{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GHUAI744USNAIIE5IS3ZTI5IWS","short_pith_number":"pith:GHUAI744","schema_version":"1.0","canonical_sha256":"31e8047f9ca49a04209d44b799a3a8b48ea34fad4736b6ebb9aac9d186ded778","source":{"kind":"arxiv","id":"2402.18679","version":4},"attestation_state":"computed","paper":{"title":"Data Interpreter: An LLM Agent For Data Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bangbang Liu, Bang Liu, Binhao Wu, Ceyao Zhang, Chenglin Wu, Chenxing Wei, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Lingyao Zhang, Li Zhang, Mingchen Zhuge, Min Yang, Sirui Hong, Taicheng Guo, Tuo Zhou, Wei Tao, Xiangru Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yizhang Lin, Yuheng Cheng, Zhibin Gou, Zongze Xu","submitted_at":"2024-02-28T19:49:55Z","abstract_excerpt":"Large Language Model (LLM)-based agents have shown effectiveness across many applications. However, their use in data science scenarios requiring solving long-term interconnected tasks, dynamic data adjustments and domain expertise remains challenging. Previous approaches primarily focus on individual tasks, making it difficult to assess the complete data science workflow. Moreover, they struggle to handle real-time changes in intermediate data and fail to adapt dynamically to evolving task dependencies inherent to data science problems. In this paper, we present Data Interpreter, an LLM-based"},"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":"2402.18679","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-28T19:49:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ddf726c4ec1e8feb99199f2dc2b7f92644d075d82bdecaa4d93d1a5f5d16cecb","abstract_canon_sha256":"abcc7e7331df8c4c4054cd1168f277f40f519620081a0d8b4ba2c02615bcacca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:40.820124Z","signature_b64":"/tlDpOQJUdui+8U3SBH+UMfEvNSmadPu1SdTn3byTd2SwuMOUzjBTTE1+dwyGGGNTjczUidOGYUL1VV3MSERBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31e8047f9ca49a04209d44b799a3a8b48ea34fad4736b6ebb9aac9d186ded778","last_reissued_at":"2026-07-05T09:20:40.819646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:40.819646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Interpreter: An LLM Agent For Data Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bangbang Liu, Bang Liu, Binhao Wu, Ceyao Zhang, Chenglin Wu, Chenxing Wei, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Lingyao Zhang, Li Zhang, Mingchen Zhuge, Min Yang, Sirui Hong, Taicheng Guo, Tuo Zhou, Wei Tao, Xiangru Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yizhang Lin, Yuheng Cheng, Zhibin Gou, Zongze Xu","submitted_at":"2024-02-28T19:49:55Z","abstract_excerpt":"Large Language Model (LLM)-based agents have shown effectiveness across many applications. However, their use in data science scenarios requiring solving long-term interconnected tasks, dynamic data adjustments and domain expertise remains challenging. Previous approaches primarily focus on individual tasks, making it difficult to assess the complete data science workflow. Moreover, they struggle to handle real-time changes in intermediate data and fail to adapt dynamically to evolving task dependencies inherent to data science problems. In this paper, we present Data Interpreter, an LLM-based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18679","kind":"arxiv","version":4},"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/2402.18679/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":"2402.18679","created_at":"2026-07-05T09:20:40.819707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18679v4","created_at":"2026-07-05T09:20:40.819707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18679","created_at":"2026-07-05T09:20:40.819707+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHUAI744USNA","created_at":"2026-07-05T09:20:40.819707+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHUAI744USNAIIE5","created_at":"2026-07-05T09:20:40.819707+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHUAI744","created_at":"2026-07-05T09:20:40.819707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25207","citing_title":"ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26627","citing_title":"Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17915","citing_title":"Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17628","citing_title":"OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation","ref_index":187,"is_internal_anchor":false},{"citing_arxiv_id":"2606.16000","citing_title":"GRACE-DS: a Guarded Reward-guided Agent Correction Environment in Data Science","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05250","citing_title":"Towards Persistent Case-Based Memory for Autonomous Data Science: A CBR-Augmented R&D-Agent with a Locally Deployable Small Language Model","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12376","citing_title":"ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28896","citing_title":"A Task-Driven and Quality-Assured Agent Framework for SAR Data Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":175,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12376","citing_title":"ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10362","citing_title":"CellDX AI Autopilot: Agent-Guided Training and Deployment of Pathology Classifiers","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14655","citing_title":"AgentGA: Evolving Code Solutions in Agent-Seed Space","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08491","citing_title":"Figures as Interfaces: Toward LLM-Native Artifacts for Scientific Discovery","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2308.00352","citing_title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14655","citing_title":"AgentGA: Evolving Code Solutions in Agent-Seed Space","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS","json":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS.json","graph_json":"https://pith.science/api/pith-number/GHUAI744USNAIIE5IS3ZTI5IWS/graph.json","events_json":"https://pith.science/api/pith-number/GHUAI744USNAIIE5IS3ZTI5IWS/events.json","paper":"https://pith.science/paper/GHUAI744"},"agent_actions":{"view_html":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS","download_json":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS.json","view_paper":"https://pith.science/paper/GHUAI744","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18679&json=true","fetch_graph":"https://pith.science/api/pith-number/GHUAI744USNAIIE5IS3ZTI5IWS/graph.json","fetch_events":"https://pith.science/api/pith-number/GHUAI744USNAIIE5IS3ZTI5IWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS/action/storage_attestation","attest_author":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS/action/author_attestation","sign_citation":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS/action/citation_signature","submit_replication":"https://pith.science/pith/GHUAI744USNAIIE5IS3ZTI5IWS/action/replication_record"}},"created_at":"2026-07-05T09:20:40.819707+00:00","updated_at":"2026-07-05T09:20:40.819707+00:00"}