{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YC7QFPUKCIKZCCPZLHNE3Q2FQG","short_pith_number":"pith:YC7QFPUK","schema_version":"1.0","canonical_sha256":"c0bf02be8a12159109f959da4dc345819ec839a8da6fc5a78b1097e9024dbcfb","source":{"kind":"arxiv","id":"2503.03920","version":1},"attestation_state":"computed","paper":{"title":"Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ali Payani, Jie Hao, Mingrui Liu, Myungjin Lee, Yuman Wu","submitted_at":"2025-03-05T21:41:03Z","abstract_excerpt":"We study the task of personalized federated fine-tuning with heterogeneous data in the context of language models, where clients collaboratively fine-tune a language model (e.g., BERT, GPT) without sharing their local data, achieving personalization simultaneously. While recent efforts have applied parameter-efficient fine-tuning techniques like low-rank adaptation (LoRA) in federated settings, they typically use single or multiple independent low-rank adapters with predefined maximal and minimal ranks, which may not be optimal for diverse data sources over clients.\n  To address this issue, we"},"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":"2503.03920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-05T21:41:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"03240b58b913f118dd9bea1dcb13d5cc6b343d40ff0590353d9448a91e6448b7","abstract_canon_sha256":"4b6629e41cf6c7bd40b83bc480d65bd9af8b8bb536603e82af7fe716f5588c45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:24.319769Z","signature_b64":"oqbhNcl6HCnGKFvpJPTqDlz85C3sibVf3/DmUrjV+LuIgv6cNwiltLWxRIoEBeun79ybsY90Uqg0FmgCwdxzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0bf02be8a12159109f959da4dc345819ec839a8da6fc5a78b1097e9024dbcfb","last_reissued_at":"2026-07-05T10:25:24.319269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:24.319269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ali Payani, Jie Hao, Mingrui Liu, Myungjin Lee, Yuman Wu","submitted_at":"2025-03-05T21:41:03Z","abstract_excerpt":"We study the task of personalized federated fine-tuning with heterogeneous data in the context of language models, where clients collaboratively fine-tune a language model (e.g., BERT, GPT) without sharing their local data, achieving personalization simultaneously. While recent efforts have applied parameter-efficient fine-tuning techniques like low-rank adaptation (LoRA) in federated settings, they typically use single or multiple independent low-rank adapters with predefined maximal and minimal ranks, which may not be optimal for diverse data sources over clients.\n  To address this issue, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03920","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/2503.03920/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":"2503.03920","created_at":"2026-07-05T10:25:24.319336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03920v1","created_at":"2026-07-05T10:25:24.319336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03920","created_at":"2026-07-05T10:25:24.319336+00:00"},{"alias_kind":"pith_short_12","alias_value":"YC7QFPUKCIKZ","created_at":"2026-07-05T10:25:24.319336+00:00"},{"alias_kind":"pith_short_16","alias_value":"YC7QFPUKCIKZCCPZ","created_at":"2026-07-05T10:25:24.319336+00:00"},{"alias_kind":"pith_short_8","alias_value":"YC7QFPUK","created_at":"2026-07-05T10:25:24.319336+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/YC7QFPUKCIKZCCPZLHNE3Q2FQG","json":"https://pith.science/pith/YC7QFPUKCIKZCCPZLHNE3Q2FQG.json","graph_json":"https://pith.science/api/pith-number/YC7QFPUKCIKZCCPZLHNE3Q2FQG/graph.json","events_json":"https://pith.science/api/pith-number/YC7QFPUKCIKZCCPZLHNE3Q2FQG/events.json","paper":"https://pith.science/paper/YC7QFPUK"},"agent_actions":{"view_html":"https://pith.science/pith/YC7QFPUKCIKZCCPZLHNE3Q2FQG","download_json":"https://pith.science/pith/YC7QFPUKCIKZCCPZLHNE3Q2FQG.json","view_paper":"https://pith.science/paper/YC7QFPUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03920&json=true","fetch_graph":"https://pith.science/api/pith-number/YC7QFPUKCIKZCCPZLHNE3Q2FQG/graph.json","fetch_events":"https://pith.science/api/pith-number/YC7QFPUKCIKZCCPZLHNE3Q2FQG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YC7QFPUKCIKZCCPZLHNE3Q2FQG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YC7QFPUKCIKZCCPZLHNE3Q2FQG/action/storage_attestation","attest_author":"https://pith.science/pith/YC7QFPUKCIKZCCPZLHNE3Q2FQG/action/author_attestation","sign_citation":"https://pith.science/pith/YC7QFPUKCIKZCCPZLHNE3Q2FQG/action/citation_signature","submit_replication":"https://pith.science/pith/YC7QFPUKCIKZCCPZLHNE3Q2FQG/action/replication_record"}},"created_at":"2026-07-05T10:25:24.319336+00:00","updated_at":"2026-07-05T10:25:24.319336+00:00"}