{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:35GLOGLLSI6EQVDWLOO3NKPFCT","short_pith_number":"pith:35GLOGLL","canonical_record":{"source":{"id":"2110.15545","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-29T05:25:44Z","cross_cats_sorted":[],"title_canon_sha256":"45b3767dc1d4beef07e1e3d9c033eeee2ab36871261b2b270d1d9e2244defe7f","abstract_canon_sha256":"7523ed2c5e09edc583ce6c9b7e5f56afd02e3af885652128459a2356be43b9b6"},"schema_version":"1.0"},"canonical_sha256":"df4cb7196b923c4854765b9db6a9e514ea0938464bbe46cc2124f99c893362b7","source":{"kind":"arxiv","id":"2110.15545","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.15545","created_at":"2026-07-05T05:23:07Z"},{"alias_kind":"arxiv_version","alias_value":"2110.15545v3","created_at":"2026-07-05T05:23:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15545","created_at":"2026-07-05T05:23:07Z"},{"alias_kind":"pith_short_12","alias_value":"35GLOGLLSI6E","created_at":"2026-07-05T05:23:07Z"},{"alias_kind":"pith_short_16","alias_value":"35GLOGLLSI6EQVDW","created_at":"2026-07-05T05:23:07Z"},{"alias_kind":"pith_short_8","alias_value":"35GLOGLL","created_at":"2026-07-05T05:23:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:35GLOGLLSI6EQVDWLOO3NKPFCT","target":"record","payload":{"canonical_record":{"source":{"id":"2110.15545","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-29T05:25:44Z","cross_cats_sorted":[],"title_canon_sha256":"45b3767dc1d4beef07e1e3d9c033eeee2ab36871261b2b270d1d9e2244defe7f","abstract_canon_sha256":"7523ed2c5e09edc583ce6c9b7e5f56afd02e3af885652128459a2356be43b9b6"},"schema_version":"1.0"},"canonical_sha256":"df4cb7196b923c4854765b9db6a9e514ea0938464bbe46cc2124f99c893362b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:07.341625Z","signature_b64":"TlloXfIMmnlOm+3DtLA+KarnYYvpBR1V8uNLVJYqHF+dZxMESk0VWTD10sms9xt5qhOVRppjCeI4n0SaHdrwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df4cb7196b923c4854765b9db6a9e514ea0938464bbe46cc2124f99c893362b7","last_reissued_at":"2026-07-05T05:23:07.341183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:07.341183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.15545","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:23:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UZzzlaxnOUGyvNSOIvP7RwUVAHQuffxaEJ0hZszycj1bDTgrL2xA7ClXw5JJcPkQgrrZdRzPUYCUcoEFPoQlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:53:23.158453Z"},"content_sha256":"0b723e7c395c727f0ff44f2dbc4ea31aeebfef5a5c6682f1cf4f88c8d4d23eeb","schema_version":"1.0","event_id":"sha256:0b723e7c395c727f0ff44f2dbc4ea31aeebfef5a5c6682f1cf4f88c8d4d23eeb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:35GLOGLLSI6EQVDWLOO3NKPFCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Fairness via Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongxu Chen, Kangwook Lee, Yuchen Zeng","submitted_at":"2021-10-29T05:25:44Z","abstract_excerpt":"Recently, lots of algorithms have been proposed for learning a fair classifier from decentralized data. However, many theoretical and algorithmic questions remain open. First, is federated learning necessary, i.e., can we simply train locally fair classifiers and aggregate them? In this work, we first propose a new theoretical framework, with which we demonstrate that federated learning can strictly boost model fairness compared with such non-federated algorithms. We then theoretically and empirically show that the performance tradeoff of FedAvg-based fair learning algorithms is strictly worse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15545","kind":"arxiv","version":3},"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/2110.15545/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":"2026-07-05T05:23:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lJ6iTCy1gbKeUXmb0JxoCb2F4SZNMC55e3MdBbOBXdZHs9VwKdHcYSztf66ks6cMTxxz0KyXQpIezNVqe0nIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:53:23.159037Z"},"content_sha256":"4e90e59eb646604406b316a0cf3074ea762678ad704713b1fc17f4837dc03122","schema_version":"1.0","event_id":"sha256:4e90e59eb646604406b316a0cf3074ea762678ad704713b1fc17f4837dc03122"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/35GLOGLLSI6EQVDWLOO3NKPFCT/bundle.json","state_url":"https://pith.science/pith/35GLOGLLSI6EQVDWLOO3NKPFCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/35GLOGLLSI6EQVDWLOO3NKPFCT/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":"2026-08-11T19:53:23Z","links":{"resolver":"https://pith.science/pith/35GLOGLLSI6EQVDWLOO3NKPFCT","bundle":"https://pith.science/pith/35GLOGLLSI6EQVDWLOO3NKPFCT/bundle.json","state":"https://pith.science/pith/35GLOGLLSI6EQVDWLOO3NKPFCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/35GLOGLLSI6EQVDWLOO3NKPFCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:35GLOGLLSI6EQVDWLOO3NKPFCT","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":"7523ed2c5e09edc583ce6c9b7e5f56afd02e3af885652128459a2356be43b9b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-29T05:25:44Z","title_canon_sha256":"45b3767dc1d4beef07e1e3d9c033eeee2ab36871261b2b270d1d9e2244defe7f"},"schema_version":"1.0","source":{"id":"2110.15545","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.15545","created_at":"2026-07-05T05:23:07Z"},{"alias_kind":"arxiv_version","alias_value":"2110.15545v3","created_at":"2026-07-05T05:23:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15545","created_at":"2026-07-05T05:23:07Z"},{"alias_kind":"pith_short_12","alias_value":"35GLOGLLSI6E","created_at":"2026-07-05T05:23:07Z"},{"alias_kind":"pith_short_16","alias_value":"35GLOGLLSI6EQVDW","created_at":"2026-07-05T05:23:07Z"},{"alias_kind":"pith_short_8","alias_value":"35GLOGLL","created_at":"2026-07-05T05:23:07Z"}],"graph_snapshots":[{"event_id":"sha256:4e90e59eb646604406b316a0cf3074ea762678ad704713b1fc17f4837dc03122","target":"graph","created_at":"2026-07-05T05:23:07Z","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/2110.15545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, lots of algorithms have been proposed for learning a fair classifier from decentralized data. However, many theoretical and algorithmic questions remain open. First, is federated learning necessary, i.e., can we simply train locally fair classifiers and aggregate them? In this work, we first propose a new theoretical framework, with which we demonstrate that federated learning can strictly boost model fairness compared with such non-federated algorithms. We then theoretically and empirically show that the performance tradeoff of FedAvg-based fair learning algorithms is strictly worse","authors_text":"Hongxu Chen, Kangwook Lee, Yuchen Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-29T05:25:44Z","title":"Improving Fairness via Federated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15545","kind":"arxiv","version":3},"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":"sha256:0b723e7c395c727f0ff44f2dbc4ea31aeebfef5a5c6682f1cf4f88c8d4d23eeb","target":"record","created_at":"2026-07-05T05:23:07Z","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":"7523ed2c5e09edc583ce6c9b7e5f56afd02e3af885652128459a2356be43b9b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-29T05:25:44Z","title_canon_sha256":"45b3767dc1d4beef07e1e3d9c033eeee2ab36871261b2b270d1d9e2244defe7f"},"schema_version":"1.0","source":{"id":"2110.15545","kind":"arxiv","version":3}},"canonical_sha256":"df4cb7196b923c4854765b9db6a9e514ea0938464bbe46cc2124f99c893362b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df4cb7196b923c4854765b9db6a9e514ea0938464bbe46cc2124f99c893362b7","first_computed_at":"2026-07-05T05:23:07.341183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:07.341183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TlloXfIMmnlOm+3DtLA+KarnYYvpBR1V8uNLVJYqHF+dZxMESk0VWTD10sms9xt5qhOVRppjCeI4n0SaHdrwDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:07.341625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.15545","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b723e7c395c727f0ff44f2dbc4ea31aeebfef5a5c6682f1cf4f88c8d4d23eeb","sha256:4e90e59eb646604406b316a0cf3074ea762678ad704713b1fc17f4837dc03122"],"state_sha256":"9b913dc016a9ade34dce5cd50dd597eb4a002a50373d42055bd84177aa57c7cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"otxzmVJKeDbHNACfVFbP5fRQBdNU7RT57+mK2LV/OPOsJAoDPTAvSGdGmhpH/Az1Sli+J4MSjXsWqy/wJW7hCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:53:23.163066Z","bundle_sha256":"125dfe47894c0f4bf13f10c85b50194f066136d4f1b548cda6e417f56545d0b8"}}