{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2UUMRUNTEBC24O6NEUMBCK4VDS","short_pith_number":"pith:2UUMRUNT","schema_version":"1.0","canonical_sha256":"d528c8d1b32045ae3bcd2518112b951cb626f1b3d84ab9c6fac05dabbd267431","source":{"kind":"arxiv","id":"2508.12727","version":1},"attestation_state":"computed","paper":{"title":"FedSODA: Federated Fine-tuning of LLMs via Similarity Group Pruning and Orchestrated Distillation Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Han, Dewen Qiao, Manning Zhu, Pengzhan Zhou, Songtao Guo, Yansong Ning","submitted_at":"2025-08-18T08:49:32Z","abstract_excerpt":"Federated fine-tuning (FFT) of large language models (LLMs) has recently emerged as a promising solution to enable domain-specific adaptation while preserving data privacy. Despite its benefits, FFT on resource-constrained clients relies on the high computational and memory demands of full-model fine-tuning, which limits the potential advancement. This paper presents FedSODA, a resource-efficient FFT framework that enables clients to adapt LLMs without accessing or storing the full model. Specifically, we first propose a similarity group pruning (SGP) module, which prunes redundant layers from"},"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":"2508.12727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-18T08:49:32Z","cross_cats_sorted":[],"title_canon_sha256":"29c2dfd4158234e5a61bb6e2eb33333b5cd0df52e9f4b95f721f21db1d2f9b73","abstract_canon_sha256":"6ad76ed0d9f0e439b2df420383d4c0d8dc064c8e3cc08581ecb1ebce4680a365"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:25.995150Z","signature_b64":"+SeBc2GNpKFUTQZFj22r53OveR/UrNizNZ7SDJxKu322s4f0cKv0aDxlUuNw7fUm/N7MfC9EcZRn9lyKDJi5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d528c8d1b32045ae3bcd2518112b951cb626f1b3d84ab9c6fac05dabbd267431","last_reissued_at":"2026-07-05T11:55:25.994699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:25.994699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedSODA: Federated Fine-tuning of LLMs via Similarity Group Pruning and Orchestrated Distillation Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Han, Dewen Qiao, Manning Zhu, Pengzhan Zhou, Songtao Guo, Yansong Ning","submitted_at":"2025-08-18T08:49:32Z","abstract_excerpt":"Federated fine-tuning (FFT) of large language models (LLMs) has recently emerged as a promising solution to enable domain-specific adaptation while preserving data privacy. Despite its benefits, FFT on resource-constrained clients relies on the high computational and memory demands of full-model fine-tuning, which limits the potential advancement. This paper presents FedSODA, a resource-efficient FFT framework that enables clients to adapt LLMs without accessing or storing the full model. Specifically, we first propose a similarity group pruning (SGP) module, which prunes redundant layers from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12727","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/2508.12727/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":"2508.12727","created_at":"2026-07-05T11:55:25.994757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12727v1","created_at":"2026-07-05T11:55:25.994757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12727","created_at":"2026-07-05T11:55:25.994757+00:00"},{"alias_kind":"pith_short_12","alias_value":"2UUMRUNTEBC2","created_at":"2026-07-05T11:55:25.994757+00:00"},{"alias_kind":"pith_short_16","alias_value":"2UUMRUNTEBC24O6N","created_at":"2026-07-05T11:55:25.994757+00:00"},{"alias_kind":"pith_short_8","alias_value":"2UUMRUNT","created_at":"2026-07-05T11:55:25.994757+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/2UUMRUNTEBC24O6NEUMBCK4VDS","json":"https://pith.science/pith/2UUMRUNTEBC24O6NEUMBCK4VDS.json","graph_json":"https://pith.science/api/pith-number/2UUMRUNTEBC24O6NEUMBCK4VDS/graph.json","events_json":"https://pith.science/api/pith-number/2UUMRUNTEBC24O6NEUMBCK4VDS/events.json","paper":"https://pith.science/paper/2UUMRUNT"},"agent_actions":{"view_html":"https://pith.science/pith/2UUMRUNTEBC24O6NEUMBCK4VDS","download_json":"https://pith.science/pith/2UUMRUNTEBC24O6NEUMBCK4VDS.json","view_paper":"https://pith.science/paper/2UUMRUNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12727&json=true","fetch_graph":"https://pith.science/api/pith-number/2UUMRUNTEBC24O6NEUMBCK4VDS/graph.json","fetch_events":"https://pith.science/api/pith-number/2UUMRUNTEBC24O6NEUMBCK4VDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2UUMRUNTEBC24O6NEUMBCK4VDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2UUMRUNTEBC24O6NEUMBCK4VDS/action/storage_attestation","attest_author":"https://pith.science/pith/2UUMRUNTEBC24O6NEUMBCK4VDS/action/author_attestation","sign_citation":"https://pith.science/pith/2UUMRUNTEBC24O6NEUMBCK4VDS/action/citation_signature","submit_replication":"https://pith.science/pith/2UUMRUNTEBC24O6NEUMBCK4VDS/action/replication_record"}},"created_at":"2026-07-05T11:55:25.994757+00:00","updated_at":"2026-07-05T11:55:25.994757+00:00"}