{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YAHEHVX2C2FPCZXBB4ZB5TB3NL","short_pith_number":"pith:YAHEHVX2","schema_version":"1.0","canonical_sha256":"c00e43d6fa168af166e10f321ecc3b6ac532298d580e530d4a2bd20ff62ea89a","source":{"kind":"arxiv","id":"2402.06954","version":1},"attestation_state":"computed","paper":{"title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.DC","cs.MA"],"primary_cat":"cs.LG","authors_text":"Dihan Li, Jingyi Chai, Rui Ye, Siheng Chen, Wenhao Wang, Yanfeng Wang, Yaxin Du, Yinda Xu, Zexi Li","submitted_at":"2024-02-10T13:50:11Z","abstract_excerpt":"Trained on massive publicly available data, large language models (LLMs) have demonstrated tremendous success across various fields. While more data contributes to better performance, a disconcerting reality is that high-quality public data will be exhausted in a few years. In this paper, we offer a potential next step for contemporary LLMs: collaborative and privacy-preserving LLM training on the underutilized distributed private data via federated learning (FL), where multiple data owners collaboratively train a shared model without transmitting raw data. To achieve this, we build a concise,"},"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":"2402.06954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T13:50:11Z","cross_cats_sorted":["cs.CL","cs.DC","cs.MA"],"title_canon_sha256":"3b7e4265d5490ff8c0ae38a8dee05455fb845a94cbd81a8e264e226066c75971","abstract_canon_sha256":"c7f3c10452744938b764528ea61c65d251ac5e9f31b602443bea7f000f0536ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:40.958623Z","signature_b64":"RvWkjrJ5mXrE5Rs0entX26eiTQu3PNXk6//+4VF6AFlBEJWoegGGlP0W2xyIw6A+XLrb9duNNKubypO/Z8UZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c00e43d6fa168af166e10f321ecc3b6ac532298d580e530d4a2bd20ff62ea89a","last_reissued_at":"2026-07-05T07:43:40.958114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:40.958114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.DC","cs.MA"],"primary_cat":"cs.LG","authors_text":"Dihan Li, Jingyi Chai, Rui Ye, Siheng Chen, Wenhao Wang, Yanfeng Wang, Yaxin Du, Yinda Xu, Zexi Li","submitted_at":"2024-02-10T13:50:11Z","abstract_excerpt":"Trained on massive publicly available data, large language models (LLMs) have demonstrated tremendous success across various fields. While more data contributes to better performance, a disconcerting reality is that high-quality public data will be exhausted in a few years. In this paper, we offer a potential next step for contemporary LLMs: collaborative and privacy-preserving LLM training on the underutilized distributed private data via federated learning (FL), where multiple data owners collaboratively train a shared model without transmitting raw data. To achieve this, we build a concise,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06954","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/2402.06954/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":"2402.06954","created_at":"2026-07-05T07:43:40.958173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06954v1","created_at":"2026-07-05T07:43:40.958173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06954","created_at":"2026-07-05T07:43:40.958173+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAHEHVX2C2FP","created_at":"2026-07-05T07:43:40.958173+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAHEHVX2C2FPCZXB","created_at":"2026-07-05T07:43:40.958173+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAHEHVX2","created_at":"2026-07-05T07:43:40.958173+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06154","citing_title":"Amortizing Federated Adaptation: Hypernetwork Driven LoRA for Personalized Foundation Models","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02958","citing_title":"Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25435","citing_title":"PI-TTA: Physics-Informed Source-Free Test-Time Adaptation for Robust Human Activity Recognition on Mobile Devices","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YAHEHVX2C2FPCZXBB4ZB5TB3NL","json":"https://pith.science/pith/YAHEHVX2C2FPCZXBB4ZB5TB3NL.json","graph_json":"https://pith.science/api/pith-number/YAHEHVX2C2FPCZXBB4ZB5TB3NL/graph.json","events_json":"https://pith.science/api/pith-number/YAHEHVX2C2FPCZXBB4ZB5TB3NL/events.json","paper":"https://pith.science/paper/YAHEHVX2"},"agent_actions":{"view_html":"https://pith.science/pith/YAHEHVX2C2FPCZXBB4ZB5TB3NL","download_json":"https://pith.science/pith/YAHEHVX2C2FPCZXBB4ZB5TB3NL.json","view_paper":"https://pith.science/paper/YAHEHVX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06954&json=true","fetch_graph":"https://pith.science/api/pith-number/YAHEHVX2C2FPCZXBB4ZB5TB3NL/graph.json","fetch_events":"https://pith.science/api/pith-number/YAHEHVX2C2FPCZXBB4ZB5TB3NL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAHEHVX2C2FPCZXBB4ZB5TB3NL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAHEHVX2C2FPCZXBB4ZB5TB3NL/action/storage_attestation","attest_author":"https://pith.science/pith/YAHEHVX2C2FPCZXBB4ZB5TB3NL/action/author_attestation","sign_citation":"https://pith.science/pith/YAHEHVX2C2FPCZXBB4ZB5TB3NL/action/citation_signature","submit_replication":"https://pith.science/pith/YAHEHVX2C2FPCZXBB4ZB5TB3NL/action/replication_record"}},"created_at":"2026-07-05T07:43:40.958173+00:00","updated_at":"2026-07-05T07:43:40.958173+00:00"}