{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V2YHWSBQNRC6JRHZXLQGR6SVGM","short_pith_number":"pith:V2YHWSBQ","schema_version":"1.0","canonical_sha256":"aeb07b48306c45e4c4f9bae068fa553330920fa9f407da98e2a2e72812d333cf","source":{"kind":"arxiv","id":"2603.29139","version":2},"attestation_state":"computed","paper":{"title":"SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.HC"],"primary_cat":"cs.AI","authors_text":"Bei Wang, Chaoli Wang, David Lenz, Guoxi Liu, Haichao Miao, Hanqi Guo, Helgi I. Ingolfsson, Hongfeng Yu, Jianxin Sun, Kaiyuan Tang, Kuangshi Ai, Michael Molash, Nathaniel Gorski, Shusen Liu, Teja Leburu, Tom Peterka","submitted_at":"2026-03-31T01:41:28Z","abstract_excerpt":"Recent advances in large language models (LLMs) have enabled agentic systems to translate natural-language intent into executable scientific visualization (SciVis) tasks. Despite rapid progress, the community lacks a principled and reproducible benchmark for evaluating these emerging SciVis agents in realistic, multi-step analysis settings. We present SciVisAgentBench, a comprehensive and extensible benchmark for evaluating scientific data analysis and visualization agents. Our benchmark is grounded in a structured taxonomy spanning four dimensions: application domain, data type, complexity le"},"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":"2603.29139","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-31T01:41:28Z","cross_cats_sorted":["cs.GR","cs.HC"],"title_canon_sha256":"0b6a8860e1fb4365c1988d98d1d505b205b7132c773290634190868fd485cd16","abstract_canon_sha256":"f22aeb20e02fa06f303449c0f894d458df069f119e33b5783f47451fa3645dc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:09.632008Z","signature_b64":"OUZAvToXCxL/WkA5BR7KGh6okDgwXPRiRIiXLNFNZtbu4RhBE/tNZAjAbf4eUSBvvgi3n0rcEVTBMkwvBMq7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aeb07b48306c45e4c4f9bae068fa553330920fa9f407da98e2a2e72812d333cf","last_reissued_at":"2026-06-30T00:15:09.631586Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:09.631586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.HC"],"primary_cat":"cs.AI","authors_text":"Bei Wang, Chaoli Wang, David Lenz, Guoxi Liu, Haichao Miao, Hanqi Guo, Helgi I. Ingolfsson, Hongfeng Yu, Jianxin Sun, Kaiyuan Tang, Kuangshi Ai, Michael Molash, Nathaniel Gorski, Shusen Liu, Teja Leburu, Tom Peterka","submitted_at":"2026-03-31T01:41:28Z","abstract_excerpt":"Recent advances in large language models (LLMs) have enabled agentic systems to translate natural-language intent into executable scientific visualization (SciVis) tasks. Despite rapid progress, the community lacks a principled and reproducible benchmark for evaluating these emerging SciVis agents in realistic, multi-step analysis settings. We present SciVisAgentBench, a comprehensive and extensible benchmark for evaluating scientific data analysis and visualization agents. Our benchmark is grounded in a structured taxonomy spanning four dimensions: application domain, data type, complexity le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.29139","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/2603.29139/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":"2603.29139","created_at":"2026-06-30T00:15:09.631648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.29139v2","created_at":"2026-06-30T00:15:09.631648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29139","created_at":"2026-06-30T00:15:09.631648+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2YHWSBQNRC6","created_at":"2026-06-30T00:15:09.631648+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2YHWSBQNRC6JRHZ","created_at":"2026-06-30T00:15:09.631648+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2YHWSBQ","created_at":"2026-06-30T00:15:09.631648+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.21825","citing_title":"Toward AI VIS Co-Scientists: A General and End-to-End Agent Harness for Solving Complex Data Visualization Tasks","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13911","citing_title":"Rongzai agent: A Large Language Model-Based Autonomous Assistant for Rietveld Refinement of Neutron Diffraction Data","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27996","citing_title":"Exploring LLM Agent Designs and Interaction Modalities for Scientific Visualization","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27996","citing_title":"Exploring LLM Agent Designs and Interaction Modalities for Scientific Visualization","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V2YHWSBQNRC6JRHZXLQGR6SVGM","json":"https://pith.science/pith/V2YHWSBQNRC6JRHZXLQGR6SVGM.json","graph_json":"https://pith.science/api/pith-number/V2YHWSBQNRC6JRHZXLQGR6SVGM/graph.json","events_json":"https://pith.science/api/pith-number/V2YHWSBQNRC6JRHZXLQGR6SVGM/events.json","paper":"https://pith.science/paper/V2YHWSBQ"},"agent_actions":{"view_html":"https://pith.science/pith/V2YHWSBQNRC6JRHZXLQGR6SVGM","download_json":"https://pith.science/pith/V2YHWSBQNRC6JRHZXLQGR6SVGM.json","view_paper":"https://pith.science/paper/V2YHWSBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.29139&json=true","fetch_graph":"https://pith.science/api/pith-number/V2YHWSBQNRC6JRHZXLQGR6SVGM/graph.json","fetch_events":"https://pith.science/api/pith-number/V2YHWSBQNRC6JRHZXLQGR6SVGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2YHWSBQNRC6JRHZXLQGR6SVGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2YHWSBQNRC6JRHZXLQGR6SVGM/action/storage_attestation","attest_author":"https://pith.science/pith/V2YHWSBQNRC6JRHZXLQGR6SVGM/action/author_attestation","sign_citation":"https://pith.science/pith/V2YHWSBQNRC6JRHZXLQGR6SVGM/action/citation_signature","submit_replication":"https://pith.science/pith/V2YHWSBQNRC6JRHZXLQGR6SVGM/action/replication_record"}},"created_at":"2026-06-30T00:15:09.631648+00:00","updated_at":"2026-06-30T00:15:09.631648+00:00"}