{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BHUAKOOI4FNMW55IGZ5GP2TEW5","short_pith_number":"pith:BHUAKOOI","schema_version":"1.0","canonical_sha256":"09e80539c8e15acb77a8367a67ea64b740df00f3e724a39a459587b833cb2c45","source":{"kind":"arxiv","id":"2410.07331","version":2},"attestation_state":"computed","paper":{"title":"DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fangyu Lei, Jianwen Luo, Jun Zhao, Kang Liu, Lifu Huang, Shizhu He, Xiao Liu, Yan Yu, Yifan Wei, Yiming Huang, Yitong Zhang","submitted_at":"2024-10-09T18:00:05Z","abstract_excerpt":"We introduce DA-Code, a code generation benchmark specifically designed to assess LLMs on agent-based data science tasks. This benchmark features three core elements: First, the tasks within DA-Code are inherently challenging, setting them apart from traditional code generation tasks and demanding advanced coding skills in grounding and planning. Second, examples in DA-Code are all based on real and diverse data, covering a wide range of complex data wrangling and analytics tasks. Third, to solve the tasks, the models must utilize complex data science programming languages, to perform intricat"},"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":"2410.07331","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T18:00:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5e78c11aa30fe2de84026638b4c6c2af76510aae1f2036485817c216c3da3d4","abstract_canon_sha256":"ada5916b49bd1355c94f89b9cfd5c0355c5648f2afec395d429df38c4696b8e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:54.400913Z","signature_b64":"ikiQQm92Bsse20tfCsWobwxAjliKPhCR5rtRHnj1URgh+m/eOSIPcpdsPf6yW78GxBQsw6pv9eqRigOuKBCKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09e80539c8e15acb77a8367a67ea64b740df00f3e724a39a459587b833cb2c45","last_reissued_at":"2026-07-05T09:18:54.400454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:54.400454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fangyu Lei, Jianwen Luo, Jun Zhao, Kang Liu, Lifu Huang, Shizhu He, Xiao Liu, Yan Yu, Yifan Wei, Yiming Huang, Yitong Zhang","submitted_at":"2024-10-09T18:00:05Z","abstract_excerpt":"We introduce DA-Code, a code generation benchmark specifically designed to assess LLMs on agent-based data science tasks. This benchmark features three core elements: First, the tasks within DA-Code are inherently challenging, setting them apart from traditional code generation tasks and demanding advanced coding skills in grounding and planning. Second, examples in DA-Code are all based on real and diverse data, covering a wide range of complex data wrangling and analytics tasks. Third, to solve the tasks, the models must utilize complex data science programming languages, to perform intricat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07331","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/2410.07331/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":"2410.07331","created_at":"2026-07-05T09:18:54.400512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07331v2","created_at":"2026-07-05T09:18:54.400512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07331","created_at":"2026-07-05T09:18:54.400512+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHUAKOOI4FNM","created_at":"2026-07-05T09:18:54.400512+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHUAKOOI4FNMW55I","created_at":"2026-07-05T09:18:54.400512+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHUAKOOI","created_at":"2026-07-05T09:18:54.400512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21140","citing_title":"Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09774","citing_title":"Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00051","citing_title":"Business Utility of Large Language Models as Exploratory Data Analysis Agents","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09774","citing_title":"Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16321","citing_title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BHUAKOOI4FNMW55IGZ5GP2TEW5","json":"https://pith.science/pith/BHUAKOOI4FNMW55IGZ5GP2TEW5.json","graph_json":"https://pith.science/api/pith-number/BHUAKOOI4FNMW55IGZ5GP2TEW5/graph.json","events_json":"https://pith.science/api/pith-number/BHUAKOOI4FNMW55IGZ5GP2TEW5/events.json","paper":"https://pith.science/paper/BHUAKOOI"},"agent_actions":{"view_html":"https://pith.science/pith/BHUAKOOI4FNMW55IGZ5GP2TEW5","download_json":"https://pith.science/pith/BHUAKOOI4FNMW55IGZ5GP2TEW5.json","view_paper":"https://pith.science/paper/BHUAKOOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07331&json=true","fetch_graph":"https://pith.science/api/pith-number/BHUAKOOI4FNMW55IGZ5GP2TEW5/graph.json","fetch_events":"https://pith.science/api/pith-number/BHUAKOOI4FNMW55IGZ5GP2TEW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHUAKOOI4FNMW55IGZ5GP2TEW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHUAKOOI4FNMW55IGZ5GP2TEW5/action/storage_attestation","attest_author":"https://pith.science/pith/BHUAKOOI4FNMW55IGZ5GP2TEW5/action/author_attestation","sign_citation":"https://pith.science/pith/BHUAKOOI4FNMW55IGZ5GP2TEW5/action/citation_signature","submit_replication":"https://pith.science/pith/BHUAKOOI4FNMW55IGZ5GP2TEW5/action/replication_record"}},"created_at":"2026-07-05T09:18:54.400512+00:00","updated_at":"2026-07-05T09:18:54.400512+00:00"}