{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NTYYTOITLIT37U5OWEE3BNTGKA","short_pith_number":"pith:NTYYTOIT","schema_version":"1.0","canonical_sha256":"6cf189b9135a27bfd3aeb109b0b666500e308adf80c601d4230e4c90e63b9cd8","source":{"kind":"arxiv","id":"2501.09237","version":1},"attestation_state":"computed","paper":{"title":"Split Fine-Tuning for Large Language Models in Wireless Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Guoliang Cheng, Lingyang Song, Songge Zhang, Wen Wu, Xinyu Huang, Xuemin Shen, Zuguang Li","submitted_at":"2025-01-16T01:44:05Z","abstract_excerpt":"Fine-tuning is the process of adapting the pre-trained large language models (LLMs) for downstream tasks. Due to substantial parameters, fine-tuning LLMs on mobile devices demands considerable memory resources, and suffers from high communication overhead and long fine-tuning delay. In this paper, we propose an efficient LLM fine-tuning scheme in wireless networks, named Split Fine-Tuning (SFT), which can accommodate LLM fine-tuning on mobile devices. Specifically, an LLM is split into a server-side part on the edge server and a device-side part on the mobile device to satisfy the device-side "},"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":"2501.09237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-16T01:44:05Z","cross_cats_sorted":[],"title_canon_sha256":"3228a96d5421398603839f5c97e7f20dc521e4b7ec6e7f9cd2d7e1c4aa306d6a","abstract_canon_sha256":"d3a54e81b5c42b00e70daa86893b27eade608f02e8dfeb3baa0d01d0831f0ef2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:43.933577Z","signature_b64":"nhguJOuLWDg7eUEF0UDQ8j4eBIc9MazIsfJBdcDuePTs7xECSvw204PGy5ZJA6/G+LmPnZHucTzNxawR5e9SCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cf189b9135a27bfd3aeb109b0b666500e308adf80c601d4230e4c90e63b9cd8","last_reissued_at":"2026-07-05T10:01:43.933176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:43.933176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Split Fine-Tuning for Large Language Models in Wireless Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Guoliang Cheng, Lingyang Song, Songge Zhang, Wen Wu, Xinyu Huang, Xuemin Shen, Zuguang Li","submitted_at":"2025-01-16T01:44:05Z","abstract_excerpt":"Fine-tuning is the process of adapting the pre-trained large language models (LLMs) for downstream tasks. Due to substantial parameters, fine-tuning LLMs on mobile devices demands considerable memory resources, and suffers from high communication overhead and long fine-tuning delay. In this paper, we propose an efficient LLM fine-tuning scheme in wireless networks, named Split Fine-Tuning (SFT), which can accommodate LLM fine-tuning on mobile devices. Specifically, an LLM is split into a server-side part on the edge server and a device-side part on the mobile device to satisfy the device-side "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09237","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/2501.09237/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":"2501.09237","created_at":"2026-07-05T10:01:43.933234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09237v1","created_at":"2026-07-05T10:01:43.933234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09237","created_at":"2026-07-05T10:01:43.933234+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTYYTOITLIT3","created_at":"2026-07-05T10:01:43.933234+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTYYTOITLIT37U5O","created_at":"2026-07-05T10:01:43.933234+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTYYTOIT","created_at":"2026-07-05T10:01:43.933234+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/NTYYTOITLIT37U5OWEE3BNTGKA","json":"https://pith.science/pith/NTYYTOITLIT37U5OWEE3BNTGKA.json","graph_json":"https://pith.science/api/pith-number/NTYYTOITLIT37U5OWEE3BNTGKA/graph.json","events_json":"https://pith.science/api/pith-number/NTYYTOITLIT37U5OWEE3BNTGKA/events.json","paper":"https://pith.science/paper/NTYYTOIT"},"agent_actions":{"view_html":"https://pith.science/pith/NTYYTOITLIT37U5OWEE3BNTGKA","download_json":"https://pith.science/pith/NTYYTOITLIT37U5OWEE3BNTGKA.json","view_paper":"https://pith.science/paper/NTYYTOIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09237&json=true","fetch_graph":"https://pith.science/api/pith-number/NTYYTOITLIT37U5OWEE3BNTGKA/graph.json","fetch_events":"https://pith.science/api/pith-number/NTYYTOITLIT37U5OWEE3BNTGKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTYYTOITLIT37U5OWEE3BNTGKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTYYTOITLIT37U5OWEE3BNTGKA/action/storage_attestation","attest_author":"https://pith.science/pith/NTYYTOITLIT37U5OWEE3BNTGKA/action/author_attestation","sign_citation":"https://pith.science/pith/NTYYTOITLIT37U5OWEE3BNTGKA/action/citation_signature","submit_replication":"https://pith.science/pith/NTYYTOITLIT37U5OWEE3BNTGKA/action/replication_record"}},"created_at":"2026-07-05T10:01:43.933234+00:00","updated_at":"2026-07-05T10:01:43.933234+00:00"}