{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KDDH4P5RKNQWW73PEIQLHP54KT","short_pith_number":"pith:KDDH4P5R","schema_version":"1.0","canonical_sha256":"50c67e3fb153616b7f6f2220b3bfbc54c852d191aef94cb523e82620b31675e3","source":{"kind":"arxiv","id":"2404.15384","version":1},"attestation_state":"computed","paper":{"title":"FL-TAC: Enhanced Fine-Tuning in Federated Learning via Low-Rank, Task-Specific Adapter Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Siqi Ping, Wenbo Ding, Xiao-Ping Zhang, Yang Liu, Yuzhu Mao","submitted_at":"2024-04-23T10:50:38Z","abstract_excerpt":"Although large-scale pre-trained models hold great potential for adapting to downstream tasks through fine-tuning, the performance of such fine-tuned models is often limited by the difficulty of collecting sufficient high-quality, task-specific data. Federated Learning (FL) offers a promising solution by enabling fine-tuning across large-scale clients with a variety of task data, but it is bottlenecked by significant communication overhead due to the pre-trained models' extensive size. This paper addresses the high communication cost for fine-tuning large pre-trained models within FL framework"},"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":"2404.15384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-23T10:50:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26fd44aaac7c58b2551d5282fd3727fd6424b59e22d094356c2c3abb32228bf0","abstract_canon_sha256":"3b0d330dce80083c48c3d3b52d62c7eda4db9d7498ad0996b00a3c239437583a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:27.040866Z","signature_b64":"ZtUoU3KLVvM6DHfnMTOOQzM1FLjZctMfzDiyz2DygEcRkqJ5OGtoWtJDgFmK09ZU9+1pgNf9CK6ne/lVaoyHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50c67e3fb153616b7f6f2220b3bfbc54c852d191aef94cb523e82620b31675e3","last_reissued_at":"2026-07-05T08:11:27.039242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:27.039242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FL-TAC: Enhanced Fine-Tuning in Federated Learning via Low-Rank, Task-Specific Adapter Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Siqi Ping, Wenbo Ding, Xiao-Ping Zhang, Yang Liu, Yuzhu Mao","submitted_at":"2024-04-23T10:50:38Z","abstract_excerpt":"Although large-scale pre-trained models hold great potential for adapting to downstream tasks through fine-tuning, the performance of such fine-tuned models is often limited by the difficulty of collecting sufficient high-quality, task-specific data. Federated Learning (FL) offers a promising solution by enabling fine-tuning across large-scale clients with a variety of task data, but it is bottlenecked by significant communication overhead due to the pre-trained models' extensive size. This paper addresses the high communication cost for fine-tuning large pre-trained models within FL framework"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15384","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/2404.15384/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":"2404.15384","created_at":"2026-07-05T08:11:27.040287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15384v1","created_at":"2026-07-05T08:11:27.040287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15384","created_at":"2026-07-05T08:11:27.040287+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDDH4P5RKNQW","created_at":"2026-07-05T08:11:27.040287+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDDH4P5RKNQWW73P","created_at":"2026-07-05T08:11:27.040287+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDDH4P5R","created_at":"2026-07-05T08:11:27.040287+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05142","citing_title":"Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KDDH4P5RKNQWW73PEIQLHP54KT","json":"https://pith.science/pith/KDDH4P5RKNQWW73PEIQLHP54KT.json","graph_json":"https://pith.science/api/pith-number/KDDH4P5RKNQWW73PEIQLHP54KT/graph.json","events_json":"https://pith.science/api/pith-number/KDDH4P5RKNQWW73PEIQLHP54KT/events.json","paper":"https://pith.science/paper/KDDH4P5R"},"agent_actions":{"view_html":"https://pith.science/pith/KDDH4P5RKNQWW73PEIQLHP54KT","download_json":"https://pith.science/pith/KDDH4P5RKNQWW73PEIQLHP54KT.json","view_paper":"https://pith.science/paper/KDDH4P5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15384&json=true","fetch_graph":"https://pith.science/api/pith-number/KDDH4P5RKNQWW73PEIQLHP54KT/graph.json","fetch_events":"https://pith.science/api/pith-number/KDDH4P5RKNQWW73PEIQLHP54KT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDDH4P5RKNQWW73PEIQLHP54KT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDDH4P5RKNQWW73PEIQLHP54KT/action/storage_attestation","attest_author":"https://pith.science/pith/KDDH4P5RKNQWW73PEIQLHP54KT/action/author_attestation","sign_citation":"https://pith.science/pith/KDDH4P5RKNQWW73PEIQLHP54KT/action/citation_signature","submit_replication":"https://pith.science/pith/KDDH4P5RKNQWW73PEIQLHP54KT/action/replication_record"}},"created_at":"2026-07-05T08:11:27.040287+00:00","updated_at":"2026-07-05T08:11:27.040287+00:00"}