{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I2VRNJ2J4EI5FTSMCOIULACE6U","short_pith_number":"pith:I2VRNJ2J","schema_version":"1.0","canonical_sha256":"46ab16a749e111d2ce4c1391458044f5232827e8ed021840c352128657b32fca","source":{"kind":"arxiv","id":"2412.17692","version":2},"attestation_state":"computed","paper":{"title":"FedTLU: Federated Learning with Targeted Layer Updates","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Carlee Joe-Wong, Jong-Ik Park","submitted_at":"2024-12-23T16:17:46Z","abstract_excerpt":"Federated learning (FL) addresses privacy concerns in training language models by enabling multiple clients to contribute to the training, without sending their data to others. However, non-IID (identically and independently distributed) data across clients often limits FL's performance. This issue is especially challenging during model fine-tuning, as noise due to variations in clients' data distributions can harm model convergence near stationary points. This paper proposes a targeted layer update strategy for fine-tuning in FL. Instead of randomly updating layers of the language model, as o"},"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":"2412.17692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-23T16:17:46Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"e9ea1eb75ec49b80daf73ce8f94941bd5ef38e323248dc66c5b944e3e85cb61a","abstract_canon_sha256":"aaec71890547136ef4ff67a42abadba7e42e2a0153a3667bc3a46fb9d49e3054"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:15.627988Z","signature_b64":"PC2JfCJ8qXvujGQATmdRt9aGzj5h2B3gHvbkPpTzSju4BhLHhPOriOHZOQbOvg3NkgPZ3N5pbNSWeqtmitcPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46ab16a749e111d2ce4c1391458044f5232827e8ed021840c352128657b32fca","last_reissued_at":"2026-07-05T10:05:15.627470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:15.627470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedTLU: Federated Learning with Targeted Layer Updates","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Carlee Joe-Wong, Jong-Ik Park","submitted_at":"2024-12-23T16:17:46Z","abstract_excerpt":"Federated learning (FL) addresses privacy concerns in training language models by enabling multiple clients to contribute to the training, without sending their data to others. However, non-IID (identically and independently distributed) data across clients often limits FL's performance. This issue is especially challenging during model fine-tuning, as noise due to variations in clients' data distributions can harm model convergence near stationary points. This paper proposes a targeted layer update strategy for fine-tuning in FL. Instead of randomly updating layers of the language model, as o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17692","kind":"arxiv","version":2},"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/2412.17692/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":"2412.17692","created_at":"2026-07-05T10:05:15.627538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17692v2","created_at":"2026-07-05T10:05:15.627538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17692","created_at":"2026-07-05T10:05:15.627538+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2VRNJ2J4EI5","created_at":"2026-07-05T10:05:15.627538+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2VRNJ2J4EI5FTSM","created_at":"2026-07-05T10:05:15.627538+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2VRNJ2J","created_at":"2026-07-05T10:05:15.627538+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/I2VRNJ2J4EI5FTSMCOIULACE6U","json":"https://pith.science/pith/I2VRNJ2J4EI5FTSMCOIULACE6U.json","graph_json":"https://pith.science/api/pith-number/I2VRNJ2J4EI5FTSMCOIULACE6U/graph.json","events_json":"https://pith.science/api/pith-number/I2VRNJ2J4EI5FTSMCOIULACE6U/events.json","paper":"https://pith.science/paper/I2VRNJ2J"},"agent_actions":{"view_html":"https://pith.science/pith/I2VRNJ2J4EI5FTSMCOIULACE6U","download_json":"https://pith.science/pith/I2VRNJ2J4EI5FTSMCOIULACE6U.json","view_paper":"https://pith.science/paper/I2VRNJ2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17692&json=true","fetch_graph":"https://pith.science/api/pith-number/I2VRNJ2J4EI5FTSMCOIULACE6U/graph.json","fetch_events":"https://pith.science/api/pith-number/I2VRNJ2J4EI5FTSMCOIULACE6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2VRNJ2J4EI5FTSMCOIULACE6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2VRNJ2J4EI5FTSMCOIULACE6U/action/storage_attestation","attest_author":"https://pith.science/pith/I2VRNJ2J4EI5FTSMCOIULACE6U/action/author_attestation","sign_citation":"https://pith.science/pith/I2VRNJ2J4EI5FTSMCOIULACE6U/action/citation_signature","submit_replication":"https://pith.science/pith/I2VRNJ2J4EI5FTSMCOIULACE6U/action/replication_record"}},"created_at":"2026-07-05T10:05:15.627538+00:00","updated_at":"2026-07-05T10:05:15.627538+00:00"}