{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F6OIIVVR6KC2AFTKS2FA6YWPKK","short_pith_number":"pith:F6OIIVVR","schema_version":"1.0","canonical_sha256":"2f9c8456b1f285a0166a968a0f62cf52aa49d5034fd7d46e1d5608a77cb5edaf","source":{"kind":"arxiv","id":"2305.05644","version":2},"attestation_state":"computed","paper":{"title":"Towards Building the Federated GPT: Federated Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.SY","eess.SY"],"primary_cat":"cs.CL","authors_text":"Chunyuan Li, Guoyin Wang, Jianyi Zhang, Martin Kuo, Ruiyi Zhang, Saeed Vahidian, Tong Yu, Yiran Chen, Yufan Zhou","submitted_at":"2023-05-09T17:42:34Z","abstract_excerpt":"While \"instruction-tuned\" generative large language models (LLMs) have demonstrated an impressive ability to generalize to new tasks, the training phases heavily rely on large amounts of diverse and high-quality instruction data (such as ChatGPT and GPT-4). Unfortunately, acquiring high-quality data, especially when it comes to human-written data, can pose significant challenges both in terms of cost and accessibility. Moreover, concerns related to privacy can further limit access to such data, making the process of obtaining it a complex and nuanced undertaking. Consequently, this hinders the"},"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":"2305.05644","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T17:42:34Z","cross_cats_sorted":["cs.DC","cs.SY","eess.SY"],"title_canon_sha256":"f19a16c481ae68f74771167a42dca9573a0e6992451eafed94bab3f4dbb7ac06","abstract_canon_sha256":"5b1dc51a21b07c2a8cf3d7296a7556d742d8ecd2834552793c32a229ca6dbf20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:27.529752Z","signature_b64":"kdndbXlazVKRi7OIswtrv4yYAcwtWu/uOjRVBZPm3lrm58i6/rSE89L1l5ekcNPwUOYvBNk9bJGhsBavtxCkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f9c8456b1f285a0166a968a0f62cf52aa49d5034fd7d46e1d5608a77cb5edaf","last_reissued_at":"2026-07-05T07:38:27.529256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:27.529256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Building the Federated GPT: Federated Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.SY","eess.SY"],"primary_cat":"cs.CL","authors_text":"Chunyuan Li, Guoyin Wang, Jianyi Zhang, Martin Kuo, Ruiyi Zhang, Saeed Vahidian, Tong Yu, Yiran Chen, Yufan Zhou","submitted_at":"2023-05-09T17:42:34Z","abstract_excerpt":"While \"instruction-tuned\" generative large language models (LLMs) have demonstrated an impressive ability to generalize to new tasks, the training phases heavily rely on large amounts of diverse and high-quality instruction data (such as ChatGPT and GPT-4). Unfortunately, acquiring high-quality data, especially when it comes to human-written data, can pose significant challenges both in terms of cost and accessibility. Moreover, concerns related to privacy can further limit access to such data, making the process of obtaining it a complex and nuanced undertaking. Consequently, this hinders the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05644","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/2305.05644/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":"2305.05644","created_at":"2026-07-05T07:38:27.529324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05644v2","created_at":"2026-07-05T07:38:27.529324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05644","created_at":"2026-07-05T07:38:27.529324+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6OIIVVR6KC2","created_at":"2026-07-05T07:38:27.529324+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6OIIVVR6KC2AFTK","created_at":"2026-07-05T07:38:27.529324+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6OIIVVR","created_at":"2026-07-05T07:38:27.529324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08636","citing_title":"EdgeFlowerTune: Evaluating Federated LLM Fine-Tuning Under Realistic Edge System Constraints","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06833","citing_title":"FedDetox: Robust Federated SLM Alignment via On-Device Data Sanitization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06596","citing_title":"FedAttr: Towards Privacy-preserving Client-Level Attribution in Federated LLM Fine-tuning","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F6OIIVVR6KC2AFTKS2FA6YWPKK","json":"https://pith.science/pith/F6OIIVVR6KC2AFTKS2FA6YWPKK.json","graph_json":"https://pith.science/api/pith-number/F6OIIVVR6KC2AFTKS2FA6YWPKK/graph.json","events_json":"https://pith.science/api/pith-number/F6OIIVVR6KC2AFTKS2FA6YWPKK/events.json","paper":"https://pith.science/paper/F6OIIVVR"},"agent_actions":{"view_html":"https://pith.science/pith/F6OIIVVR6KC2AFTKS2FA6YWPKK","download_json":"https://pith.science/pith/F6OIIVVR6KC2AFTKS2FA6YWPKK.json","view_paper":"https://pith.science/paper/F6OIIVVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05644&json=true","fetch_graph":"https://pith.science/api/pith-number/F6OIIVVR6KC2AFTKS2FA6YWPKK/graph.json","fetch_events":"https://pith.science/api/pith-number/F6OIIVVR6KC2AFTKS2FA6YWPKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6OIIVVR6KC2AFTKS2FA6YWPKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6OIIVVR6KC2AFTKS2FA6YWPKK/action/storage_attestation","attest_author":"https://pith.science/pith/F6OIIVVR6KC2AFTKS2FA6YWPKK/action/author_attestation","sign_citation":"https://pith.science/pith/F6OIIVVR6KC2AFTKS2FA6YWPKK/action/citation_signature","submit_replication":"https://pith.science/pith/F6OIIVVR6KC2AFTKS2FA6YWPKK/action/replication_record"}},"created_at":"2026-07-05T07:38:27.529324+00:00","updated_at":"2026-07-05T07:38:27.529324+00:00"}