{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2ZRZXK6HGZ7OJMMDXINDZUQ53Z","short_pith_number":"pith:2ZRZXK6H","canonical_record":{"source":{"id":"1902.00146","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T01:34:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6883be1ed61c80240a8e103b179d4bce6fac52cb7dbfd6bdd3b98437b696d9a9","abstract_canon_sha256":"7f945992eda1d37de39f8f8b2428aad83af12d117f816ac246d2ba37d3946bc4"},"schema_version":"1.0"},"canonical_sha256":"d6639babc7367ee4b183ba1a3cd21dde573044dd57d566c93113dc21b14a61dd","source":{"kind":"arxiv","id":"1902.00146","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00146","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00146v1","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00146","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"2ZRZXK6HGZ7O","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2ZRZXK6HGZ7OJMMD","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2ZRZXK6H","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2ZRZXK6HGZ7OJMMDXINDZUQ53Z","target":"record","payload":{"canonical_record":{"source":{"id":"1902.00146","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T01:34:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6883be1ed61c80240a8e103b179d4bce6fac52cb7dbfd6bdd3b98437b696d9a9","abstract_canon_sha256":"7f945992eda1d37de39f8f8b2428aad83af12d117f816ac246d2ba37d3946bc4"},"schema_version":"1.0"},"canonical_sha256":"d6639babc7367ee4b183ba1a3cd21dde573044dd57d566c93113dc21b14a61dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:58.194439Z","signature_b64":"K+kaUY4upD/I4RxYzVOkeaE0ZFqPzXGfIq4WKAdAmmrYRCkf/c8OBD36ov1NjWrbtUsNcxz7l1IhaELf6kd4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6639babc7367ee4b183ba1a3cd21dde573044dd57d566c93113dc21b14a61dd","last_reissued_at":"2026-05-17T23:54:58.193938Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:58.193938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.00146","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":"2026-05-17T23:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mpAPWwLd1ONp6njclpWu0FVW6FbSXHZKedNLJ6iZtOwvU/urrXoo9RFItN6vBgIvYVzbAdPPK+ewhbMDbncEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T15:58:06.788719Z"},"content_sha256":"3965da0ad3f70036631d1164ddcbcacdcbae4235b0b882332298cb17b31baa3e","schema_version":"1.0","event_id":"sha256:3965da0ad3f70036631d1164ddcbcacdcbae4235b0b882332298cb17b31baa3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2ZRZXK6HGZ7OJMMDXINDZUQ53Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agnostic Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ananda Theertha Suresh, Gary Sivek, Mehryar Mohri","submitted_at":"2019-02-01T01:34:49Z","abstract_excerpt":"A key learning scenario in large-scale applications is that of federated learning, where a centralized model is trained based on data originating from a large number of clients. We argue that, with the existing training and inference, federated models can be biased towards different clients. Instead, we propose a new framework of agnostic federated learning, where the centralized model is optimized for any target distribution formed by a mixture of the client distributions. We further show that this framework naturally yields a notion of fairness. We present data-dependent Rademacher complexit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00146","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":""},"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":"2026-05-17T23:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T3datUfBC+5pyTQ4RGde24cazaBbOoAaWgWnEAIsIKPcUT4gUNAHCZxCyPAjPQKG1VAiNQXZhZ9VH82ztjueBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T15:58:06.789059Z"},"content_sha256":"e4adfe4d37473064cdb63ca5b6eb507b846f0ae03f6af041eff5a0956b569d6e","schema_version":"1.0","event_id":"sha256:e4adfe4d37473064cdb63ca5b6eb507b846f0ae03f6af041eff5a0956b569d6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2ZRZXK6HGZ7OJMMDXINDZUQ53Z/bundle.json","state_url":"https://pith.science/pith/2ZRZXK6HGZ7OJMMDXINDZUQ53Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2ZRZXK6HGZ7OJMMDXINDZUQ53Z/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":"2026-06-30T15:58:06Z","links":{"resolver":"https://pith.science/pith/2ZRZXK6HGZ7OJMMDXINDZUQ53Z","bundle":"https://pith.science/pith/2ZRZXK6HGZ7OJMMDXINDZUQ53Z/bundle.json","state":"https://pith.science/pith/2ZRZXK6HGZ7OJMMDXINDZUQ53Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2ZRZXK6HGZ7OJMMDXINDZUQ53Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2ZRZXK6HGZ7OJMMDXINDZUQ53Z","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":"7f945992eda1d37de39f8f8b2428aad83af12d117f816ac246d2ba37d3946bc4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T01:34:49Z","title_canon_sha256":"6883be1ed61c80240a8e103b179d4bce6fac52cb7dbfd6bdd3b98437b696d9a9"},"schema_version":"1.0","source":{"id":"1902.00146","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00146","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00146v1","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00146","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"2ZRZXK6HGZ7O","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2ZRZXK6HGZ7OJMMD","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2ZRZXK6H","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:e4adfe4d37473064cdb63ca5b6eb507b846f0ae03f6af041eff5a0956b569d6e","target":"graph","created_at":"2026-05-17T23:54:58Z","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"},"paper":{"abstract_excerpt":"A key learning scenario in large-scale applications is that of federated learning, where a centralized model is trained based on data originating from a large number of clients. We argue that, with the existing training and inference, federated models can be biased towards different clients. Instead, we propose a new framework of agnostic federated learning, where the centralized model is optimized for any target distribution formed by a mixture of the client distributions. We further show that this framework naturally yields a notion of fairness. We present data-dependent Rademacher complexit","authors_text":"Ananda Theertha Suresh, Gary Sivek, Mehryar Mohri","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T01:34:49Z","title":"Agnostic Federated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00146","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":"sha256:3965da0ad3f70036631d1164ddcbcacdcbae4235b0b882332298cb17b31baa3e","target":"record","created_at":"2026-05-17T23:54:58Z","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":"7f945992eda1d37de39f8f8b2428aad83af12d117f816ac246d2ba37d3946bc4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T01:34:49Z","title_canon_sha256":"6883be1ed61c80240a8e103b179d4bce6fac52cb7dbfd6bdd3b98437b696d9a9"},"schema_version":"1.0","source":{"id":"1902.00146","kind":"arxiv","version":1}},"canonical_sha256":"d6639babc7367ee4b183ba1a3cd21dde573044dd57d566c93113dc21b14a61dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6639babc7367ee4b183ba1a3cd21dde573044dd57d566c93113dc21b14a61dd","first_computed_at":"2026-05-17T23:54:58.193938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:58.193938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K+kaUY4upD/I4RxYzVOkeaE0ZFqPzXGfIq4WKAdAmmrYRCkf/c8OBD36ov1NjWrbtUsNcxz7l1IhaELf6kd4BA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:58.194439Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.00146","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3965da0ad3f70036631d1164ddcbcacdcbae4235b0b882332298cb17b31baa3e","sha256:e4adfe4d37473064cdb63ca5b6eb507b846f0ae03f6af041eff5a0956b569d6e"],"state_sha256":"0af965ad81735ae55fad9cdcc826eedb6cd81bab0ab82d7f5ecdd8df75039807"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PwMR4Piu1Q63QL/PmaxCqExA5VcaSuMXL8EwYK11Uy5LCcTVpJNDxJK4PMsR0oGLTqhZGNjiqjHVBw452i/zCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T15:58:06.790911Z","bundle_sha256":"d90dab24041e22ba4bdc43b6d19d96e4794553280815324ca77dc588a6f5e68b"}}