{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:U6KYBAPM4RUYQU6CMOO2RTGV3R","short_pith_number":"pith:U6KYBAPM","schema_version":"1.0","canonical_sha256":"a7958081ece4698853c2639da8ccd5dc7dabc4cec0594fb411d9121b4e7dd802","source":{"kind":"arxiv","id":"2206.09262","version":6},"attestation_state":"computed","paper":{"title":"Motley: Benchmarking Heterogeneity and Personalization in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Shanshan Wu, Tian Li, Virginia Smith, Yu Xiao, Zachary Charles, Zheng Xu, Ziyu Liu","submitted_at":"2022-06-18T18:18:49Z","abstract_excerpt":"Personalized federated learning considers learning models unique to each client in a heterogeneous network. The resulting client-specific models have been purported to improve metrics such as accuracy, fairness, and robustness in federated networks. However, despite a plethora of work in this area, it remains unclear: (1) which personalization techniques are most effective in various settings, and (2) how important personalization truly is for realistic federated applications. To better answer these questions, we propose Motley, a benchmark for personalized federated learning. Motley consists "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.09262","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-18T18:18:49Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"a6f1843b29da71de4f31f964baec9b382591c67fe85880ced67a7dfb5a8c8268","abstract_canon_sha256":"50a7ca9c370551369f4cbc5365a93126d06fcef952f2fe591b92357eaa46d04c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:43.590782Z","signature_b64":"IrklJSowhpbqk1SWik0lW9xYZSYUnT5QlTDbym0xFLPVvqRZ4q2A1FORxTrMU6T/22la93JdCOypTj8ZlvC9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7958081ece4698853c2639da8ccd5dc7dabc4cec0594fb411d9121b4e7dd802","last_reissued_at":"2026-07-05T05:00:43.590271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:43.590271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motley: Benchmarking Heterogeneity and Personalization in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Shanshan Wu, Tian Li, Virginia Smith, Yu Xiao, Zachary Charles, Zheng Xu, Ziyu Liu","submitted_at":"2022-06-18T18:18:49Z","abstract_excerpt":"Personalized federated learning considers learning models unique to each client in a heterogeneous network. The resulting client-specific models have been purported to improve metrics such as accuracy, fairness, and robustness in federated networks. However, despite a plethora of work in this area, it remains unclear: (1) which personalization techniques are most effective in various settings, and (2) how important personalization truly is for realistic federated applications. To better answer these questions, we propose Motley, a benchmark for personalized federated learning. Motley consists "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09262","kind":"arxiv","version":6},"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/2206.09262/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.09262","created_at":"2026-07-05T05:00:43.590340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.09262v6","created_at":"2026-07-05T05:00:43.590340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09262","created_at":"2026-07-05T05:00:43.590340+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6KYBAPM4RUY","created_at":"2026-07-05T05:00:43.590340+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6KYBAPM4RUYQU6C","created_at":"2026-07-05T05:00:43.590340+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6KYBAPM","created_at":"2026-07-05T05:00:43.590340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06183","citing_title":"Differentially Private Federated Clustering with Random Rebalancing","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6KYBAPM4RUYQU6CMOO2RTGV3R","json":"https://pith.science/pith/U6KYBAPM4RUYQU6CMOO2RTGV3R.json","graph_json":"https://pith.science/api/pith-number/U6KYBAPM4RUYQU6CMOO2RTGV3R/graph.json","events_json":"https://pith.science/api/pith-number/U6KYBAPM4RUYQU6CMOO2RTGV3R/events.json","paper":"https://pith.science/paper/U6KYBAPM"},"agent_actions":{"view_html":"https://pith.science/pith/U6KYBAPM4RUYQU6CMOO2RTGV3R","download_json":"https://pith.science/pith/U6KYBAPM4RUYQU6CMOO2RTGV3R.json","view_paper":"https://pith.science/paper/U6KYBAPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.09262&json=true","fetch_graph":"https://pith.science/api/pith-number/U6KYBAPM4RUYQU6CMOO2RTGV3R/graph.json","fetch_events":"https://pith.science/api/pith-number/U6KYBAPM4RUYQU6CMOO2RTGV3R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6KYBAPM4RUYQU6CMOO2RTGV3R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6KYBAPM4RUYQU6CMOO2RTGV3R/action/storage_attestation","attest_author":"https://pith.science/pith/U6KYBAPM4RUYQU6CMOO2RTGV3R/action/author_attestation","sign_citation":"https://pith.science/pith/U6KYBAPM4RUYQU6CMOO2RTGV3R/action/citation_signature","submit_replication":"https://pith.science/pith/U6KYBAPM4RUYQU6CMOO2RTGV3R/action/replication_record"}},"created_at":"2026-07-05T05:00:43.590340+00:00","updated_at":"2026-07-05T05:00:43.590340+00:00"}