{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R5257NC7WQ4QYBLXAVKFF3J3YW","short_pith_number":"pith:R5257NC7","schema_version":"1.0","canonical_sha256":"8f75dfb45fb4390c0577055452ed3bc5a9ec682b8b4363c692f663c6e3edf46c","source":{"kind":"arxiv","id":"2607.01647","version":1},"attestation_state":"computed","paper":{"title":"AgenticDataBench: A Comprehensive Benchmark for Data Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Baolin Sun, Chengyuan Yang, Daizhou Wen, Guoliang Li, Huaiyu Ruan, Jiaxing Han, Peng Zhang, Shan Zhong, Tao Fang, Xiang Qi, Ying Yan, Yu Su, Zhaoyan Sun","submitted_at":"2026-07-02T03:18:59Z","abstract_excerpt":"Data science aims to derive actionable insights from heterogeneous raw data, unlocking the value of the massive amounts of data generated in modern society. Automating this process is essential to reducing labor-intensive efforts for data scientists and enabling scalable data-driven applications. Recently, large language model (LLM)-based data agents have emerged as a promising solution to automate data science workflows. However, the field lacks comprehensive benchmarks to rigorously evaluate these agents across diverse scenarios with fine-grained granularity. To address this gap, we propose "},"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":"2607.01647","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-07-02T03:18:59Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"69001ebc69fede2eaa5894a5587b7619255d40197c0c40e806125ba0fb7fb27e","abstract_canon_sha256":"6c9720ccbc124481f429124ececd0040fadae1c6b95da0b1c179943c92ca9515"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:04.441726Z","signature_b64":"+jky460jyTyfNr64MNefEtkoX2Qlq4L5lXz8WWnBhJdalhiBCCwGIPcwsAufcWIHdvm6umB5gfB91ZzcFqMOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f75dfb45fb4390c0577055452ed3bc5a9ec682b8b4363c692f663c6e3edf46c","last_reissued_at":"2026-07-03T01:17:04.441324Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:04.441324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgenticDataBench: A Comprehensive Benchmark for Data Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Baolin Sun, Chengyuan Yang, Daizhou Wen, Guoliang Li, Huaiyu Ruan, Jiaxing Han, Peng Zhang, Shan Zhong, Tao Fang, Xiang Qi, Ying Yan, Yu Su, Zhaoyan Sun","submitted_at":"2026-07-02T03:18:59Z","abstract_excerpt":"Data science aims to derive actionable insights from heterogeneous raw data, unlocking the value of the massive amounts of data generated in modern society. Automating this process is essential to reducing labor-intensive efforts for data scientists and enabling scalable data-driven applications. Recently, large language model (LLM)-based data agents have emerged as a promising solution to automate data science workflows. However, the field lacks comprehensive benchmarks to rigorously evaluate these agents across diverse scenarios with fine-grained granularity. To address this gap, we propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01647","kind":"arxiv","version":1},"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/2607.01647/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":"2607.01647","created_at":"2026-07-03T01:17:04.441390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01647v1","created_at":"2026-07-03T01:17:04.441390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01647","created_at":"2026-07-03T01:17:04.441390+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5257NC7WQ4Q","created_at":"2026-07-03T01:17:04.441390+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5257NC7WQ4QYBLX","created_at":"2026-07-03T01:17:04.441390+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5257NC7","created_at":"2026-07-03T01:17:04.441390+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/R5257NC7WQ4QYBLXAVKFF3J3YW","json":"https://pith.science/pith/R5257NC7WQ4QYBLXAVKFF3J3YW.json","graph_json":"https://pith.science/api/pith-number/R5257NC7WQ4QYBLXAVKFF3J3YW/graph.json","events_json":"https://pith.science/api/pith-number/R5257NC7WQ4QYBLXAVKFF3J3YW/events.json","paper":"https://pith.science/paper/R5257NC7"},"agent_actions":{"view_html":"https://pith.science/pith/R5257NC7WQ4QYBLXAVKFF3J3YW","download_json":"https://pith.science/pith/R5257NC7WQ4QYBLXAVKFF3J3YW.json","view_paper":"https://pith.science/paper/R5257NC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01647&json=true","fetch_graph":"https://pith.science/api/pith-number/R5257NC7WQ4QYBLXAVKFF3J3YW/graph.json","fetch_events":"https://pith.science/api/pith-number/R5257NC7WQ4QYBLXAVKFF3J3YW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5257NC7WQ4QYBLXAVKFF3J3YW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5257NC7WQ4QYBLXAVKFF3J3YW/action/storage_attestation","attest_author":"https://pith.science/pith/R5257NC7WQ4QYBLXAVKFF3J3YW/action/author_attestation","sign_citation":"https://pith.science/pith/R5257NC7WQ4QYBLXAVKFF3J3YW/action/citation_signature","submit_replication":"https://pith.science/pith/R5257NC7WQ4QYBLXAVKFF3J3YW/action/replication_record"}},"created_at":"2026-07-03T01:17:04.441390+00:00","updated_at":"2026-07-03T01:17:04.441390+00:00"}