":{"id":"2207.11447","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-23T07:20:22Z","cross_cats_sorted":[],"title_canon_sha256":"081135fa04d2f83aa35d71cd847b74730cb57d4ecc3da25df20419ddc3bb9380","abstract_canon_sha256":"94ce7070de624c3b1d6823441b4c9ecc7f1b3f484d4d1b8e352530cb0ef8dfc1"},"schema_version":"1.0"},"canonical_sha256":"2f31018ed6ee20757cfe461cef17e80b5734d899a140c407a5a2066eb378e4c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:19.277687Z","signature_b64":"vJ1SaahDmsFtl3QznQcc5bG9YcJ8KCTxH6eco0mMcHdUXI3UpdYHyeEATpxAlvkrSobic33glTGY6HGDbZIeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f31018ed6ee20757cfe461cef17e80b5734d899a140c407a5a2066eb378e4c5","last_reissued_at":"2026-07-05T06:57:19.277206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:19.277206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.11447","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":"2026-07-05T06:57:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mKNekLSDUsc/Mxuocb+u1nw78UBJK87RdMpfqLpWZUe8Tcr1wsPuVDEdij/0Pv3OyBcvSZohlH0YR5lcUMPpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:38:42.692072Z"},"content_sha256":"74e41480d520674eeef257f8bb22b3904f23aba350f7e7ce709798c9650472d7","schema_version":"1.0","event_id":"sha256:74e41480d520674eeef257f8bb22b3904f23aba350f7e7ce709798c9650472d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:F4YQDDWW5YQHK7H6IYOO6F7IBN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Handling Data Heterogeneity in Federated Learning via Knowledge Distillation and Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cong Yang, Jingwen Shi, Xiao Zhang, Xinyu Lei, Xu Zhou, Yichun Shi","submitted_at":"2022-07-23T07:20:22Z","abstract_excerpt":"Federated learning (FL) supports distributed training of a global machine learning model across multiple devices with the help of a central server. However, data heterogeneity across different devices leads to the client model drift issue and results in model performance degradation and poor model fairness. To address the issue, we design Federated learning with global-local Knowledge Fusion (FedKF) scheme in this paper. The key idea in FedKF is to let the server return the global knowledge to be fused with the local knowledge in each training round so that the local model can be regularized t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.11447","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/2207.11447/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":"2026-07-05T06:57:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ry+AuPF5PyJwAr2Z4tfQgapVdhT+7br0tTGmPda1QLWHPM9R8sqk/KeQ9DsaVPjWbfr46v1IL1OFHfNJMaQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:38:42.692696Z"},"content_sha256":"76be9a537f9222e3bdd61bb6ef93556c72c8e03e46341b99b41a48b31b216834","schema_version":"1.0","event_id":"sha256:76be9a537f9222e3bdd61bb6ef93556c72c8e03e46341b99b41a48b31b216834"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4YQDDWW5YQHK7H6IYOO6F7IBN/bundle.json","state_url":"https://pith.science/pith/F4YQDDWW5YQHK7H6IYOO6F7IBN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4YQDDWW5YQHK7H6IYOO6F7IBN/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":"2026-08-19T03:38:42Z","links":{"resolver":"https://pith.science/pith/F4YQDDWW5YQHK7H6IYOO6F7IBN","bundle":"https://pith.science/pith/F4YQDDWW5YQHK7H6IYOO6F7IBN/bundle.json","state":"https://pith.science/pith/F4YQDDWW5YQHK7H6IYOO6F7IBN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4YQDDWW5YQHK7H6IYOO6F7IBN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F4YQDDWW5YQHK7H6IYOO6F7IBN","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":"94ce7070de624c3b1d6823441b4c9ecc7f1b3f484d4d1b8e352530cb0ef8dfc1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-23T07:20:22Z","title_canon_sha256":"081135fa04d2f83aa35d71cd847b74730cb57d4ecc3da25df20419ddc3bb9380"},"schema_version":"1.0","source":{"id":"2207.11447","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.11447","created_at":"2026-07-05T06:57:19Z"},{"alias_kind":"arxiv_version","alias_value":"2207.11447v2","created_at":"2026-07-05T06:57:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.11447","created_at":"2026-07-05T06:57:19Z"},{"alias_kind":"pith_short_12","alias_value":"F4YQDDWW5YQH","created_at":"2026-07-05T06:57:19Z"},{"alias_kind":"pith_short_16","alias_value":"F4YQDDWW5YQHK7H6","created_at":"2026-07-05T06:57:19Z"},{"alias_kind":"pith_short_8","alias_value":"F4YQDDWW","created_at":"2026-07-05T06:57:19Z"}],"graph_snapshots":[{"event_id":"sha256:76be9a537f9222e3bdd61bb6ef93556c72c8e03e46341b99b41a48b31b216834","target":"graph","created_at":"2026-07-05T06:57:19Z","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/2207.11447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated learning (FL) supports distributed training of a global machine learning model across multiple devices with the help of a central server. However, data heterogeneity across different devices leads to the client model drift issue and results in model performance degradation and poor model fairness. To address the issue, we design Federated learning with global-local Knowledge Fusion (FedKF) scheme in this paper. The key idea in FedKF is to let the server return the global knowledge to be fused with the local knowledge in each training round so that the local model can be regularized t","authors_text":"Cong Yang, Jingwen Shi, Xiao Zhang, Xinyu Lei, Xu Zhou, Yichun Shi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-23T07:20:22Z","title":"Handling Data Heterogeneity in Federated Learning via Knowledge Distillation and Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.11447","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":"sha256:74e41480d520674eeef257f8bb22b3904f23aba350f7e7ce709798c9650472d7","target":"record","created_at":"2026-07-05T06:57:19Z","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":"94ce7070de624c3b1d6823441b4c9ecc7f1b3f484d4d1b8e352530cb0ef8dfc1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-23T07:20:22Z","title_canon_sha256":"081135fa04d2f83aa35d71cd847b74730cb57d4ecc3da25df20419ddc3bb9380"},"schema_version":"1.0","source":{"id":"2207.11447","kind":"arxiv","version":2}},"canonical_sha256":"2f31018ed6ee20757cfe461cef17e80b5734d899a140c407a5a2066eb378e4c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f31018ed6ee20757cfe461cef17e80b5734d899a140c407a5a2066eb378e4c5","first_computed_at":"2026-07-05T06:57:19.277206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:19.277206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vJ1SaahDmsFtl3QznQcc5bG9YcJ8KCTxH6eco0mMcHdUXI3UpdYHyeEATpxAlvkrSobic33glTGY6HGDbZIeDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:19.277687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.11447","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74e41480d520674eeef257f8bb22b3904f23aba350f7e7ce709798c9650472d7","sha256:76be9a537f9222e3bdd61bb6ef93556c72c8e03e46341b99b41a48b31b216834"],"state_sha256":"94eb9831ec9b9f76f057aa44071b50d567daa9e636b32d818610e228b407443e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NfctcclSCwOfzs3ejevnsVLTl1RO8uhG3ZVA0Wk3iZ5IDYcO1Uwe1B7fxT3juX/uiiKmyIhm9+CHBXEaPKVEAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T03:38:42.698117Z","bundle_sha256":"81a6817fc5deea1f3429af7fb67cbb014027d94cb9b0a3802ca006b1bc2be9c9"}}