{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5ZHVXQ5V2B74TNHWJLQY4525NJ","short_pith_number":"pith:5ZHVXQ5V","schema_version":"1.0","canonical_sha256":"ee4f5bc3b5d07fc9b4f64ae18e775d6a701ec4bf0a49bf3b10cfbc5e991e947a","source":{"kind":"arxiv","id":"2212.10481","version":2},"attestation_state":"computed","paper":{"title":"Execution-Based Evaluation for Open-Domain Code Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Daniel Fried, Graham Neubig, Shuyan Zhou, Zhiruo Wang","submitted_at":"2022-12-20T17:54:37Z","abstract_excerpt":"To extend the scope of coding queries to more realistic settings, we propose ODEX, the first Open-Domain EXecution-based natural language (NL) to Python code generation dataset. ODEX has 945 NL-Code pairs spanning 79 diverse libraries, along with 1,707 human-written test cases for execution. Our NL-Code pairs are harvested from StackOverflow forums to encourage natural and practical coding queries. Moreover, ODEX supports four natural languages as intents, in English, Spanish, Japanese, and Russian. ODEX unveils intriguing behavioral differences among top-performing code language models (LM). "},"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":"2212.10481","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2022-12-20T17:54:37Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6d2290b3f539d2ca9b7d89c3deb9f9c387627ad143e57dd6a1ca88bbe89152e0","abstract_canon_sha256":"93af15d6fadee5b6c654556cd956a00d78d71ba6c3b2e351a1b459cecdeb1a5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:44.203494Z","signature_b64":"N7RQ9qzxFeT5PT6Vo3TKXVaazNDuL4aCy51uOEiC2CrSHPY3G3sUmLyt7AdW1KbBbyrl9Z3UHujpZ6sFi2utBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee4f5bc3b5d07fc9b4f64ae18e775d6a701ec4bf0a49bf3b10cfbc5e991e947a","last_reissued_at":"2026-07-05T06:11:44.202974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:44.202974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Execution-Based Evaluation for Open-Domain Code Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Daniel Fried, Graham Neubig, Shuyan Zhou, Zhiruo Wang","submitted_at":"2022-12-20T17:54:37Z","abstract_excerpt":"To extend the scope of coding queries to more realistic settings, we propose ODEX, the first Open-Domain EXecution-based natural language (NL) to Python code generation dataset. ODEX has 945 NL-Code pairs spanning 79 diverse libraries, along with 1,707 human-written test cases for execution. Our NL-Code pairs are harvested from StackOverflow forums to encourage natural and practical coding queries. Moreover, ODEX supports four natural languages as intents, in English, Spanish, Japanese, and Russian. ODEX unveils intriguing behavioral differences among top-performing code language models (LM). "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10481","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/2212.10481/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":"2212.10481","created_at":"2026-07-05T06:11:44.203034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10481v2","created_at":"2026-07-05T06:11:44.203034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10481","created_at":"2026-07-05T06:11:44.203034+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZHVXQ5V2B74","created_at":"2026-07-05T06:11:44.203034+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZHVXQ5V2B74TNHW","created_at":"2026-07-05T06:11:44.203034+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZHVXQ5V","created_at":"2026-07-05T06:11:44.203034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06411","citing_title":"RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2509.22202","citing_title":"Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09686","citing_title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":280,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22659","citing_title":"RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2305.06161","citing_title":"StarCoder: may the source be with you!","ref_index":296,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07974","citing_title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZHVXQ5V2B74TNHWJLQY4525NJ","json":"https://pith.science/pith/5ZHVXQ5V2B74TNHWJLQY4525NJ.json","graph_json":"https://pith.science/api/pith-number/5ZHVXQ5V2B74TNHWJLQY4525NJ/graph.json","events_json":"https://pith.science/api/pith-number/5ZHVXQ5V2B74TNHWJLQY4525NJ/events.json","paper":"https://pith.science/paper/5ZHVXQ5V"},"agent_actions":{"view_html":"https://pith.science/pith/5ZHVXQ5V2B74TNHWJLQY4525NJ","download_json":"https://pith.science/pith/5ZHVXQ5V2B74TNHWJLQY4525NJ.json","view_paper":"https://pith.science/paper/5ZHVXQ5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10481&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZHVXQ5V2B74TNHWJLQY4525NJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZHVXQ5V2B74TNHWJLQY4525NJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZHVXQ5V2B74TNHWJLQY4525NJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZHVXQ5V2B74TNHWJLQY4525NJ/action/storage_attestation","attest_author":"https://pith.science/pith/5ZHVXQ5V2B74TNHWJLQY4525NJ/action/author_attestation","sign_citation":"https://pith.science/pith/5ZHVXQ5V2B74TNHWJLQY4525NJ/action/citation_signature","submit_replication":"https://pith.science/pith/5ZHVXQ5V2B74TNHWJLQY4525NJ/action/replication_record"}},"created_at":"2026-07-05T06:11:44.203034+00:00","updated_at":"2026-07-05T06:11:44.203034+00:00"}