{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OHB5QLO3HQCZZAHFD6SYAOJBIP","short_pith_number":"pith:OHB5QLO3","schema_version":"1.0","canonical_sha256":"71c3d82ddb3c059c80e51fa580392143fb6c831d218583d3eaa766006b01e0f1","source":{"kind":"arxiv","id":"2406.06647","version":4},"attestation_state":"computed","paper":{"title":"How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Christopher Lott, Hanghang Tong, James Ezick, Ruizhong Qiu, Weiliang Will Zeng","submitted_at":"2024-06-10T04:19:20Z","abstract_excerpt":"The emergence of large language models (LLMs) has significantly pushed the frontiers of program synthesis. Advancement of LLM-based program synthesis calls for a thorough evaluation of LLM-generated code. Most evaluation frameworks focus on the (functional) correctness of generated code; efficiency, as an important measure of code quality, has been overlooked in existing evaluations. In this work, we develop ENAMEL (EfficeNcy AutoMatic EvaLuator), a rigorous and high-standard benchmark for evaluating the capability of LLMs in generating efficient code. Firstly, we propose a new efficiency metr"},"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":"2406.06647","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-10T04:19:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b4711752396aecd89fb587cddec73ec93de9b59bea2bd7aab69bddf12397272f","abstract_canon_sha256":"5b0ada3a1d7e9fae9c9e6848e3d6c7c8aff9a40696ccda1c0ff6a1f6785dd644"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:34.345897Z","signature_b64":"w9neNPfMLQTEhKWT6vWjpukpbHPOvAOVJddZjePAQgkEXMb0SrRwKO5vnTBbRME2bmZwHgOppXoV/LY+vW8HDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71c3d82ddb3c059c80e51fa580392143fb6c831d218583d3eaa766006b01e0f1","last_reissued_at":"2026-07-05T10:16:34.345406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:34.345406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Christopher Lott, Hanghang Tong, James Ezick, Ruizhong Qiu, Weiliang Will Zeng","submitted_at":"2024-06-10T04:19:20Z","abstract_excerpt":"The emergence of large language models (LLMs) has significantly pushed the frontiers of program synthesis. Advancement of LLM-based program synthesis calls for a thorough evaluation of LLM-generated code. Most evaluation frameworks focus on the (functional) correctness of generated code; efficiency, as an important measure of code quality, has been overlooked in existing evaluations. In this work, we develop ENAMEL (EfficeNcy AutoMatic EvaLuator), a rigorous and high-standard benchmark for evaluating the capability of LLMs in generating efficient code. Firstly, we propose a new efficiency metr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06647","kind":"arxiv","version":4},"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/2406.06647/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":"2406.06647","created_at":"2026-07-05T10:16:34.345467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06647v4","created_at":"2026-07-05T10:16:34.345467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06647","created_at":"2026-07-05T10:16:34.345467+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHB5QLO3HQCZ","created_at":"2026-07-05T10:16:34.345467+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHB5QLO3HQCZZAHF","created_at":"2026-07-05T10:16:34.345467+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHB5QLO3","created_at":"2026-07-05T10:16:34.345467+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06826","citing_title":"SkelDPO: A Skeleton-Guided Direct Preference Optimization Framework for Efficient Code Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06821","citing_title":"Chiseling Out Efficiency: Structured Skeleton Supervision for Efficient Code Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04023","citing_title":"CodegenBench: Can LLMs Write Efficient Code Across Architectures?","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2510.15494","citing_title":"Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11280","citing_title":"Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24464","citing_title":"Incisor: Ex Ante Cloud Instance Selection for HPC Jobs","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OHB5QLO3HQCZZAHFD6SYAOJBIP","json":"https://pith.science/pith/OHB5QLO3HQCZZAHFD6SYAOJBIP.json","graph_json":"https://pith.science/api/pith-number/OHB5QLO3HQCZZAHFD6SYAOJBIP/graph.json","events_json":"https://pith.science/api/pith-number/OHB5QLO3HQCZZAHFD6SYAOJBIP/events.json","paper":"https://pith.science/paper/OHB5QLO3"},"agent_actions":{"view_html":"https://pith.science/pith/OHB5QLO3HQCZZAHFD6SYAOJBIP","download_json":"https://pith.science/pith/OHB5QLO3HQCZZAHFD6SYAOJBIP.json","view_paper":"https://pith.science/paper/OHB5QLO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06647&json=true","fetch_graph":"https://pith.science/api/pith-number/OHB5QLO3HQCZZAHFD6SYAOJBIP/graph.json","fetch_events":"https://pith.science/api/pith-number/OHB5QLO3HQCZZAHFD6SYAOJBIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHB5QLO3HQCZZAHFD6SYAOJBIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHB5QLO3HQCZZAHFD6SYAOJBIP/action/storage_attestation","attest_author":"https://pith.science/pith/OHB5QLO3HQCZZAHFD6SYAOJBIP/action/author_attestation","sign_citation":"https://pith.science/pith/OHB5QLO3HQCZZAHFD6SYAOJBIP/action/citation_signature","submit_replication":"https://pith.science/pith/OHB5QLO3HQCZZAHFD6SYAOJBIP/action/replication_record"}},"created_at":"2026-07-05T10:16:34.345467+00:00","updated_at":"2026-07-05T10:16:34.345467+00:00"}