{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AVOTLRISYCA6OV7S7ZP46F4AW4","short_pith_number":"pith:AVOTLRIS","schema_version":"1.0","canonical_sha256":"055d35c512c081e757f2fe5fcf1780b72959e1b6cbd4ffb8b12d5ea9d2ce4590","source":{"kind":"arxiv","id":"2411.05059","version":2},"attestation_state":"computed","paper":{"title":"FineTuneBench: How well do commercial fine-tuning APIs infuse knowledge into LLMs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Eric Wu, James Zou, Kevin Wu","submitted_at":"2024-11-07T18:22:14Z","abstract_excerpt":"There is great interest in fine-tuning frontier large language models (LLMs) to inject new information and update existing knowledge. While commercial LLM fine-tuning APIs from providers such as OpenAI and Google promise flexible adaptation for various applications, the efficacy of fine-tuning remains unclear. In this study, we introduce FineTuneBench, an evaluation framework and dataset for understanding how well commercial fine-tuning APIs can successfully learn new and updated knowledge. We analyze five frontier LLMs with commercially available fine-tuning APIs, including GPT-4o and Gemini "},"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":"2411.05059","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-07T18:22:14Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"7f6f2c43c45fff76889f79c087f44515e0690c4c90c1a2b5813c1509cf8be43a","abstract_canon_sha256":"8b0d3660f2f76d384b440a0b834b07e32776b87ed20f66481acc3423e86061ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:00.511917Z","signature_b64":"2a32d1L7Xu7A2/WGmujFaos9hWZwwu/gFt/3rNWuw6kcRJad9tv9Tutk3W6DtarG4f6Se2D3MQZKzn/0I5hSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"055d35c512c081e757f2fe5fcf1780b72959e1b6cbd4ffb8b12d5ea9d2ce4590","last_reissued_at":"2026-07-05T09:34:00.511473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:00.511473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FineTuneBench: How well do commercial fine-tuning APIs infuse knowledge into LLMs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Eric Wu, James Zou, Kevin Wu","submitted_at":"2024-11-07T18:22:14Z","abstract_excerpt":"There is great interest in fine-tuning frontier large language models (LLMs) to inject new information and update existing knowledge. While commercial LLM fine-tuning APIs from providers such as OpenAI and Google promise flexible adaptation for various applications, the efficacy of fine-tuning remains unclear. In this study, we introduce FineTuneBench, an evaluation framework and dataset for understanding how well commercial fine-tuning APIs can successfully learn new and updated knowledge. We analyze five frontier LLMs with commercially available fine-tuning APIs, including GPT-4o and Gemini "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05059","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/2411.05059/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":"2411.05059","created_at":"2026-07-05T09:34:00.511530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05059v2","created_at":"2026-07-05T09:34:00.511530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05059","created_at":"2026-07-05T09:34:00.511530+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVOTLRISYCA6","created_at":"2026-07-05T09:34:00.511530+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVOTLRISYCA6OV7S","created_at":"2026-07-05T09:34:00.511530+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVOTLRIS","created_at":"2026-07-05T09:34:00.511530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05436","citing_title":"Ten Headache Specialists versus Artificial Intelligence for Clinical Literature Summarization: A Critical Evaluation and Comparison","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09533","citing_title":"Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06385","citing_title":"Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AVOTLRISYCA6OV7S7ZP46F4AW4","json":"https://pith.science/pith/AVOTLRISYCA6OV7S7ZP46F4AW4.json","graph_json":"https://pith.science/api/pith-number/AVOTLRISYCA6OV7S7ZP46F4AW4/graph.json","events_json":"https://pith.science/api/pith-number/AVOTLRISYCA6OV7S7ZP46F4AW4/events.json","paper":"https://pith.science/paper/AVOTLRIS"},"agent_actions":{"view_html":"https://pith.science/pith/AVOTLRISYCA6OV7S7ZP46F4AW4","download_json":"https://pith.science/pith/AVOTLRISYCA6OV7S7ZP46F4AW4.json","view_paper":"https://pith.science/paper/AVOTLRIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05059&json=true","fetch_graph":"https://pith.science/api/pith-number/AVOTLRISYCA6OV7S7ZP46F4AW4/graph.json","fetch_events":"https://pith.science/api/pith-number/AVOTLRISYCA6OV7S7ZP46F4AW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVOTLRISYCA6OV7S7ZP46F4AW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVOTLRISYCA6OV7S7ZP46F4AW4/action/storage_attestation","attest_author":"https://pith.science/pith/AVOTLRISYCA6OV7S7ZP46F4AW4/action/author_attestation","sign_citation":"https://pith.science/pith/AVOTLRISYCA6OV7S7ZP46F4AW4/action/citation_signature","submit_replication":"https://pith.science/pith/AVOTLRISYCA6OV7S7ZP46F4AW4/action/replication_record"}},"created_at":"2026-07-05T09:34:00.511530+00:00","updated_at":"2026-07-05T09:34:00.511530+00:00"}