{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JC6IYE4DGRH5EMDF2BIERXPYPS","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":"2aeb3a4804dda085f6efdf618d4e061bc3d1137aac260836dc6e5601ada5daa0","cross_cats_sorted":["cs.DC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-12-02T14:29:00Z","title_canon_sha256":"aaff00967d94412e74e8775461e4dd1f418194cb3260248c9afd35e76343df94"},"schema_version":"1.0","source":{"id":"1912.00818","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.00818","created_at":"2026-05-18T03:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"1912.00818v1","created_at":"2026-05-18T03:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00818","created_at":"2026-05-18T03:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"JC6IYE4DGRH5","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"JC6IYE4DGRH5EMDF","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"JC6IYE4D","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:39e89a2c37b9b624f9d54a7f66c3be77cde5ac679156fcf5a3a8ab351cac5766","target":"graph","created_at":"2026-05-18T03:38:44Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"FedPer, a base + personalization layer approach for federated training of deep feedforward neural networks, can combat the ill-effects of statistical heterogeneity."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That splitting the network into shared base layers and local personalization layers is sufficient to overcome statistical heterogeneity without needing additional regularization or adaptation mechanisms."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"FedPer uses shared base layers and per-user personalization layers to enable effective federated training of deep networks despite non-identical data distributions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Splitting neural networks into shared base layers and local personalization layers enables effective federated learning despite statistical heterogeneity."}],"snapshot_sha256":"61ac1e2e4a09c5ee3b39ca5bd13a17300c8725c826d6a94ac6e7860ff1a6b2c5"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d3ff59f67d7f74a9a0cbb7607b0f4d968a2c83a4304a5167985600e493440150"},"paper":{"abstract_excerpt":"The emerging paradigm of federated learning strives to enable collaborative training of machine learning models on the network edge without centrally aggregating raw data and hence, improving data privacy. This sharply deviates from traditional machine learning and necessitates the design of algorithms robust to various sources of heterogeneity. Specifically, statistical heterogeneity of data across user devices can severely degrade the performance of standard federated averaging for traditional machine learning applications like personalization with deep learning. This paper pro-posesFedPer, ","authors_text":"Aaditya Kumar Singh, Manoj Ghuhan Arivazhagan, Sunav Choudhary, Vinay Aggarwal","cross_cats":["cs.DC","stat.ML"],"headline":"Splitting neural networks into shared base layers and local personalization layers enables effective federated learning despite statistical heterogeneity.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-12-02T14:29:00Z","title":"Federated Learning with Personalization Layers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00818","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-13T23:36:31.962727Z","id":"b16644ba-a58c-4ccd-9adc-78567b50fd2f","model_set":{"reader":"grok-4.3"},"one_line_summary":"FedPer uses shared base layers and per-user personalization layers to enable effective federated training of deep networks despite non-identical data distributions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Splitting neural networks into shared base layers and local personalization layers enables effective federated learning despite statistical heterogeneity.","strongest_claim":"FedPer, a base + personalization layer approach for federated training of deep feedforward neural networks, can combat the ill-effects of statistical heterogeneity.","weakest_assumption":"That splitting the network into shared base layers and local personalization layers is sufficient to overcome statistical heterogeneity without needing additional regularization or adaptation mechanisms."}},"verdict_id":"b16644ba-a58c-4ccd-9adc-78567b50fd2f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2743515c68c10a926f45f8952a336fc96b91ac93c840f46e9109e3d1013db3e8","target":"record","created_at":"2026-05-18T03:38:44Z","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":"2aeb3a4804dda085f6efdf618d4e061bc3d1137aac260836dc6e5601ada5daa0","cross_cats_sorted":["cs.DC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-12-02T14:29:00Z","title_canon_sha256":"aaff00967d94412e74e8775461e4dd1f418194cb3260248c9afd35e76343df94"},"schema_version":"1.0","source":{"id":"1912.00818","kind":"arxiv","version":1}},"canonical_sha256":"48bc8c1383344fd23065d05048ddf87cbbb054507dfa6936e59f1ac47f0fde0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48bc8c1383344fd23065d05048ddf87cbbb054507dfa6936e59f1ac47f0fde0f","first_computed_at":"2026-05-18T03:38:44.381648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:38:44.381648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z5fe/Xts9h6kQ6XJoGx9RAASpJGBgcWgt8TjwY/krQPGNlRhRqPqg5At1zSJHdYeCp+axHd27i/gChXVKFwBDg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:38:44.382167Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.00818","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2743515c68c10a926f45f8952a336fc96b91ac93c840f46e9109e3d1013db3e8","sha256:39e89a2c37b9b624f9d54a7f66c3be77cde5ac679156fcf5a3a8ab351cac5766"],"state_sha256":"0be5993b7a543ef38bf5cb40b9e14431ac3c5091da9aa3f4077fe54af1bc378b"}