{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UFBWKSPQRFH3UXBNGKFSSHDSHV","short_pith_number":"pith:UFBWKSPQ","schema_version":"1.0","canonical_sha256":"a1436549f0894fba5c2d328b291c723d65c87c2a98d5438f347b96d7a4a5eb1b","source":{"kind":"arxiv","id":"2605.26120","version":1},"attestation_state":"computed","paper":{"title":"Semantic-aware Token Selection and Resource Optimization for Communication-efficient Split Federated Fine-tuning in Edge Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Geyong Min, Xianke Qiang, Zheng Chang","submitted_at":"2026-04-21T13:53:48Z","abstract_excerpt":"Deploying large Transformer-based vision models on resource-limited mobile devices at network edge is severely constrained by hardware limitations and dynamic wireless environments. While federated learning (FL) enables collaborative training without sharing raw data, strictly local fine-tuning of such massive models remains computationally prohibitive for edge devices. Split federated learning (SFL) alleviates this burden by offloading deep layers to the edge server, yet it suffers from heavy communication overhead when transmitting high-dimensional activation tokens. To address this bottlene"},"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":"2605.26120","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-04-21T13:53:48Z","cross_cats_sorted":[],"title_canon_sha256":"05d0e0c658a152e1b8096b681cb17597f5b5a79654e010dd62c54c0b69fb74fd","abstract_canon_sha256":"5b3b76a4f57381789753544f714c831b039489613fd39238c8f26beae9afaba3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T00:04:24.805242Z","signature_b64":"YptRv885alxX7BSmHNbi2AV0ySG62I+g3Sqbo9ZeT6vNGCPfurEMWV/NjQKk7uJ/RszhGno43635iAhCLWnDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1436549f0894fba5c2d328b291c723d65c87c2a98d5438f347b96d7a4a5eb1b","last_reissued_at":"2026-05-27T00:04:24.804533Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T00:04:24.804533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic-aware Token Selection and Resource Optimization for Communication-efficient Split Federated Fine-tuning in Edge Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Geyong Min, Xianke Qiang, Zheng Chang","submitted_at":"2026-04-21T13:53:48Z","abstract_excerpt":"Deploying large Transformer-based vision models on resource-limited mobile devices at network edge is severely constrained by hardware limitations and dynamic wireless environments. While federated learning (FL) enables collaborative training without sharing raw data, strictly local fine-tuning of such massive models remains computationally prohibitive for edge devices. Split federated learning (SFL) alleviates this burden by offloading deep layers to the edge server, yet it suffers from heavy communication overhead when transmitting high-dimensional activation tokens. To address this bottlene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26120","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/2605.26120/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":"2605.26120","created_at":"2026-05-27T00:04:24.804617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26120v1","created_at":"2026-05-27T00:04:24.804617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26120","created_at":"2026-05-27T00:04:24.804617+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFBWKSPQRFH3","created_at":"2026-05-27T00:04:24.804617+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFBWKSPQRFH3UXBN","created_at":"2026-05-27T00:04:24.804617+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFBWKSPQ","created_at":"2026-05-27T00:04:24.804617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFBWKSPQRFH3UXBNGKFSSHDSHV","json":"https://pith.science/pith/UFBWKSPQRFH3UXBNGKFSSHDSHV.json","graph_json":"https://pith.science/api/pith-number/UFBWKSPQRFH3UXBNGKFSSHDSHV/graph.json","events_json":"https://pith.science/api/pith-number/UFBWKSPQRFH3UXBNGKFSSHDSHV/events.json","paper":"https://pith.science/paper/UFBWKSPQ"},"agent_actions":{"view_html":"https://pith.science/pith/UFBWKSPQRFH3UXBNGKFSSHDSHV","download_json":"https://pith.science/pith/UFBWKSPQRFH3UXBNGKFSSHDSHV.json","view_paper":"https://pith.science/paper/UFBWKSPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26120&json=true","fetch_graph":"https://pith.science/api/pith-number/UFBWKSPQRFH3UXBNGKFSSHDSHV/graph.json","fetch_events":"https://pith.science/api/pith-number/UFBWKSPQRFH3UXBNGKFSSHDSHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFBWKSPQRFH3UXBNGKFSSHDSHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFBWKSPQRFH3UXBNGKFSSHDSHV/action/storage_attestation","attest_author":"https://pith.science/pith/UFBWKSPQRFH3UXBNGKFSSHDSHV/action/author_attestation","sign_citation":"https://pith.science/pith/UFBWKSPQRFH3UXBNGKFSSHDSHV/action/citation_signature","submit_replication":"https://pith.science/pith/UFBWKSPQRFH3UXBNGKFSSHDSHV/action/replication_record"}},"created_at":"2026-05-27T00:04:24.804617+00:00","updated_at":"2026-05-27T00:04:24.804617+00:00"}