{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5ZHVXQ5V2B74TNHWJLQY4525NJ","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":"93af15d6fadee5b6c654556cd956a00d78d71ba6c3b2e351a1b459cecdeb1a5b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2022-12-20T17:54:37Z","title_canon_sha256":"6d2290b3f539d2ca9b7d89c3deb9f9c387627ad143e57dd6a1ca88bbe89152e0"},"schema_version":"1.0","source":{"id":"2212.10481","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10481","created_at":"2026-07-05T06:11:44Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10481v2","created_at":"2026-07-05T06:11:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10481","created_at":"2026-07-05T06:11:44Z"},{"alias_kind":"pith_short_12","alias_value":"5ZHVXQ5V2B74","created_at":"2026-07-05T06:11:44Z"},{"alias_kind":"pith_short_16","alias_value":"5ZHVXQ5V2B74TNHW","created_at":"2026-07-05T06:11:44Z"},{"alias_kind":"pith_short_8","alias_value":"5ZHVXQ5V","created_at":"2026-07-05T06:11:44Z"}],"graph_snapshots":[{"event_id":"sha256:c956331fd1e2784a46ff8ab08e834d7b615daab8626811ca70d264c4afb0be33","target":"graph","created_at":"2026-07-05T06:11:44Z","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/2212.10481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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). ","authors_text":"Daniel Fried, Graham Neubig, Shuyan Zhou, Zhiruo Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2022-12-20T17:54:37Z","title":"Execution-Based Evaluation for Open-Domain Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10481","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":"sha256:4491a67bf810203088b8af13b4460b8a9f15bd24a6e43594148fb860e6618132","target":"record","created_at":"2026-07-05T06:11:44Z","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":"93af15d6fadee5b6c654556cd956a00d78d71ba6c3b2e351a1b459cecdeb1a5b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2022-12-20T17:54:37Z","title_canon_sha256":"6d2290b3f539d2ca9b7d89c3deb9f9c387627ad143e57dd6a1ca88bbe89152e0"},"schema_version":"1.0","source":{"id":"2212.10481","kind":"arxiv","version":2}},"canonical_sha256":"ee4f5bc3b5d07fc9b4f64ae18e775d6a701ec4bf0a49bf3b10cfbc5e991e947a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee4f5bc3b5d07fc9b4f64ae18e775d6a701ec4bf0a49bf3b10cfbc5e991e947a","first_computed_at":"2026-07-05T06:11:44.202974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:44.202974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N7RQ9qzxFeT5PT6Vo3TKXVaazNDuL4aCy51uOEiC2CrSHPY3G3sUmLyt7AdW1KbBbyrl9Z3UHujpZ6sFi2utBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:44.203494Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10481","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4491a67bf810203088b8af13b4460b8a9f15bd24a6e43594148fb860e6618132","sha256:c956331fd1e2784a46ff8ab08e834d7b615daab8626811ca70d264c4afb0be33"],"state_sha256":"0e3a2556377fe48707fcff9b58c30043bd3c769db194103575bd456ca57dec60"}