{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EL763XKLY6JCZLF2ABLLMWVTVF","short_pith_number":"pith:EL763XKL","schema_version":"1.0","canonical_sha256":"22ffeddd4bc7922cacba0056b65ab3a96b67ef0ba98418d516c96436e38edea4","source":{"kind":"arxiv","id":"2403.13101","version":4},"attestation_state":"computed","paper":{"title":"AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Guanqiao Qu, Kin K. Leung, Wei Wei, Xianhao Chen, Zheng Lin","submitted_at":"2024-03-19T19:05:24Z","abstract_excerpt":"The increasing complexity of deep neural networks poses significant barriers to democratizing them to resource-limited edge devices. To address this challenge, split federated learning (SFL) has emerged as a promising solution by of floading the primary training workload to a server via model partitioning while enabling parallel training among edge devices. However, although system optimization substantially influences the performance of SFL under resource-constrained systems, the problem remains largely uncharted. In this paper, we provide a convergence analysis of SFL which quantifies the im"},"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":"2403.13101","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-19T19:05:24Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"fc31c5d51233219fcfe3fccff5096f1d5ee631a76bb0fa1b15eb913d1d9eb914","abstract_canon_sha256":"61845cf599e93716559b8f41f868d97ecffb396bd5762e9ed96d4517525e9668"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:37.247614Z","signature_b64":"Pi1GzqflHnweja0PmSTepscUfbINgjnDwwnO/TPDQK2pshIPcEsKAoXdrAy8tNh2oT7/Co4Z654QDvH05ZVHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22ffeddd4bc7922cacba0056b65ab3a96b67ef0ba98418d516c96436e38edea4","last_reissued_at":"2026-07-05T11:15:37.247110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:37.247110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Guanqiao Qu, Kin K. Leung, Wei Wei, Xianhao Chen, Zheng Lin","submitted_at":"2024-03-19T19:05:24Z","abstract_excerpt":"The increasing complexity of deep neural networks poses significant barriers to democratizing them to resource-limited edge devices. To address this challenge, split federated learning (SFL) has emerged as a promising solution by of floading the primary training workload to a server via model partitioning while enabling parallel training among edge devices. However, although system optimization substantially influences the performance of SFL under resource-constrained systems, the problem remains largely uncharted. In this paper, we provide a convergence analysis of SFL which quantifies the im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13101","kind":"arxiv","version":4},"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/2403.13101/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":"2403.13101","created_at":"2026-07-05T11:15:37.247173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13101v4","created_at":"2026-07-05T11:15:37.247173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13101","created_at":"2026-07-05T11:15:37.247173+00:00"},{"alias_kind":"pith_short_12","alias_value":"EL763XKLY6JC","created_at":"2026-07-05T11:15:37.247173+00:00"},{"alias_kind":"pith_short_16","alias_value":"EL763XKLY6JCZLF2","created_at":"2026-07-05T11:15:37.247173+00:00"},{"alias_kind":"pith_short_8","alias_value":"EL763XKL","created_at":"2026-07-05T11:15:37.247173+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10685","citing_title":"Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generation","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EL763XKLY6JCZLF2ABLLMWVTVF","json":"https://pith.science/pith/EL763XKLY6JCZLF2ABLLMWVTVF.json","graph_json":"https://pith.science/api/pith-number/EL763XKLY6JCZLF2ABLLMWVTVF/graph.json","events_json":"https://pith.science/api/pith-number/EL763XKLY6JCZLF2ABLLMWVTVF/events.json","paper":"https://pith.science/paper/EL763XKL"},"agent_actions":{"view_html":"https://pith.science/pith/EL763XKLY6JCZLF2ABLLMWVTVF","download_json":"https://pith.science/pith/EL763XKLY6JCZLF2ABLLMWVTVF.json","view_paper":"https://pith.science/paper/EL763XKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13101&json=true","fetch_graph":"https://pith.science/api/pith-number/EL763XKLY6JCZLF2ABLLMWVTVF/graph.json","fetch_events":"https://pith.science/api/pith-number/EL763XKLY6JCZLF2ABLLMWVTVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EL763XKLY6JCZLF2ABLLMWVTVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EL763XKLY6JCZLF2ABLLMWVTVF/action/storage_attestation","attest_author":"https://pith.science/pith/EL763XKLY6JCZLF2ABLLMWVTVF/action/author_attestation","sign_citation":"https://pith.science/pith/EL763XKLY6JCZLF2ABLLMWVTVF/action/citation_signature","submit_replication":"https://pith.science/pith/EL763XKLY6JCZLF2ABLLMWVTVF/action/replication_record"}},"created_at":"2026-07-05T11:15:37.247173+00:00","updated_at":"2026-07-05T11:15:37.247173+00:00"}