{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OGGGZMYZB2PZU23YBW4NURVGBW","short_pith_number":"pith:OGGGZMYZ","schema_version":"1.0","canonical_sha256":"718c6cb3190e9f9a6b780db8da46a60d8074c5be8733b91ecd51f084dfc0c443","source":{"kind":"arxiv","id":"2310.10508","version":2},"attestation_state":"computed","paper":{"title":"Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Clark Tang, Hadi Hemmati, Jiho Shin, Maleknaz Nayebi, Song Wang, Tahmineh Mohati","submitted_at":"2023-10-11T00:21:00Z","abstract_excerpt":"The rapid advancements in large language models (LLMs) have greatly expanded the potential for automated code-related tasks. Two primary methodologies are used in this domain: prompt engineering and fine-tuning. Prompt engineering involves applying different strategies to query LLMs, like ChatGPT, while fine-tuning further adapts pre-trained models, such as CodeBERT, by training them on task-specific data. Despite the growth in the area, there remains a lack of comprehensive comparative analysis between the approaches for code models. In this paper, we evaluate GPT-4 using three prompt enginee"},"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":"2310.10508","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-10-11T00:21:00Z","cross_cats_sorted":[],"title_canon_sha256":"f01f4cfbae37a2b15c272b677fa48977827319954128e8351f5944081395f21f","abstract_canon_sha256":"5ee756fda3e4b4cdabfea7aebeaa6c38587ab53421666634461f31747f03b5d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:05.474939Z","signature_b64":"DgovR6mR/rBisoY7V39amPi4Jmx1oSfi9g7Xp/1GqUUF53YbtTB11stCW+Bv18p/xYURHP8t7/qq8gezq18rDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"718c6cb3190e9f9a6b780db8da46a60d8074c5be8733b91ecd51f084dfc0c443","last_reissued_at":"2026-07-05T10:17:05.474449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:05.474449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Clark Tang, Hadi Hemmati, Jiho Shin, Maleknaz Nayebi, Song Wang, Tahmineh Mohati","submitted_at":"2023-10-11T00:21:00Z","abstract_excerpt":"The rapid advancements in large language models (LLMs) have greatly expanded the potential for automated code-related tasks. Two primary methodologies are used in this domain: prompt engineering and fine-tuning. Prompt engineering involves applying different strategies to query LLMs, like ChatGPT, while fine-tuning further adapts pre-trained models, such as CodeBERT, by training them on task-specific data. Despite the growth in the area, there remains a lack of comprehensive comparative analysis between the approaches for code models. In this paper, we evaluate GPT-4 using three prompt enginee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10508","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/2310.10508/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":"2310.10508","created_at":"2026-07-05T10:17:05.474508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10508v2","created_at":"2026-07-05T10:17:05.474508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10508","created_at":"2026-07-05T10:17:05.474508+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGGGZMYZB2PZ","created_at":"2026-07-05T10:17:05.474508+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGGGZMYZB2PZU23Y","created_at":"2026-07-05T10:17:05.474508+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGGGZMYZ","created_at":"2026-07-05T10:17:05.474508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19216","citing_title":"No Two Developers Think Alike: How Problem-Solving Styles and Experience Shape Needs in Conversational Interaction with Copilot","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09401","citing_title":"Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00049","citing_title":"Prompting GPT-5 on Scrum Certification Questions: An Empirical Accuracy Study","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00048","citing_title":"Comparing Large Language Models on Scrum Certification-Style Questions: Accuracy, Stability, and Error Patterns","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2402.01411","citing_title":"CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19045","citing_title":"Efficient Black-Box Fault Localization for System-Level Test Code Using Large Language Models","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26615","citing_title":"TDD Governance for Multi-Agent Code Generation via Prompt Engineering","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26211","citing_title":"OMEGA: Optimizing Machine Learning by Evaluating Generated Algorithms","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15385","citing_title":"Prompt-Driven Code Summarization: A Systematic Literature Review","ref_index":95,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW","json":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW.json","graph_json":"https://pith.science/api/pith-number/OGGGZMYZB2PZU23YBW4NURVGBW/graph.json","events_json":"https://pith.science/api/pith-number/OGGGZMYZB2PZU23YBW4NURVGBW/events.json","paper":"https://pith.science/paper/OGGGZMYZ"},"agent_actions":{"view_html":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW","download_json":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW.json","view_paper":"https://pith.science/paper/OGGGZMYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10508&json=true","fetch_graph":"https://pith.science/api/pith-number/OGGGZMYZB2PZU23YBW4NURVGBW/graph.json","fetch_events":"https://pith.science/api/pith-number/OGGGZMYZB2PZU23YBW4NURVGBW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW/action/storage_attestation","attest_author":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW/action/author_attestation","sign_citation":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW/action/citation_signature","submit_replication":"https://pith.science/pith/OGGGZMYZB2PZU23YBW4NURVGBW/action/replication_record"}},"created_at":"2026-07-05T10:17:05.474508+00:00","updated_at":"2026-07-05T10:17:05.474508+00:00"}