{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VF5BICUZLUXC7MPUEPKXUM5L4E","short_pith_number":"pith:VF5BICUZ","canonical_record":{"source":{"id":"2109.05613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-12T21:06:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7223a7739b876529daee6df2203e1875b16861517da4fda51453053a2a675eb4","abstract_canon_sha256":"477733eb7497018fe22d7fb896dd59cfb635cbd8c269b7ca34d9d3bdc7e68099"},"schema_version":"1.0"},"canonical_sha256":"a97a140a995d2e2fb1f423d57a33abe12663a4f01dfb146e79c3c9d73711ce10","source":{"kind":"arxiv","id":"2109.05613","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.05613","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2109.05613v1","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05613","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"VF5BICUZLUXC","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"VF5BICUZLUXC7MPU","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"VF5BICUZ","created_at":"2026-07-05T03:13:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VF5BICUZLUXC7MPUEPKXUM5L4E","target":"record","payload":{"canonical_record":{"source":{"id":"2109.05613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-12T21:06:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7223a7739b876529daee6df2203e1875b16861517da4fda51453053a2a675eb4","abstract_canon_sha256":"477733eb7497018fe22d7fb896dd59cfb635cbd8c269b7ca34d9d3bdc7e68099"},"schema_version":"1.0"},"canonical_sha256":"a97a140a995d2e2fb1f423d57a33abe12663a4f01dfb146e79c3c9d73711ce10","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:40.545236Z","signature_b64":"rmOHlYso67YTUe54E3ctEvffeiBmiW2OE9yqaT/qblegmU4SwybKSC0BSew6nTltrFKZ/qXfL1XUm8qrGFg7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a97a140a995d2e2fb1f423d57a33abe12663a4f01dfb146e79c3c9d73711ce10","last_reissued_at":"2026-07-05T03:13:40.544865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:40.544865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.05613","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":"2026-07-05T03:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GHDgZUwBtXfrMzCzhrnbIm1vFi4Ka7QzNoz+yOW3un30qHZHpTKPj9+90aQ2OFSCMFhvElqKW0NW10z6fAMXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:12:01.573328Z"},"content_sha256":"47f48047cfad76866b4aa270f20aaa34be36e6768f9be5c2dbaee0aaee089b14","schema_version":"1.0","event_id":"sha256:47f48047cfad76866b4aa270f20aaa34be36e6768f9be5c2dbaee0aaee089b14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VF5BICUZLUXC7MPUEPKXUM5L4E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Critical Learning Periods in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gang Yan, Hao Wang, Jian Li","submitted_at":"2021-09-12T21:06:07Z","abstract_excerpt":"Federated learning (FL) is a popular technique to train machine learning (ML) models with decentralized data. Extensive works have studied the performance of the global model; however, it is still unclear how the training process affects the final test accuracy. Exacerbating this problem is the fact that FL executions differ significantly from traditional ML with heterogeneous data characteristics across clients, involving more hyperparameters. In this work, we show that the final test accuracy of FL is dramatically affected by the early phase of the training process, i.e., FL exhibits critica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05613","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/2109.05613/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":"2026-07-05T03:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iu0PsjcytpWgcw2V+62pFSsIhuWtZLty/pqywEZ2LqOb5uuth21xtLl01d7f6PHOK082DODJITxXa1nE3rniCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:12:01.573964Z"},"content_sha256":"bb0cba8eb7fdc44558f79b7cb1d69b56d10625c1530b4e33763f600168d10fd2","schema_version":"1.0","event_id":"sha256:bb0cba8eb7fdc44558f79b7cb1d69b56d10625c1530b4e33763f600168d10fd2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VF5BICUZLUXC7MPUEPKXUM5L4E/bundle.json","state_url":"https://pith.science/pith/VF5BICUZLUXC7MPUEPKXUM5L4E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VF5BICUZLUXC7MPUEPKXUM5L4E/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":"2026-08-09T05:12:01Z","links":{"resolver":"https://pith.science/pith/VF5BICUZLUXC7MPUEPKXUM5L4E","bundle":"https://pith.science/pith/VF5BICUZLUXC7MPUEPKXUM5L4E/bundle.json","state":"https://pith.science/pith/VF5BICUZLUXC7MPUEPKXUM5L4E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VF5BICUZLUXC7MPUEPKXUM5L4E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VF5BICUZLUXC7MPUEPKXUM5L4E","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":"477733eb7497018fe22d7fb896dd59cfb635cbd8c269b7ca34d9d3bdc7e68099","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-12T21:06:07Z","title_canon_sha256":"7223a7739b876529daee6df2203e1875b16861517da4fda51453053a2a675eb4"},"schema_version":"1.0","source":{"id":"2109.05613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.05613","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2109.05613v1","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05613","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"VF5BICUZLUXC","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"VF5BICUZLUXC7MPU","created_at":"2026-07-05T03:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"VF5BICUZ","created_at":"2026-07-05T03:13:40Z"}],"graph_snapshots":[{"event_id":"sha256:bb0cba8eb7fdc44558f79b7cb1d69b56d10625c1530b4e33763f600168d10fd2","target":"graph","created_at":"2026-07-05T03:13:40Z","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/2109.05613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated learning (FL) is a popular technique to train machine learning (ML) models with decentralized data. Extensive works have studied the performance of the global model; however, it is still unclear how the training process affects the final test accuracy. Exacerbating this problem is the fact that FL executions differ significantly from traditional ML with heterogeneous data characteristics across clients, involving more hyperparameters. In this work, we show that the final test accuracy of FL is dramatically affected by the early phase of the training process, i.e., FL exhibits critica","authors_text":"Gang Yan, Hao Wang, Jian Li","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-12T21:06:07Z","title":"Critical Learning Periods in Federated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05613","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":"sha256:47f48047cfad76866b4aa270f20aaa34be36e6768f9be5c2dbaee0aaee089b14","target":"record","created_at":"2026-07-05T03:13:40Z","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":"477733eb7497018fe22d7fb896dd59cfb635cbd8c269b7ca34d9d3bdc7e68099","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-12T21:06:07Z","title_canon_sha256":"7223a7739b876529daee6df2203e1875b16861517da4fda51453053a2a675eb4"},"schema_version":"1.0","source":{"id":"2109.05613","kind":"arxiv","version":1}},"canonical_sha256":"a97a140a995d2e2fb1f423d57a33abe12663a4f01dfb146e79c3c9d73711ce10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a97a140a995d2e2fb1f423d57a33abe12663a4f01dfb146e79c3c9d73711ce10","first_computed_at":"2026-07-05T03:13:40.544865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:40.544865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rmOHlYso67YTUe54E3ctEvffeiBmiW2OE9yqaT/qblegmU4SwybKSC0BSew6nTltrFKZ/qXfL1XUm8qrGFg7CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:40.545236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.05613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47f48047cfad76866b4aa270f20aaa34be36e6768f9be5c2dbaee0aaee089b14","sha256:bb0cba8eb7fdc44558f79b7cb1d69b56d10625c1530b4e33763f600168d10fd2"],"state_sha256":"3d2cb2048f390135437741be1c934f64e5e2d1426ae2307ee3b07dfacd0fec88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aFvVAwvbGHNoMCRa/nqEIhj/fikZo7WSb7s+3aF4dRM47lgfpiYfVBXgp+nWhbJw1/PRbml21WTGuEdlFZhjCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:12:01.578460Z","bundle_sha256":"c055a0e6a370cb13c6ed4a36992abc248b1d1715d1eb460bc2dfc155787b0032"}}