{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XLD4PB2L7EBAA4RYZSG3F4G2M3","short_pith_number":"pith:XLD4PB2L","schema_version":"1.0","canonical_sha256":"bac7c7874bf902007238cc8db2f0da66f63af2c814ebcbb3d07e5f822b2a8466","source":{"kind":"arxiv","id":"2404.10779","version":1},"attestation_state":"computed","paper":{"title":"Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Harikrishna Warrier, Kushala VM, Mathav Raj J, Yogesh Gupta","submitted_at":"2024-03-23T13:25:01Z","abstract_excerpt":"There is a compelling necessity from enterprises for fine tuning LLMs (Large Language Models) o get them trained on proprietary domain knowledge. The challenge is to imbibe the LLMs with domain specific knowledge using the most optimial resource and cost and in the best possible time. Many enterprises rely on RAG (Retrieval Augmented Generation) which does not need LLMs to be ine-tuned but they are limited by the quality of vector databases and their retrieval capabilities rather than the intrinsic capabilities of the LLMs themselves. In our current work we focus on fine tuning LLaMA, an open "},"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":"2404.10779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-23T13:25:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d086ba799e5c476efe394c02d63e5b9e1f5755cf380185ed0a3a1f0f70012157","abstract_canon_sha256":"cbcf29370d41050a6837211d82fcac15a41703542bd7f09766fa2756ed6829c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:58.563433Z","signature_b64":"QivRgn/brCnuJKUmztI54MGMXgGWYpjIyUj+694ZB7s7BjIwBFP6ruGim2qNUGsQl+bbt9U3WvEuM7N8RK6mAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bac7c7874bf902007238cc8db2f0da66f63af2c814ebcbb3d07e5f822b2a8466","last_reissued_at":"2026-07-05T08:08:58.562962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:58.562962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Harikrishna Warrier, Kushala VM, Mathav Raj J, Yogesh Gupta","submitted_at":"2024-03-23T13:25:01Z","abstract_excerpt":"There is a compelling necessity from enterprises for fine tuning LLMs (Large Language Models) o get them trained on proprietary domain knowledge. The challenge is to imbibe the LLMs with domain specific knowledge using the most optimial resource and cost and in the best possible time. Many enterprises rely on RAG (Retrieval Augmented Generation) which does not need LLMs to be ine-tuned but they are limited by the quality of vector databases and their retrieval capabilities rather than the intrinsic capabilities of the LLMs themselves. In our current work we focus on fine tuning LLaMA, an open "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10779","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/2404.10779/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":"2404.10779","created_at":"2026-07-05T08:08:58.563026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10779v1","created_at":"2026-07-05T08:08:58.563026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10779","created_at":"2026-07-05T08:08:58.563026+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLD4PB2L7EBA","created_at":"2026-07-05T08:08:58.563026+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLD4PB2L7EBAA4RY","created_at":"2026-07-05T08:08:58.563026+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLD4PB2L","created_at":"2026-07-05T08:08:58.563026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27591","citing_title":"Gradient Transformer: Learning to Generate Updates for LLMs","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2603.00989","citing_title":"Sustainable Code Generation Using Large Language Models: A Systematic Literature Review","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19776","citing_title":"Development and Preliminary Evaluation of a Domain-Specific Large Language Model for Tuberculosis Care in South Africa","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XLD4PB2L7EBAA4RYZSG3F4G2M3","json":"https://pith.science/pith/XLD4PB2L7EBAA4RYZSG3F4G2M3.json","graph_json":"https://pith.science/api/pith-number/XLD4PB2L7EBAA4RYZSG3F4G2M3/graph.json","events_json":"https://pith.science/api/pith-number/XLD4PB2L7EBAA4RYZSG3F4G2M3/events.json","paper":"https://pith.science/paper/XLD4PB2L"},"agent_actions":{"view_html":"https://pith.science/pith/XLD4PB2L7EBAA4RYZSG3F4G2M3","download_json":"https://pith.science/pith/XLD4PB2L7EBAA4RYZSG3F4G2M3.json","view_paper":"https://pith.science/paper/XLD4PB2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10779&json=true","fetch_graph":"https://pith.science/api/pith-number/XLD4PB2L7EBAA4RYZSG3F4G2M3/graph.json","fetch_events":"https://pith.science/api/pith-number/XLD4PB2L7EBAA4RYZSG3F4G2M3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLD4PB2L7EBAA4RYZSG3F4G2M3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLD4PB2L7EBAA4RYZSG3F4G2M3/action/storage_attestation","attest_author":"https://pith.science/pith/XLD4PB2L7EBAA4RYZSG3F4G2M3/action/author_attestation","sign_citation":"https://pith.science/pith/XLD4PB2L7EBAA4RYZSG3F4G2M3/action/citation_signature","submit_replication":"https://pith.science/pith/XLD4PB2L7EBAA4RYZSG3F4G2M3/action/replication_record"}},"created_at":"2026-07-05T08:08:58.563026+00:00","updated_at":"2026-07-05T08:08:58.563026+00:00"}