{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NF5TMPVETZZXZOUXCJNQ6OKXVU","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":"f36cda2ce95e0e3083feb531bcbb6e6b2898dc9a440265ebda1b0dad7af33bee","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-11-18T17:20:27Z","title_canon_sha256":"4f82110e7726f67336cd5103f71003e823ed9c1a133b2d468b483a2a4ae6d403"},"schema_version":"1.0","source":{"id":"2211.11501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.11501","created_at":"2026-07-05T05:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2211.11501v1","created_at":"2026-07-05T05:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11501","created_at":"2026-07-05T05:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"NF5TMPVETZZX","created_at":"2026-07-05T05:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"NF5TMPVETZZXZOUX","created_at":"2026-07-05T05:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"NF5TMPVE","created_at":"2026-07-05T05:17:54Z"}],"graph_snapshots":[{"event_id":"sha256:1a692378e7014016d73ac9b300b39a3f41b5a7d6fb94ebc8e5ec73adb90ea5cd","target":"graph","created_at":"2026-07-05T05:17:54Z","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/2211.11501/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce DS-1000, a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas. Compared to prior works, DS-1000 incorporates three core features. First, our problems reflect diverse, realistic, and practical use cases since we collected them from StackOverflow. Second, our automatic evaluation is highly specific (reliable) -- across all Codex-002-predicted solutions that our evaluation accept, only 1.8% of them are incorrect; we achieve this with multi-criteria metrics, checking both functional correctness by running test case","authors_text":"Chengxi Li, Daniel Fried, Luke Zettlemoyer, Ruiqi Zhong, Scott Wen-tau Yih, Sida Wang, Tao Yu, Tianyi Zhang, Yiming Wang, Yuhang Lai","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-11-18T17:20:27Z","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11501","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:c93429b61c5e7c00beaa63669fc32af447ef71a88be5315259cf6f0c092c308e","target":"record","created_at":"2026-07-05T05:17:54Z","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":"f36cda2ce95e0e3083feb531bcbb6e6b2898dc9a440265ebda1b0dad7af33bee","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-11-18T17:20:27Z","title_canon_sha256":"4f82110e7726f67336cd5103f71003e823ed9c1a133b2d468b483a2a4ae6d403"},"schema_version":"1.0","source":{"id":"2211.11501","kind":"arxiv","version":1}},"canonical_sha256":"697b363ea49e737cba97125b0f3957ad2b0e66629d1095085f567309ae960471","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"697b363ea49e737cba97125b0f3957ad2b0e66629d1095085f567309ae960471","first_computed_at":"2026-07-05T05:17:54.267061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:54.267061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZxwuMWc4qB29kxauNCe+arqTX0qJwjyGb7px3rcUQi3aIYH2SP+BXld8nS7L+xPhL+690RkQsv8/j6GvOjIyAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:54.267503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.11501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c93429b61c5e7c00beaa63669fc32af447ef71a88be5315259cf6f0c092c308e","sha256:1a692378e7014016d73ac9b300b39a3f41b5a7d6fb94ebc8e5ec73adb90ea5cd"],"state_sha256":"4820f58450aa21d595df383700aa80578d751451b91715c078f352f3a7cee567"}