{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SIFPEXAI2POCMBO7AWQ62IGUZX","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":"9a32677cb16a9c2bc04165deeed14b6ae6ad2f7b55c7c44faa65be632e030df1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T17:31:51Z","title_canon_sha256":"aeb8b39e0ac06870fe7646ab41d020de80a5427a3be24be66e89eaa6308c0523"},"schema_version":"1.0","source":{"id":"2502.13897","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13897","created_at":"2026-07-05T10:17:02Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13897v1","created_at":"2026-07-05T10:17:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13897","created_at":"2026-07-05T10:17:02Z"},{"alias_kind":"pith_short_12","alias_value":"SIFPEXAI2POC","created_at":"2026-07-05T10:17:02Z"},{"alias_kind":"pith_short_16","alias_value":"SIFPEXAI2POCMBO7","created_at":"2026-07-05T10:17:02Z"},{"alias_kind":"pith_short_8","alias_value":"SIFPEXAI","created_at":"2026-07-05T10:17:02Z"}],"graph_snapshots":[{"event_id":"sha256:61506821e4f7398968910f473c5bbb611b1521d680d66492e8e278dc790059e9","target":"graph","created_at":"2026-07-05T10:17:02Z","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/2502.13897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents DataSciBench, a comprehensive benchmark for evaluating Large Language Model (LLM) capabilities in data science. Recent related benchmarks have primarily focused on single tasks, easily obtainable ground truth, and straightforward evaluation metrics, which limits the scope of tasks that can be evaluated. In contrast, DataSciBench is constructed based on a more comprehensive and curated collection of natural and challenging prompts for uncertain ground truth and evaluation metrics. We develop a semi-automated pipeline for generating ground truth (GT) and validating evaluation","authors_text":"Dan Zhang, Fengzu Li, Jie Tang, Lekang Yang, Min Cai, Sining Zhoubian, Tianjiao Dong, Wei Wang, Yisong Yue, Ziniu Hu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T17:31:51Z","title":"DataSciBench: An LLM Agent Benchmark for Data Science"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13897","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":"sha256:5aca0e86bb43b386dc36687d94462ecc4b29b80ce4659bf05741cf7e2150f04b","target":"record","created_at":"2026-07-05T10:17:02Z","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":"9a32677cb16a9c2bc04165deeed14b6ae6ad2f7b55c7c44faa65be632e030df1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T17:31:51Z","title_canon_sha256":"aeb8b39e0ac06870fe7646ab41d020de80a5427a3be24be66e89eaa6308c0523"},"schema_version":"1.0","source":{"id":"2502.13897","kind":"arxiv","version":1}},"canonical_sha256":"920af25c08d3dc2605df05a1ed20d4cdfe89471f5ef9f5311b86875680fa7b25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"920af25c08d3dc2605df05a1ed20d4cdfe89471f5ef9f5311b86875680fa7b25","first_computed_at":"2026-07-05T10:17:02.304507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:02.304507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VQNM5L/L7o05iwi/KXpyNQmMbXiXJC2yz3v/IJTi6kEF7sQq65NO7428XXUKglkS0ExyG8EwCrFvPLkRNuDcCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:02.304910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13897","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5aca0e86bb43b386dc36687d94462ecc4b29b80ce4659bf05741cf7e2150f04b","sha256:61506821e4f7398968910f473c5bbb611b1521d680d66492e8e278dc790059e9"],"state_sha256":"d851b804637d00da04f83ab8f92797bf1bd390fec5043506bd0a13468f63b8d4"}