{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N6YY7W57PEELFY7BG5BNG3ULIA","short_pith_number":"pith:N6YY7W57","schema_version":"1.0","canonical_sha256":"6fb18fdbbf7908b2e3e13742d36e8b4039b93f387494c6078a141fe4ae4c6897","source":{"kind":"arxiv","id":"2505.13004","version":1},"attestation_state":"computed","paper":{"title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boyu Zhu, Dong Huang, Heming Cui, Jie M. Zhang, Luu Anh Tuan, Mingzhe Du, Qianru Zhang, See-kiong Ng, Siu-Ming Yiu, Terry Yue Zhuo, Yuhao Qing, Zhijiang Guo","submitted_at":"2025-05-19T11:43:37Z","abstract_excerpt":"Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To address this gap, we introduce EffiBench-X, the first multi-language benchmark designed to measure the efficiency of LLM-generated code. EffiBench-X supports Python, C++, Java, JavaScript, Ruby, and Golang. It comprises competitive programming tasks with human-expert solutions as efficiency baselines. Evaluating state-of-the-art LLMs on EffiBench-X reveals that while models generate functionally correct code, they consist"},"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":"2505.13004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T11:43:37Z","cross_cats_sorted":[],"title_canon_sha256":"c8a957e3616fc0be15e15a641346450506b4d7af37ffcc695971ec0cd6acb9c3","abstract_canon_sha256":"00a0a0078a100f28cbbd62be6fca928443cb40f3ff2c4a7933570f4a199e953f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:13.644053Z","signature_b64":"aoij8yEgk96G9zgBPbbm7Apt2lOWedGO+G38c4BV6Jquf5gSLDBL2VlACLLWsCLen1CULUUprYHqarMucdeHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fb18fdbbf7908b2e3e13742d36e8b4039b93f387494c6078a141fe4ae4c6897","last_reissued_at":"2026-07-05T11:05:13.643576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:13.643576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boyu Zhu, Dong Huang, Heming Cui, Jie M. Zhang, Luu Anh Tuan, Mingzhe Du, Qianru Zhang, See-kiong Ng, Siu-Ming Yiu, Terry Yue Zhuo, Yuhao Qing, Zhijiang Guo","submitted_at":"2025-05-19T11:43:37Z","abstract_excerpt":"Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To address this gap, we introduce EffiBench-X, the first multi-language benchmark designed to measure the efficiency of LLM-generated code. EffiBench-X supports Python, C++, Java, JavaScript, Ruby, and Golang. It comprises competitive programming tasks with human-expert solutions as efficiency baselines. Evaluating state-of-the-art LLMs on EffiBench-X reveals that while models generate functionally correct code, they consist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13004","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/2505.13004/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":"2505.13004","created_at":"2026-07-05T11:05:13.643636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13004v1","created_at":"2026-07-05T11:05:13.643636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13004","created_at":"2026-07-05T11:05:13.643636+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6YY7W57PEEL","created_at":"2026-07-05T11:05:13.643636+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6YY7W57PEELFY7B","created_at":"2026-07-05T11:05:13.643636+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6YY7W57","created_at":"2026-07-05T11:05:13.643636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15222","citing_title":"PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2506.01249","citing_title":"SysLLMatic: Large Language Models are Software System Optimizers","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01379","citing_title":"Multi-LLM Orchestration for High-Quality Code Generation: Exploiting Complementary Model Strengths","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12268","citing_title":"CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6YY7W57PEELFY7BG5BNG3ULIA","json":"https://pith.science/pith/N6YY7W57PEELFY7BG5BNG3ULIA.json","graph_json":"https://pith.science/api/pith-number/N6YY7W57PEELFY7BG5BNG3ULIA/graph.json","events_json":"https://pith.science/api/pith-number/N6YY7W57PEELFY7BG5BNG3ULIA/events.json","paper":"https://pith.science/paper/N6YY7W57"},"agent_actions":{"view_html":"https://pith.science/pith/N6YY7W57PEELFY7BG5BNG3ULIA","download_json":"https://pith.science/pith/N6YY7W57PEELFY7BG5BNG3ULIA.json","view_paper":"https://pith.science/paper/N6YY7W57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13004&json=true","fetch_graph":"https://pith.science/api/pith-number/N6YY7W57PEELFY7BG5BNG3ULIA/graph.json","fetch_events":"https://pith.science/api/pith-number/N6YY7W57PEELFY7BG5BNG3ULIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6YY7W57PEELFY7BG5BNG3ULIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6YY7W57PEELFY7BG5BNG3ULIA/action/storage_attestation","attest_author":"https://pith.science/pith/N6YY7W57PEELFY7BG5BNG3ULIA/action/author_attestation","sign_citation":"https://pith.science/pith/N6YY7W57PEELFY7BG5BNG3ULIA/action/citation_signature","submit_replication":"https://pith.science/pith/N6YY7W57PEELFY7BG5BNG3ULIA/action/replication_record"}},"created_at":"2026-07-05T11:05:13.643636+00:00","updated_at":"2026-07-05T11:05:13.643636+00:00"}