{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M6VKT4IQ23TDIGEL3ZCUO4SZT5","short_pith_number":"pith:M6VKT4IQ","schema_version":"1.0","canonical_sha256":"67aaa9f110d6e634188bde454772599f452ee9621be5bb4c2f02933901df639b","source":{"kind":"arxiv","id":"2408.10577","version":1},"attestation_state":"computed","paper":{"title":"Optimizing Large Language Model Hyperparameters for Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ahnaf Ibn Sayeed, Chetan Arora, Christoph Treude, Fanyu Wang, Sherlock Licorish","submitted_at":"2024-08-20T06:32:57Z","abstract_excerpt":"Large Language Models (LLMs), such as GPT models, are increasingly used in software engineering for various tasks, such as code generation, requirements management, and debugging. While automating these tasks has garnered significant attention, a systematic study on the impact of varying hyperparameters on code generation outcomes remains unexplored. This study aims to assess LLMs' code generation performance by exhaustively exploring the impact of various hyperparameters. Hyperparameters for LLMs are adjustable settings that affect the model's behaviour and performance. Specifically, we inves"},"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":"2408.10577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-08-20T06:32:57Z","cross_cats_sorted":[],"title_canon_sha256":"6cc41814c507674753956559ce99dfea8fa590e332145c4da2dafd6df4b96a80","abstract_canon_sha256":"071bc07ffb501ae6d6b5b4f8b92019d9edf761282c7e6ae19a0aea1cb3d09549"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:14.071235Z","signature_b64":"sXa35KY+sTKPSbNgqTjYqqTB0w0RCZBdVQv/ibfnbR95TjudchwDdORl8H4Ydp3ENumAKzsVdkL8HoOJA1iUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67aaa9f110d6e634188bde454772599f452ee9621be5bb4c2f02933901df639b","last_reissued_at":"2026-07-05T08:57:14.070832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:14.070832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Large Language Model Hyperparameters for Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ahnaf Ibn Sayeed, Chetan Arora, Christoph Treude, Fanyu Wang, Sherlock Licorish","submitted_at":"2024-08-20T06:32:57Z","abstract_excerpt":"Large Language Models (LLMs), such as GPT models, are increasingly used in software engineering for various tasks, such as code generation, requirements management, and debugging. While automating these tasks has garnered significant attention, a systematic study on the impact of varying hyperparameters on code generation outcomes remains unexplored. This study aims to assess LLMs' code generation performance by exhaustively exploring the impact of various hyperparameters. Hyperparameters for LLMs are adjustable settings that affect the model's behaviour and performance. Specifically, we inves"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10577","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/2408.10577/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":"2408.10577","created_at":"2026-07-05T08:57:14.070892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10577v1","created_at":"2026-07-05T08:57:14.070892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10577","created_at":"2026-07-05T08:57:14.070892+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6VKT4IQ23TD","created_at":"2026-07-05T08:57:14.070892+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6VKT4IQ23TDIGEL","created_at":"2026-07-05T08:57:14.070892+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6VKT4IQ","created_at":"2026-07-05T08:57:14.070892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31135","citing_title":"R+R: Reassessing Java Security API Misuse in Current LLMs: A Replication on JCA and JSSE APIs with External Security Knowledge","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13413","citing_title":"Dataset-Level Metrics Attenuate Non-Determinism: A Fine-Grained Non-Determinism Evaluation in Diffusion Language Models","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6VKT4IQ23TDIGEL3ZCUO4SZT5","json":"https://pith.science/pith/M6VKT4IQ23TDIGEL3ZCUO4SZT5.json","graph_json":"https://pith.science/api/pith-number/M6VKT4IQ23TDIGEL3ZCUO4SZT5/graph.json","events_json":"https://pith.science/api/pith-number/M6VKT4IQ23TDIGEL3ZCUO4SZT5/events.json","paper":"https://pith.science/paper/M6VKT4IQ"},"agent_actions":{"view_html":"https://pith.science/pith/M6VKT4IQ23TDIGEL3ZCUO4SZT5","download_json":"https://pith.science/pith/M6VKT4IQ23TDIGEL3ZCUO4SZT5.json","view_paper":"https://pith.science/paper/M6VKT4IQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10577&json=true","fetch_graph":"https://pith.science/api/pith-number/M6VKT4IQ23TDIGEL3ZCUO4SZT5/graph.json","fetch_events":"https://pith.science/api/pith-number/M6VKT4IQ23TDIGEL3ZCUO4SZT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6VKT4IQ23TDIGEL3ZCUO4SZT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6VKT4IQ23TDIGEL3ZCUO4SZT5/action/storage_attestation","attest_author":"https://pith.science/pith/M6VKT4IQ23TDIGEL3ZCUO4SZT5/action/author_attestation","sign_citation":"https://pith.science/pith/M6VKT4IQ23TDIGEL3ZCUO4SZT5/action/citation_signature","submit_replication":"https://pith.science/pith/M6VKT4IQ23TDIGEL3ZCUO4SZT5/action/replication_record"}},"created_at":"2026-07-05T08:57:14.070892+00:00","updated_at":"2026-07-05T08:57:14.070892+00:00"}