{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2UF75TJCFO5HTC6DXTAIU24XO6","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":"0ff4fbcd91c3bb6d2f3d972c6fa975b0f9bab15a0eb77b64575479c0b9a64669","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T16:31:02Z","title_canon_sha256":"f228f207f677b3c3cd103c39615b9994aa3ebdb450c9619585eb35b85b42d829"},"schema_version":"1.0","source":{"id":"2308.01861","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01861","created_at":"2026-07-05T06:40:54Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01861v2","created_at":"2026-07-05T06:40:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01861","created_at":"2026-07-05T06:40:54Z"},{"alias_kind":"pith_short_12","alias_value":"2UF75TJCFO5H","created_at":"2026-07-05T06:40:54Z"},{"alias_kind":"pith_short_16","alias_value":"2UF75TJCFO5HTC6D","created_at":"2026-07-05T06:40:54Z"},{"alias_kind":"pith_short_8","alias_value":"2UF75TJC","created_at":"2026-07-05T06:40:54Z"}],"graph_snapshots":[{"event_id":"sha256:8ead8b82f4ad32397521eec9fac42316d66f53ae98d5f926b72f15666154ae0a","target":"graph","created_at":"2026-07-05T06:40:54Z","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/2308.01861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we make the first attempt to evaluate LLMs in a more challenging code generation scenario, i.e. class-level code generation. We first manually construct the first class-level code generation benchmark ClassEval of 100 class-level Python code generation tasks with approximately 500 person-hours. Based on it, we then perform the first study of 11 state-of-the-art LLMs on class-level code generation. Based on our results, we have the following main findings. First, we find that all existing LLMs show much worse performance on class-level code generation compared to on standalone met","authors_text":"Chaofeng Sha, Hanlin Wang, Jiayi Feng, Junwei Liu, Kaixin Wang, Mingwei Liu, Xin Peng, Xueying Du, Yiling Lou, Yixuan Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T16:31:02Z","title":"ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01861","kind":"arxiv","version":2},"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":"sha256:5f777481f84eef1e4e4cc617733634277ea8555754579725f0d140e016e3cc47","target":"record","created_at":"2026-07-05T06:40:54Z","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":"0ff4fbcd91c3bb6d2f3d972c6fa975b0f9bab15a0eb77b64575479c0b9a64669","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T16:31:02Z","title_canon_sha256":"f228f207f677b3c3cd103c39615b9994aa3ebdb450c9619585eb35b85b42d829"},"schema_version":"1.0","source":{"id":"2308.01861","kind":"arxiv","version":2}},"canonical_sha256":"d50bfecd222bba798bc3bcc08a6b9777aeae9978d2c0955d566ded2bceec5486","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d50bfecd222bba798bc3bcc08a6b9777aeae9978d2c0955d566ded2bceec5486","first_computed_at":"2026-07-05T06:40:54.007884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:40:54.007884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1MwD5HhGq7DuNeKvgl2AmY/F+JB0Cg+STqoUUHiZaaAd8lL8PX1BsZ8EkudFS1TMK2bQyPJy1BXiNWaUwYFoCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:40:54.008469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.01861","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f777481f84eef1e4e4cc617733634277ea8555754579725f0d140e016e3cc47","sha256:8ead8b82f4ad32397521eec9fac42316d66f53ae98d5f926b72f15666154ae0a"],"state_sha256":"996498436d115299586e52fde6b0cb008da03bfcfd2b06b044e28463d048e2f2"}