{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RFXSIEZ2HSWK3NMNZX6HT56APE","short_pith_number":"pith:RFXSIEZ2","schema_version":"1.0","canonical_sha256":"896f24133a3cacadb58dcdfc79f7c079369517d9d4ba66f01527c73a9ac4af87","source":{"kind":"arxiv","id":"2206.13179","version":2},"attestation_state":"computed","paper":{"title":"AixBench: A Code Generation Benchmark Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"(2) Peking University), Ge Li (2), He Wei (1) ((1) aiXcoder, He Zong (1), Siyuan Jiang (1), Xiaowei Miao (1), Yang Liu (1), Yiyang Hao (1), Yongqiang Liu (1)","submitted_at":"2022-06-27T10:44:48Z","abstract_excerpt":"We present a benchmark dataset for evaluating method-level code generation task. The benchmark contains a dataset of 175 samples for automated evaluation and a dataset of 161 samples for manual evaluation. We also present a new metric for automatically evaluating the correctness of the generated code, and a set of criteria to manually evaluating the overall quality of the generated code."},"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":"2206.13179","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-06-27T10:44:48Z","cross_cats_sorted":[],"title_canon_sha256":"affadcbef03d4c41ab05ab5df11b46deadbfbf06b3cdea05f3d6545b0be21cce","abstract_canon_sha256":"89d087286dfd36591bb433374da0aab7040549f17d8db88b78463d92399fef75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:19.856035Z","signature_b64":"J1N4t7cDvJIoWrkyjWgWnbouLD5KEyHadGC/j2Ffv3TrPOAzmhUjimroZk0KhBef56CX5qBIfgnsgcYhEQGiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"896f24133a3cacadb58dcdfc79f7c079369517d9d4ba66f01527c73a9ac4af87","last_reissued_at":"2026-07-05T04:42:19.855578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:19.855578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AixBench: A Code Generation Benchmark Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"(2) Peking University), Ge Li (2), He Wei (1) ((1) aiXcoder, He Zong (1), Siyuan Jiang (1), Xiaowei Miao (1), Yang Liu (1), Yiyang Hao (1), Yongqiang Liu (1)","submitted_at":"2022-06-27T10:44:48Z","abstract_excerpt":"We present a benchmark dataset for evaluating method-level code generation task. The benchmark contains a dataset of 175 samples for automated evaluation and a dataset of 161 samples for manual evaluation. We also present a new metric for automatically evaluating the correctness of the generated code, and a set of criteria to manually evaluating the overall quality of the generated code."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13179","kind":"arxiv","version":2},"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/2206.13179/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":"2206.13179","created_at":"2026-07-05T04:42:19.855666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.13179v2","created_at":"2026-07-05T04:42:19.855666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13179","created_at":"2026-07-05T04:42:19.855666+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFXSIEZ2HSWK","created_at":"2026-07-05T04:42:19.855666+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFXSIEZ2HSWK3NMN","created_at":"2026-07-05T04:42:19.855666+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFXSIEZ2","created_at":"2026-07-05T04:42:19.855666+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.17181","citing_title":"A Study of LLMs' Preferences for Libraries and Programming Languages","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00433","citing_title":"Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFXSIEZ2HSWK3NMNZX6HT56APE","json":"https://pith.science/pith/RFXSIEZ2HSWK3NMNZX6HT56APE.json","graph_json":"https://pith.science/api/pith-number/RFXSIEZ2HSWK3NMNZX6HT56APE/graph.json","events_json":"https://pith.science/api/pith-number/RFXSIEZ2HSWK3NMNZX6HT56APE/events.json","paper":"https://pith.science/paper/RFXSIEZ2"},"agent_actions":{"view_html":"https://pith.science/pith/RFXSIEZ2HSWK3NMNZX6HT56APE","download_json":"https://pith.science/pith/RFXSIEZ2HSWK3NMNZX6HT56APE.json","view_paper":"https://pith.science/paper/RFXSIEZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.13179&json=true","fetch_graph":"https://pith.science/api/pith-number/RFXSIEZ2HSWK3NMNZX6HT56APE/graph.json","fetch_events":"https://pith.science/api/pith-number/RFXSIEZ2HSWK3NMNZX6HT56APE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFXSIEZ2HSWK3NMNZX6HT56APE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFXSIEZ2HSWK3NMNZX6HT56APE/action/storage_attestation","attest_author":"https://pith.science/pith/RFXSIEZ2HSWK3NMNZX6HT56APE/action/author_attestation","sign_citation":"https://pith.science/pith/RFXSIEZ2HSWK3NMNZX6HT56APE/action/citation_signature","submit_replication":"https://pith.science/pith/RFXSIEZ2HSWK3NMNZX6HT56APE/action/replication_record"}},"created_at":"2026-07-05T04:42:19.855666+00:00","updated_at":"2026-07-05T04:42:19.855666+00:00"}