{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FZ6GZLVQVNFF3ICMOXM3XVPDTZ","short_pith_number":"pith:FZ6GZLVQ","schema_version":"1.0","canonical_sha256":"2e7c6caeb0ab4a5da04c75d9bbd5e39e5c2ac6719ca84c603e308e23dc738790","source":{"kind":"arxiv","id":"2407.10956","version":1},"attestation_state":"computed","paper":{"title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ansong Ni, Caiming Xiong, Danyang Zhang, Fangyu Lei, Hanchong Zhang, Haoyuan Wu, Hongcheng Gao, Hongshen Xu, Jixuan Chen, Kai Yu, Lu Chen, Pengcheng Yin, Qian Liu, Ruisheng Cao, Ruoxi Sun, Sida Wang, Tao Yu, Tianbao Xie, Victor Zhong, Wenjing Hu, Xinzhuang Xiong, Yeqiao Fu, Yuchen Mao","submitted_at":"2024-07-15T17:54:37Z","abstract_excerpt":"Data science and engineering workflows often span multiple stages, from warehousing to orchestration, using tools like BigQuery, dbt, and Airbyte. As vision language models (VLMs) advance in multimodal understanding and code generation, VLM-based agents could potentially automate these workflows by generating SQL queries, Python code, and GUI operations. This automation can improve the productivity of experts while democratizing access to large-scale data analysis. In this paper, we introduce Spider2-V, the first multimodal agent benchmark focusing on professional data science and engineering "},"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":"2407.10956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-15T17:54:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6cb43df52e695afa63f3158d93d0bf0d7a8404a55d93e4d268c00ec107b34760","abstract_canon_sha256":"7420724f0af8cdc88b274e77b9620648dbeaa0e0cee5c13e8d934fdcb2ad5c58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:06.928351Z","signature_b64":"hEUvHNYvoODWzF9i94CHaOFfFC5K9Jmiyu8OTQYHgfHa3mQudlvj2ANXNRCRdeewXjsHnLZ7OwWwmCE15ZNeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e7c6caeb0ab4a5da04c75d9bbd5e39e5c2ac6719ca84c603e308e23dc738790","last_reissued_at":"2026-07-05T08:44:06.927915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:06.927915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ansong Ni, Caiming Xiong, Danyang Zhang, Fangyu Lei, Hanchong Zhang, Haoyuan Wu, Hongcheng Gao, Hongshen Xu, Jixuan Chen, Kai Yu, Lu Chen, Pengcheng Yin, Qian Liu, Ruisheng Cao, Ruoxi Sun, Sida Wang, Tao Yu, Tianbao Xie, Victor Zhong, Wenjing Hu, Xinzhuang Xiong, Yeqiao Fu, Yuchen Mao","submitted_at":"2024-07-15T17:54:37Z","abstract_excerpt":"Data science and engineering workflows often span multiple stages, from warehousing to orchestration, using tools like BigQuery, dbt, and Airbyte. As vision language models (VLMs) advance in multimodal understanding and code generation, VLM-based agents could potentially automate these workflows by generating SQL queries, Python code, and GUI operations. This automation can improve the productivity of experts while democratizing access to large-scale data analysis. In this paper, we introduce Spider2-V, the first multimodal agent benchmark focusing on professional data science and engineering "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10956","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/2407.10956/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":"2407.10956","created_at":"2026-07-05T08:44:06.927974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10956v1","created_at":"2026-07-05T08:44:06.927974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10956","created_at":"2026-07-05T08:44:06.927974+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZ6GZLVQVNFF","created_at":"2026-07-05T08:44:06.927974+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZ6GZLVQVNFF3ICM","created_at":"2026-07-05T08:44:06.927974+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZ6GZLVQ","created_at":"2026-07-05T08:44:06.927974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21654","citing_title":"ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00051","citing_title":"Business Utility of Large Language Models as Exploratory Data Analysis Agents","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04454","citing_title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04065","citing_title":"Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21375","citing_title":"VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ","json":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ.json","graph_json":"https://pith.science/api/pith-number/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/graph.json","events_json":"https://pith.science/api/pith-number/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/events.json","paper":"https://pith.science/paper/FZ6GZLVQ"},"agent_actions":{"view_html":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ","download_json":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ.json","view_paper":"https://pith.science/paper/FZ6GZLVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10956&json=true","fetch_graph":"https://pith.science/api/pith-number/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/action/storage_attestation","attest_author":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/action/author_attestation","sign_citation":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/action/citation_signature","submit_replication":"https://pith.science/pith/FZ6GZLVQVNFF3ICMOXM3XVPDTZ/action/replication_record"}},"created_at":"2026-07-05T08:44:06.927974+00:00","updated_at":"2026-07-05T08:44:06.927974+00:00"}