{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VSWLRFWTZFRS3NZPZJEFXDSQFV","short_pith_number":"pith:VSWLRFWT","schema_version":"1.0","canonical_sha256":"acacb896d3c9632db72fca485b8e502d4952895f60e9b0872ede0493aa9cfb9c","source":{"kind":"arxiv","id":"2408.15600","version":3},"attestation_state":"computed","paper":{"title":"Exploring Selective Layer Fine-Tuning in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Bolin Ding, Jun Zhang, Yaliang Li, Yuchang Sun, Yuexiang Xie","submitted_at":"2024-08-28T07:48:39Z","abstract_excerpt":"Federated learning (FL) has emerged as a promising paradigm for fine-tuning foundation models using distributed data in a privacy-preserving manner. Under limited computational resources, clients often find it more practical to fine-tune a selected subset of layers, rather than the entire model, based on their task-specific data. In this study, we provide a thorough theoretical exploration of selective layer fine-tuning in FL, emphasizing a flexible approach that allows the clients to adjust their selected layers according to their local data and resources. We theoretically demonstrate that th"},"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":"2408.15600","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-28T07:48:39Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"8b7c6b9cf794aeae0499192f04979c76d257e05badb91e3b15f6a696c4d03991","abstract_canon_sha256":"23254b4abefcd66b831558cac7707214d807482083876fcda6c2c430561b4ca3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:19.361012Z","signature_b64":"enCOqKbE8tzvGCuBjoTYWIrvzc4vBqbsBgFOkq4L5FVc0LSGDL1nN2xOldohoyUnDIlsdWP92Et7H6zPqUBKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acacb896d3c9632db72fca485b8e502d4952895f60e9b0872ede0493aa9cfb9c","last_reissued_at":"2026-07-05T09:40:19.360543Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:19.360543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Selective Layer Fine-Tuning in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Bolin Ding, Jun Zhang, Yaliang Li, Yuchang Sun, Yuexiang Xie","submitted_at":"2024-08-28T07:48:39Z","abstract_excerpt":"Federated learning (FL) has emerged as a promising paradigm for fine-tuning foundation models using distributed data in a privacy-preserving manner. Under limited computational resources, clients often find it more practical to fine-tune a selected subset of layers, rather than the entire model, based on their task-specific data. In this study, we provide a thorough theoretical exploration of selective layer fine-tuning in FL, emphasizing a flexible approach that allows the clients to adjust their selected layers according to their local data and resources. We theoretically demonstrate that th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15600","kind":"arxiv","version":3},"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/2408.15600/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":"2408.15600","created_at":"2026-07-05T09:40:19.360598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15600v3","created_at":"2026-07-05T09:40:19.360598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15600","created_at":"2026-07-05T09:40:19.360598+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSWLRFWTZFRS","created_at":"2026-07-05T09:40:19.360598+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSWLRFWTZFRS3NZP","created_at":"2026-07-05T09:40:19.360598+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSWLRFWT","created_at":"2026-07-05T09:40:19.360598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23639","citing_title":"Unified Multimodal Understanding via Byte-Pair Visual Encoding","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSWLRFWTZFRS3NZPZJEFXDSQFV","json":"https://pith.science/pith/VSWLRFWTZFRS3NZPZJEFXDSQFV.json","graph_json":"https://pith.science/api/pith-number/VSWLRFWTZFRS3NZPZJEFXDSQFV/graph.json","events_json":"https://pith.science/api/pith-number/VSWLRFWTZFRS3NZPZJEFXDSQFV/events.json","paper":"https://pith.science/paper/VSWLRFWT"},"agent_actions":{"view_html":"https://pith.science/pith/VSWLRFWTZFRS3NZPZJEFXDSQFV","download_json":"https://pith.science/pith/VSWLRFWTZFRS3NZPZJEFXDSQFV.json","view_paper":"https://pith.science/paper/VSWLRFWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15600&json=true","fetch_graph":"https://pith.science/api/pith-number/VSWLRFWTZFRS3NZPZJEFXDSQFV/graph.json","fetch_events":"https://pith.science/api/pith-number/VSWLRFWTZFRS3NZPZJEFXDSQFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSWLRFWTZFRS3NZPZJEFXDSQFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSWLRFWTZFRS3NZPZJEFXDSQFV/action/storage_attestation","attest_author":"https://pith.science/pith/VSWLRFWTZFRS3NZPZJEFXDSQFV/action/author_attestation","sign_citation":"https://pith.science/pith/VSWLRFWTZFRS3NZPZJEFXDSQFV/action/citation_signature","submit_replication":"https://pith.science/pith/VSWLRFWTZFRS3NZPZJEFXDSQFV/action/replication_record"}},"created_at":"2026-07-05T09:40:19.360598+00:00","updated_at":"2026-07-05T09:40:19.360598+00:00"}