{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EXDUE3AZNX3XDAF2MBFNMF4EU7","short_pith_number":"pith:EXDUE3AZ","schema_version":"1.0","canonical_sha256":"25c7426c196df77180ba604ad61784a7d911bfed2c279f5c261d8e40a8cae4e2","source":{"kind":"arxiv","id":"2601.13591","version":2},"attestation_state":"computed","paper":{"title":"DSAEval: Evaluating Data Science Agents on a Wide Range of Real-World Data Science Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Binyan Jiang, Defeng Sun, Jian Huang, Maojun Sun, Ruijian Han, Yancheng Yuan, Yifei Xie, Yue Wu","submitted_at":"2026-01-20T04:44:36Z","abstract_excerpt":"Recent LLM-based data agents aim to automate data science tasks ranging from data analysis to deep learning. However, the open-ended nature of real-world data science problems, which often span multiple taxonomies and lack standard answers, poses a significant challenge for evaluation. To address this, we introduce DSAEval, a benchmark comprising 641 real-world data science problems grounded in 285 diverse datasets, covering both structured and unstructured data (e.g., image and text). DSAEval incorporates three distinctive features: (1) Multimodal Environment Perception, which enables agents "},"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":"2601.13591","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-01-20T04:44:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"efcc5d06dead4c5b80c6ea7120dc140f4a6dd2be0cbcb62b10f4efda428219cf","abstract_canon_sha256":"c3c7aa4bc76c8af186421ac51385d4865c51d60a157095f67f3451d53f13ff54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:20.405352Z","signature_b64":"8EeY/zNaEf2ZWEnlrXMGz0FfLCLU/brcVa+wbjWaZDzDT2YeSw3FPoSPlWEX8sL9nM/eZXQbwmqj7y/WED7jBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25c7426c196df77180ba604ad61784a7d911bfed2c279f5c261d8e40a8cae4e2","last_reissued_at":"2026-06-12T01:09:20.404435Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:20.404435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DSAEval: Evaluating Data Science Agents on a Wide Range of Real-World Data Science Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Binyan Jiang, Defeng Sun, Jian Huang, Maojun Sun, Ruijian Han, Yancheng Yuan, Yifei Xie, Yue Wu","submitted_at":"2026-01-20T04:44:36Z","abstract_excerpt":"Recent LLM-based data agents aim to automate data science tasks ranging from data analysis to deep learning. However, the open-ended nature of real-world data science problems, which often span multiple taxonomies and lack standard answers, poses a significant challenge for evaluation. To address this, we introduce DSAEval, a benchmark comprising 641 real-world data science problems grounded in 285 diverse datasets, covering both structured and unstructured data (e.g., image and text). DSAEval incorporates three distinctive features: (1) Multimodal Environment Perception, which enables agents "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.13591","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/2601.13591/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":"2601.13591","created_at":"2026-06-12T01:09:20.404549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.13591v2","created_at":"2026-06-12T01:09:20.404549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.13591","created_at":"2026-06-12T01:09:20.404549+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXDUE3AZNX3X","created_at":"2026-06-12T01:09:20.404549+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXDUE3AZNX3XDAF2","created_at":"2026-06-12T01:09:20.404549+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXDUE3AZ","created_at":"2026-06-12T01:09:20.404549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXDUE3AZNX3XDAF2MBFNMF4EU7","json":"https://pith.science/pith/EXDUE3AZNX3XDAF2MBFNMF4EU7.json","graph_json":"https://pith.science/api/pith-number/EXDUE3AZNX3XDAF2MBFNMF4EU7/graph.json","events_json":"https://pith.science/api/pith-number/EXDUE3AZNX3XDAF2MBFNMF4EU7/events.json","paper":"https://pith.science/paper/EXDUE3AZ"},"agent_actions":{"view_html":"https://pith.science/pith/EXDUE3AZNX3XDAF2MBFNMF4EU7","download_json":"https://pith.science/pith/EXDUE3AZNX3XDAF2MBFNMF4EU7.json","view_paper":"https://pith.science/paper/EXDUE3AZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.13591&json=true","fetch_graph":"https://pith.science/api/pith-number/EXDUE3AZNX3XDAF2MBFNMF4EU7/graph.json","fetch_events":"https://pith.science/api/pith-number/EXDUE3AZNX3XDAF2MBFNMF4EU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXDUE3AZNX3XDAF2MBFNMF4EU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXDUE3AZNX3XDAF2MBFNMF4EU7/action/storage_attestation","attest_author":"https://pith.science/pith/EXDUE3AZNX3XDAF2MBFNMF4EU7/action/author_attestation","sign_citation":"https://pith.science/pith/EXDUE3AZNX3XDAF2MBFNMF4EU7/action/citation_signature","submit_replication":"https://pith.science/pith/EXDUE3AZNX3XDAF2MBFNMF4EU7/action/replication_record"}},"created_at":"2026-06-12T01:09:20.404549+00:00","updated_at":"2026-06-12T01:09:20.404549+00:00"}