{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UQZKIKSNLZOYHSVJFIT4FLEYF3","short_pith_number":"pith:UQZKIKSN","schema_version":"1.0","canonical_sha256":"a432a42a4d5e5d83caa92a27c2ac982ed6cc38d69b4e96b5b8ed05cc458f7ffe","source":{"kind":"arxiv","id":"2508.16261","version":1},"attestation_state":"computed","paper":{"title":"On the Evolution of Federated Post-Training Large Language Models: A Model Accessibility View","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Fushuo Huo, Jie Gui, Junxiao Wang, Laizhong Cui, Song Guo, Tao Guo","submitted_at":"2025-08-22T09:52:31Z","abstract_excerpt":"Federated Learning (FL) enables training models across decentralized data silos while preserving client data privacy. Recent research has explored efficient methods for post-training large language models (LLMs) within FL to address computational and communication challenges. While existing approaches often rely on access to LLMs' internal information, which is frequently restricted in real-world scenarios, an inference-only paradigm (black-box FedLLM) has emerged to address these limitations. This paper presents a comprehensive survey on federated tuning for LLMs. We propose a taxonomy catego"},"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":"2508.16261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-22T09:52:31Z","cross_cats_sorted":[],"title_canon_sha256":"97a2a9f7b4085713b009b7d013c277761db91e78c50e7596b7d2bd43b3ba1bda","abstract_canon_sha256":"fd3ec5c278a8fdc989869a9792d7cf330443dc2ec10ba2feb7d1ca439149c53a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:44.871425Z","signature_b64":"t6ZmeymfYny45xN3Dp6otnNpU97/5my/ZCc67EmgF2LSkSiF2udGWASIwusrdK3IMTXNX/Xw4QwAEjN/nFGsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a432a42a4d5e5d83caa92a27c2ac982ed6cc38d69b4e96b5b8ed05cc458f7ffe","last_reissued_at":"2026-07-05T11:57:44.870954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:44.870954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Evolution of Federated Post-Training Large Language Models: A Model Accessibility View","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Fushuo Huo, Jie Gui, Junxiao Wang, Laizhong Cui, Song Guo, Tao Guo","submitted_at":"2025-08-22T09:52:31Z","abstract_excerpt":"Federated Learning (FL) enables training models across decentralized data silos while preserving client data privacy. Recent research has explored efficient methods for post-training large language models (LLMs) within FL to address computational and communication challenges. While existing approaches often rely on access to LLMs' internal information, which is frequently restricted in real-world scenarios, an inference-only paradigm (black-box FedLLM) has emerged to address these limitations. This paper presents a comprehensive survey on federated tuning for LLMs. We propose a taxonomy catego"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16261","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/2508.16261/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":"2508.16261","created_at":"2026-07-05T11:57:44.871011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16261v1","created_at":"2026-07-05T11:57:44.871011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16261","created_at":"2026-07-05T11:57:44.871011+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQZKIKSNLZOY","created_at":"2026-07-05T11:57:44.871011+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQZKIKSNLZOYHSVJ","created_at":"2026-07-05T11:57:44.871011+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQZKIKSN","created_at":"2026-07-05T11:57:44.871011+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/UQZKIKSNLZOYHSVJFIT4FLEYF3","json":"https://pith.science/pith/UQZKIKSNLZOYHSVJFIT4FLEYF3.json","graph_json":"https://pith.science/api/pith-number/UQZKIKSNLZOYHSVJFIT4FLEYF3/graph.json","events_json":"https://pith.science/api/pith-number/UQZKIKSNLZOYHSVJFIT4FLEYF3/events.json","paper":"https://pith.science/paper/UQZKIKSN"},"agent_actions":{"view_html":"https://pith.science/pith/UQZKIKSNLZOYHSVJFIT4FLEYF3","download_json":"https://pith.science/pith/UQZKIKSNLZOYHSVJFIT4FLEYF3.json","view_paper":"https://pith.science/paper/UQZKIKSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16261&json=true","fetch_graph":"https://pith.science/api/pith-number/UQZKIKSNLZOYHSVJFIT4FLEYF3/graph.json","fetch_events":"https://pith.science/api/pith-number/UQZKIKSNLZOYHSVJFIT4FLEYF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQZKIKSNLZOYHSVJFIT4FLEYF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQZKIKSNLZOYHSVJFIT4FLEYF3/action/storage_attestation","attest_author":"https://pith.science/pith/UQZKIKSNLZOYHSVJFIT4FLEYF3/action/author_attestation","sign_citation":"https://pith.science/pith/UQZKIKSNLZOYHSVJFIT4FLEYF3/action/citation_signature","submit_replication":"https://pith.science/pith/UQZKIKSNLZOYHSVJFIT4FLEYF3/action/replication_record"}},"created_at":"2026-07-05T11:57:44.871011+00:00","updated_at":"2026-07-05T11:57:44.871011+00:00"}