{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:J65ESVHIMUQU4FJOP56N2SZURX","short_pith_number":"pith:J65ESVHI","schema_version":"1.0","canonical_sha256":"4fba4954e865214e152e7f7cdd4b348dd76df47be145f6ee6c69d0bd573d4cb2","source":{"kind":"arxiv","id":"2212.08343","version":2},"attestation_state":"computed","paper":{"title":"SplitGP: Achieving Both Generalization and Personalization in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christopher G. Brinton, Dong-Jun Han, Do-Yeon Kim, Jaekyun Moon, Minseok Choi","submitted_at":"2022-12-16T08:37:24Z","abstract_excerpt":"A fundamental challenge to providing edge-AI services is the need for a machine learning (ML) model that achieves personalization (i.e., to individual clients) and generalization (i.e., to unseen data) properties concurrently. Existing techniques in federated learning (FL) have encountered a steep tradeoff between these objectives and impose large computational requirements on edge devices during training and inference. In this paper, we propose SplitGP, a new split learning solution that can simultaneously capture generalization and personalization capabilities for efficient inference across "},"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":"2212.08343","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-16T08:37:24Z","cross_cats_sorted":[],"title_canon_sha256":"70a017126ecf58f2be2ce32e3f63577a23d467336d50f4fe66256cd37eb45a98","abstract_canon_sha256":"410b9b0e22781dfa4919e695a4451be00e4c5057901f905a2386d19984e17523"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:52.103393Z","signature_b64":"01pOh3TjohiG6uJTCMq8eO13bD6ktsLvRutGKJEwewXyaYLyvMNC7jLV8sehrZv34nYpfRN8U9i3QZlgWUU1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fba4954e865214e152e7f7cdd4b348dd76df47be145f6ee6c69d0bd573d4cb2","last_reissued_at":"2026-07-05T05:40:52.102906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:52.102906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SplitGP: Achieving Both Generalization and Personalization in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christopher G. Brinton, Dong-Jun Han, Do-Yeon Kim, Jaekyun Moon, Minseok Choi","submitted_at":"2022-12-16T08:37:24Z","abstract_excerpt":"A fundamental challenge to providing edge-AI services is the need for a machine learning (ML) model that achieves personalization (i.e., to individual clients) and generalization (i.e., to unseen data) properties concurrently. Existing techniques in federated learning (FL) have encountered a steep tradeoff between these objectives and impose large computational requirements on edge devices during training and inference. In this paper, we propose SplitGP, a new split learning solution that can simultaneously capture generalization and personalization capabilities for efficient inference across "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08343","kind":"arxiv","version":2},"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/2212.08343/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":"2212.08343","created_at":"2026-07-05T05:40:52.102954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08343v2","created_at":"2026-07-05T05:40:52.102954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08343","created_at":"2026-07-05T05:40:52.102954+00:00"},{"alias_kind":"pith_short_12","alias_value":"J65ESVHIMUQU","created_at":"2026-07-05T05:40:52.102954+00:00"},{"alias_kind":"pith_short_16","alias_value":"J65ESVHIMUQU4FJO","created_at":"2026-07-05T05:40:52.102954+00:00"},{"alias_kind":"pith_short_8","alias_value":"J65ESVHI","created_at":"2026-07-05T05:40:52.102954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20946","citing_title":"Generalising Battery Control in Net-Zero Buildings via Personalised Federated RL","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J65ESVHIMUQU4FJOP56N2SZURX","json":"https://pith.science/pith/J65ESVHIMUQU4FJOP56N2SZURX.json","graph_json":"https://pith.science/api/pith-number/J65ESVHIMUQU4FJOP56N2SZURX/graph.json","events_json":"https://pith.science/api/pith-number/J65ESVHIMUQU4FJOP56N2SZURX/events.json","paper":"https://pith.science/paper/J65ESVHI"},"agent_actions":{"view_html":"https://pith.science/pith/J65ESVHIMUQU4FJOP56N2SZURX","download_json":"https://pith.science/pith/J65ESVHIMUQU4FJOP56N2SZURX.json","view_paper":"https://pith.science/paper/J65ESVHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08343&json=true","fetch_graph":"https://pith.science/api/pith-number/J65ESVHIMUQU4FJOP56N2SZURX/graph.json","fetch_events":"https://pith.science/api/pith-number/J65ESVHIMUQU4FJOP56N2SZURX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J65ESVHIMUQU4FJOP56N2SZURX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J65ESVHIMUQU4FJOP56N2SZURX/action/storage_attestation","attest_author":"https://pith.science/pith/J65ESVHIMUQU4FJOP56N2SZURX/action/author_attestation","sign_citation":"https://pith.science/pith/J65ESVHIMUQU4FJOP56N2SZURX/action/citation_signature","submit_replication":"https://pith.science/pith/J65ESVHIMUQU4FJOP56N2SZURX/action/replication_record"}},"created_at":"2026-07-05T05:40:52.102954+00:00","updated_at":"2026-07-05T05:40:52.102954+00:00"}