{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YUCUBEZ6P56GZI3IXBAJ7XZ4LU","short_pith_number":"pith:YUCUBEZ6","schema_version":"1.0","canonical_sha256":"c50540933e7f7c6ca368b8409fdf3c5d1a5b8a3db72b6877c2c6dbdc675fc7a8","source":{"kind":"arxiv","id":"2410.00131","version":2},"attestation_state":"computed","paper":{"title":"Fisher Information-based Efficient Curriculum Federated Learning with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DC"],"primary_cat":"cs.LG","authors_text":"Dejing Dou, Jiaxiang Ren, Ji Liu, Patrick Valduriez, Ruoming Jin, Yang Zhou, Zijie Zhang","submitted_at":"2024-09-30T18:12:18Z","abstract_excerpt":"As a promising paradigm to collaboratively train models with decentralized data, Federated Learning (FL) can be exploited to fine-tune Large Language Models (LLMs). While LLMs correspond to huge size, the scale of the training data significantly increases, which leads to tremendous amounts of computation and communication costs. The training data is generally non-Independent and Identically Distributed (non-IID), which requires adaptive data processing within each device. Although Low Rank Adaptation (LoRA) can significantly reduce the scale of parameters to update in the fine-tuning process, "},"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":"2410.00131","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-30T18:12:18Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DC"],"title_canon_sha256":"19422b3abbf468899767b314382e5245682b8ca37b23498e5cc38b2d8acebd62","abstract_canon_sha256":"4c8e46209c3449bab202fa3f2522c825d39dbf0d624951d15d87b8839c40e442"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:22.134530Z","signature_b64":"aKWBJByCdcPiX5gdPqQIaZfUtQDTWDhJPK9QzJJnOMOfdbwdNAcwmrNQhhI1eqE/NA/hRekWcBKzCdm/LVuPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c50540933e7f7c6ca368b8409fdf3c5d1a5b8a3db72b6877c2c6dbdc675fc7a8","last_reissued_at":"2026-07-05T09:22:22.134107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:22.134107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fisher Information-based Efficient Curriculum Federated Learning with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DC"],"primary_cat":"cs.LG","authors_text":"Dejing Dou, Jiaxiang Ren, Ji Liu, Patrick Valduriez, Ruoming Jin, Yang Zhou, Zijie Zhang","submitted_at":"2024-09-30T18:12:18Z","abstract_excerpt":"As a promising paradigm to collaboratively train models with decentralized data, Federated Learning (FL) can be exploited to fine-tune Large Language Models (LLMs). While LLMs correspond to huge size, the scale of the training data significantly increases, which leads to tremendous amounts of computation and communication costs. The training data is generally non-Independent and Identically Distributed (non-IID), which requires adaptive data processing within each device. Although Low Rank Adaptation (LoRA) can significantly reduce the scale of parameters to update in the fine-tuning process, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00131","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/2410.00131/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":"2410.00131","created_at":"2026-07-05T09:22:22.134161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00131v2","created_at":"2026-07-05T09:22:22.134161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00131","created_at":"2026-07-05T09:22:22.134161+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUCUBEZ6P56G","created_at":"2026-07-05T09:22:22.134161+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUCUBEZ6P56GZI3I","created_at":"2026-07-05T09:22:22.134161+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUCUBEZ6","created_at":"2026-07-05T09:22:22.134161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03320","citing_title":"The Future of Continual Learning in the Era of Foundation Models: Three Key Directions","ref_index":83,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YUCUBEZ6P56GZI3IXBAJ7XZ4LU","json":"https://pith.science/pith/YUCUBEZ6P56GZI3IXBAJ7XZ4LU.json","graph_json":"https://pith.science/api/pith-number/YUCUBEZ6P56GZI3IXBAJ7XZ4LU/graph.json","events_json":"https://pith.science/api/pith-number/YUCUBEZ6P56GZI3IXBAJ7XZ4LU/events.json","paper":"https://pith.science/paper/YUCUBEZ6"},"agent_actions":{"view_html":"https://pith.science/pith/YUCUBEZ6P56GZI3IXBAJ7XZ4LU","download_json":"https://pith.science/pith/YUCUBEZ6P56GZI3IXBAJ7XZ4LU.json","view_paper":"https://pith.science/paper/YUCUBEZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00131&json=true","fetch_graph":"https://pith.science/api/pith-number/YUCUBEZ6P56GZI3IXBAJ7XZ4LU/graph.json","fetch_events":"https://pith.science/api/pith-number/YUCUBEZ6P56GZI3IXBAJ7XZ4LU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUCUBEZ6P56GZI3IXBAJ7XZ4LU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUCUBEZ6P56GZI3IXBAJ7XZ4LU/action/storage_attestation","attest_author":"https://pith.science/pith/YUCUBEZ6P56GZI3IXBAJ7XZ4LU/action/author_attestation","sign_citation":"https://pith.science/pith/YUCUBEZ6P56GZI3IXBAJ7XZ4LU/action/citation_signature","submit_replication":"https://pith.science/pith/YUCUBEZ6P56GZI3IXBAJ7XZ4LU/action/replication_record"}},"created_at":"2026-07-05T09:22:22.134161+00:00","updated_at":"2026-07-05T09:22:22.134161+00:00"}