{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:74P3OX7XYGHJTRLMNXFIKUUYNJ","short_pith_number":"pith:74P3OX7X","schema_version":"1.0","canonical_sha256":"ff1fb75ff7c18e99c56c6dca8552986a63978387a156bbdd7cd74e2663ab25f2","source":{"kind":"arxiv","id":"2508.08339","version":1},"attestation_state":"computed","paper":{"title":"SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dung T. Tran, Kok-Seng Wong, Nguyen B. Ha, Van-Dinh Nguyen","submitted_at":"2025-08-11T04:13:56Z","abstract_excerpt":"Federated learning (FL) is a promising approach for addressing scalability and latency issues in large-scale networks by enabling collaborative model training without requiring the sharing of raw data. However, existing FL frameworks often overlook the computational heterogeneity of edge clients and the growing training burden on resource-limited devices. However, FL suffers from high communication costs and complex model aggregation, especially with large models. Previous works combine split learning (SL) and hierarchical FL (HierFL) to reduce device-side computation and improve scalability, "},"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":"2508.08339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-11T04:13:56Z","cross_cats_sorted":[],"title_canon_sha256":"bca2026eefd0691a6d0117c09b5c6feaf814bfa2a87fe72044e02140e8864eff","abstract_canon_sha256":"e955499153655f20b108a98a5d30cef17490896b2a85b6e70b0bc894834bd329"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:26.462563Z","signature_b64":"Getm3JX4VwfUnGSd+CLwEbJs2Bp+oaEBkSXEWVs97c2jqQD2kIAIt9M1zLS4ExQtFtCEWBztxyGVbhMWZc5SDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff1fb75ff7c18e99c56c6dca8552986a63978387a156bbdd7cd74e2663ab25f2","last_reissued_at":"2026-07-05T11:52:26.462037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:26.462037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dung T. Tran, Kok-Seng Wong, Nguyen B. Ha, Van-Dinh Nguyen","submitted_at":"2025-08-11T04:13:56Z","abstract_excerpt":"Federated learning (FL) is a promising approach for addressing scalability and latency issues in large-scale networks by enabling collaborative model training without requiring the sharing of raw data. However, existing FL frameworks often overlook the computational heterogeneity of edge clients and the growing training burden on resource-limited devices. However, FL suffers from high communication costs and complex model aggregation, especially with large models. Previous works combine split learning (SL) and hierarchical FL (HierFL) to reduce device-side computation and improve scalability, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08339","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/2508.08339/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":"2508.08339","created_at":"2026-07-05T11:52:26.462100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08339v1","created_at":"2026-07-05T11:52:26.462100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08339","created_at":"2026-07-05T11:52:26.462100+00:00"},{"alias_kind":"pith_short_12","alias_value":"74P3OX7XYGHJ","created_at":"2026-07-05T11:52:26.462100+00:00"},{"alias_kind":"pith_short_16","alias_value":"74P3OX7XYGHJTRLM","created_at":"2026-07-05T11:52:26.462100+00:00"},{"alias_kind":"pith_short_8","alias_value":"74P3OX7X","created_at":"2026-07-05T11:52:26.462100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09869","citing_title":"QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74P3OX7XYGHJTRLMNXFIKUUYNJ","json":"https://pith.science/pith/74P3OX7XYGHJTRLMNXFIKUUYNJ.json","graph_json":"https://pith.science/api/pith-number/74P3OX7XYGHJTRLMNXFIKUUYNJ/graph.json","events_json":"https://pith.science/api/pith-number/74P3OX7XYGHJTRLMNXFIKUUYNJ/events.json","paper":"https://pith.science/paper/74P3OX7X"},"agent_actions":{"view_html":"https://pith.science/pith/74P3OX7XYGHJTRLMNXFIKUUYNJ","download_json":"https://pith.science/pith/74P3OX7XYGHJTRLMNXFIKUUYNJ.json","view_paper":"https://pith.science/paper/74P3OX7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08339&json=true","fetch_graph":"https://pith.science/api/pith-number/74P3OX7XYGHJTRLMNXFIKUUYNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/74P3OX7XYGHJTRLMNXFIKUUYNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74P3OX7XYGHJTRLMNXFIKUUYNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74P3OX7XYGHJTRLMNXFIKUUYNJ/action/storage_attestation","attest_author":"https://pith.science/pith/74P3OX7XYGHJTRLMNXFIKUUYNJ/action/author_attestation","sign_citation":"https://pith.science/pith/74P3OX7XYGHJTRLMNXFIKUUYNJ/action/citation_signature","submit_replication":"https://pith.science/pith/74P3OX7XYGHJTRLMNXFIKUUYNJ/action/replication_record"}},"created_at":"2026-07-05T11:52:26.462100+00:00","updated_at":"2026-07-05T11:52:26.462100+00:00"}