{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6LXOVYIPQN5L5OJDKMGCT3ED3P","short_pith_number":"pith:6LXOVYIP","canonical_record":{"source":{"id":"2212.08944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T20:26:18Z","cross_cats_sorted":[],"title_canon_sha256":"8951a1120c44dfafcab6587d2062fd71a0eac56349524d7d9c356236a843dd63","abstract_canon_sha256":"0928044b3c9de8b49faa231594d2625efeb2b0238ddd42c14cd9cd0831756424"},"schema_version":"1.0"},"canonical_sha256":"f2eeeae10f837abeb923530c29ec83dbc53391bca7f77d15f39a2c00d83f7631","source":{"kind":"arxiv","id":"2212.08944","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08944","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08944v1","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08944","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"pith_short_12","alias_value":"6LXOVYIPQN5L","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"pith_short_16","alias_value":"6LXOVYIPQN5L5OJD","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"pith_short_8","alias_value":"6LXOVYIP","created_at":"2026-07-05T05:26:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6LXOVYIPQN5L5OJDKMGCT3ED3P","target":"record","payload":{"canonical_record":{"source":{"id":"2212.08944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T20:26:18Z","cross_cats_sorted":[],"title_canon_sha256":"8951a1120c44dfafcab6587d2062fd71a0eac56349524d7d9c356236a843dd63","abstract_canon_sha256":"0928044b3c9de8b49faa231594d2625efeb2b0238ddd42c14cd9cd0831756424"},"schema_version":"1.0"},"canonical_sha256":"f2eeeae10f837abeb923530c29ec83dbc53391bca7f77d15f39a2c00d83f7631","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:15.931509Z","signature_b64":"GMWi0edXgyaKjRbE7CsXd9nK217JDaiNdy8+3R9xZLRbDRSpihIX1DAmCLAnh0ojqnRLz9+wPp06ffvJ7ktTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2eeeae10f837abeb923530c29ec83dbc53391bca7f77d15f39a2c00d83f7631","last_reissued_at":"2026-07-05T05:26:15.931108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:15.931108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.08944","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:26:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vPNOug6O0XViLx/Gm8NGVM7LECw6F8GzQu7d6q1SQwZ9SsbaosruxWzd8YFsZugLC2HYY5MgLQHP4gLuIJYzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:44:59.817701Z"},"content_sha256":"22ae25e08462d7c69aef12b82956cbaa0e948ee2a151a7ca09d655f3afae9cd9","schema_version":"1.0","event_id":"sha256:22ae25e08462d7c69aef12b82956cbaa0e948ee2a151a7ca09d655f3afae9cd9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6LXOVYIPQN5L5OJDKMGCT3ED3P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward Data Heterogeneity of Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Hu, Yuchuan Huang","submitted_at":"2022-12-17T20:26:18Z","abstract_excerpt":"Federated learning is a popular paradigm for machine learning. Ideally, federated learning works best when all clients share a similar data distribution. However, it is not always the case in the real world. Therefore, the topic of federated learning on heterogeneous data has gained more and more effort from both academia and industry. In this project, we first do extensive experiments to show how data skew and quantity skew will affect the performance of state-of-art federated learning algorithms. Then we propose a new algorithm FedMix which adjusts existing federated learning algorithms and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08944","kind":"arxiv","version":1},"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/2212.08944/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":"2026-07-05T05:26:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"15M8xIx1wbEZ5AoKIaGdiCr9pwlWPp3yBqP6tF/VaxhakRPYbFMNq1sgk2cJkdaSWNFxw7SSNm9YIIyTTxdZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:44:59.818225Z"},"content_sha256":"d6214aa87295764b1042c905763092ca992b721ea6039f4ab145c5f586ed515c","schema_version":"1.0","event_id":"sha256:d6214aa87295764b1042c905763092ca992b721ea6039f4ab145c5f586ed515c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6LXOVYIPQN5L5OJDKMGCT3ED3P/bundle.json","state_url":"https://pith.science/pith/6LXOVYIPQN5L5OJDKMGCT3ED3P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6LXOVYIPQN5L5OJDKMGCT3ED3P/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":"2026-08-06T11:44:59Z","links":{"resolver":"https://pith.science/pith/6LXOVYIPQN5L5OJDKMGCT3ED3P","bundle":"https://pith.science/pith/6LXOVYIPQN5L5OJDKMGCT3ED3P/bundle.json","state":"https://pith.science/pith/6LXOVYIPQN5L5OJDKMGCT3ED3P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6LXOVYIPQN5L5OJDKMGCT3ED3P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6LXOVYIPQN5L5OJDKMGCT3ED3P","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":"0928044b3c9de8b49faa231594d2625efeb2b0238ddd42c14cd9cd0831756424","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T20:26:18Z","title_canon_sha256":"8951a1120c44dfafcab6587d2062fd71a0eac56349524d7d9c356236a843dd63"},"schema_version":"1.0","source":{"id":"2212.08944","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08944","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08944v1","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08944","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"pith_short_12","alias_value":"6LXOVYIPQN5L","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"pith_short_16","alias_value":"6LXOVYIPQN5L5OJD","created_at":"2026-07-05T05:26:15Z"},{"alias_kind":"pith_short_8","alias_value":"6LXOVYIP","created_at":"2026-07-05T05:26:15Z"}],"graph_snapshots":[{"event_id":"sha256:d6214aa87295764b1042c905763092ca992b721ea6039f4ab145c5f586ed515c","target":"graph","created_at":"2026-07-05T05:26:15Z","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/2212.08944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated learning is a popular paradigm for machine learning. Ideally, federated learning works best when all clients share a similar data distribution. However, it is not always the case in the real world. Therefore, the topic of federated learning on heterogeneous data has gained more and more effort from both academia and industry. In this project, we first do extensive experiments to show how data skew and quantity skew will affect the performance of state-of-art federated learning algorithms. Then we propose a new algorithm FedMix which adjusts existing federated learning algorithms and ","authors_text":"Chen Hu, Yuchuan Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T20:26:18Z","title":"Toward Data Heterogeneity of Federated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08944","kind":"arxiv","version":1},"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":"sha256:22ae25e08462d7c69aef12b82956cbaa0e948ee2a151a7ca09d655f3afae9cd9","target":"record","created_at":"2026-07-05T05:26:15Z","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":"0928044b3c9de8b49faa231594d2625efeb2b0238ddd42c14cd9cd0831756424","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T20:26:18Z","title_canon_sha256":"8951a1120c44dfafcab6587d2062fd71a0eac56349524d7d9c356236a843dd63"},"schema_version":"1.0","source":{"id":"2212.08944","kind":"arxiv","version":1}},"canonical_sha256":"f2eeeae10f837abeb923530c29ec83dbc53391bca7f77d15f39a2c00d83f7631","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2eeeae10f837abeb923530c29ec83dbc53391bca7f77d15f39a2c00d83f7631","first_computed_at":"2026-07-05T05:26:15.931108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:15.931108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GMWi0edXgyaKjRbE7CsXd9nK217JDaiNdy8+3R9xZLRbDRSpihIX1DAmCLAnh0ojqnRLz9+wPp06ffvJ7ktTAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:15.931509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08944","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22ae25e08462d7c69aef12b82956cbaa0e948ee2a151a7ca09d655f3afae9cd9","sha256:d6214aa87295764b1042c905763092ca992b721ea6039f4ab145c5f586ed515c"],"state_sha256":"37ee4ea5b357bf9293add19fd96523808a72c79e043bc21290dcd2c2c4c83063"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J2IhkrvG7guExoQoF9zlNOhLb1LIXPPIjKghVOyuRXf7Hf2vC9XK8vwxc7stsbcFD6ScAuYpvzMJuoIr4aQECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T11:44:59.822853Z","bundle_sha256":"e7a1aa8aa239b2fefca9544e8c2b999a84444b66b1f113b52e5cf05e563d3dbb"}}