{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N6YY7W57PEELFY7BG5BNG3ULIA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"00a0a0078a100f28cbbd62be6fca928443cb40f3ff2c4a7933570f4a199e953f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T11:43:37Z","title_canon_sha256":"c8a957e3616fc0be15e15a641346450506b4d7af37ffcc695971ec0cd6acb9c3"},"schema_version":"1.0","source":{"id":"2505.13004","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13004","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13004v1","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13004","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"N6YY7W57PEEL","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"N6YY7W57PEELFY7B","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"N6YY7W57","created_at":"2026-07-05T11:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:1d7c51e84498efddeffdb7c15efbd73ab0698ca791ba9127bc56f31f382b4ca1","target":"graph","created_at":"2026-07-05T11:05:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.13004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T11:43:37Z","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13004","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5d906619641dfa589510597f5a23a28cbe7d92aa3c272b3f42865e7a33da8d23","target":"record","created_at":"2026-07-05T11:05:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"00a0a0078a100f28cbbd62be6fca928443cb40f3ff2c4a7933570f4a199e953f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T11:43:37Z","title_canon_sha256":"c8a957e3616fc0be15e15a641346450506b4d7af37ffcc695971ec0cd6acb9c3"},"schema_version":"1.0","source":{"id":"2505.13004","kind":"arxiv","version":1}},"canonical_sha256":"6fb18fdbbf7908b2e3e13742d36e8b4039b93f387494c6078a141fe4ae4c6897","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fb18fdbbf7908b2e3e13742d36e8b4039b93f387494c6078a141fe4ae4c6897","first_computed_at":"2026-07-05T11:05:13.643576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:13.643576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aoij8yEgk96G9zgBPbbm7Apt2lOWedGO+G38c4BV6Jquf5gSLDBL2VlACLLWsCLen1CULUUprYHqarMucdeHCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:13.644053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13004","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d906619641dfa589510597f5a23a28cbe7d92aa3c272b3f42865e7a33da8d23","sha256:1d7c51e84498efddeffdb7c15efbd73ab0698ca791ba9127bc56f31f382b4ca1"],"state_sha256":"b6758f1a27737190b9f3d1796b1ff5caeedf4084214a66c51d5db0be84e9e583"}