{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V2YHWSBQNRC6JRHZXLQGR6SVGM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f22aeb20e02fa06f303449c0f894d458df069f119e33b5783f47451fa3645dc6","cross_cats_sorted":["cs.GR","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-31T01:41:28Z","title_canon_sha256":"0b6a8860e1fb4365c1988d98d1d505b205b7132c773290634190868fd485cd16"},"schema_version":"1.0","source":{"id":"2603.29139","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.29139","created_at":"2026-06-30T00:15:09Z"},{"alias_kind":"arxiv_version","alias_value":"2603.29139v2","created_at":"2026-06-30T00:15:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29139","created_at":"2026-06-30T00:15:09Z"},{"alias_kind":"pith_short_12","alias_value":"V2YHWSBQNRC6","created_at":"2026-06-30T00:15:09Z"},{"alias_kind":"pith_short_16","alias_value":"V2YHWSBQNRC6JRHZ","created_at":"2026-06-30T00:15:09Z"},{"alias_kind":"pith_short_8","alias_value":"V2YHWSBQ","created_at":"2026-06-30T00:15:09Z"}],"graph_snapshots":[{"event_id":"sha256:16ad5d26eb80424a854a1469b6e5e50cbf53f9bf9aba824127667cbc28b09934","target":"graph","created_at":"2026-06-30T00:15:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.29139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.GR","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-31T01:41:28Z","title":"SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.29139","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:68a4a62f8017531c3053bc06b5d0d0160d4e45b8d766edd124092ffa74b56de5","target":"record","created_at":"2026-06-30T00:15:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f22aeb20e02fa06f303449c0f894d458df069f119e33b5783f47451fa3645dc6","cross_cats_sorted":["cs.GR","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-31T01:41:28Z","title_canon_sha256":"0b6a8860e1fb4365c1988d98d1d505b205b7132c773290634190868fd485cd16"},"schema_version":"1.0","source":{"id":"2603.29139","kind":"arxiv","version":2}},"canonical_sha256":"aeb07b48306c45e4c4f9bae068fa553330920fa9f407da98e2a2e72812d333cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aeb07b48306c45e4c4f9bae068fa553330920fa9f407da98e2a2e72812d333cf","first_computed_at":"2026-06-30T00:15:09.631586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T00:15:09.631586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OUZAvToXCxL/WkA5BR7KGh6okDgwXPRiRIiXLNFNZtbu4RhBE/tNZAjAbf4eUSBvvgi3n0rcEVTBMkwvBMq7AA==","signature_status":"signed_v1","signed_at":"2026-06-30T00:15:09.632008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.29139","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68a4a62f8017531c3053bc06b5d0d0160d4e45b8d766edd124092ffa74b56de5","sha256:16ad5d26eb80424a854a1469b6e5e50cbf53f9bf9aba824127667cbc28b09934"],"state_sha256":"21d57ee32116d34682fd37559d174bfdace5da54a49b66014d89f3e37672a4f1"}