{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X57QK7SYSPQ7KFK2ICD3MBE4SB","short_pith_number":"pith:X57QK7SY","schema_version":"1.0","canonical_sha256":"bf7f057e5893e1f5155a4087b6049c90587fa5756003ae1587222c3f7631b7f7","source":{"kind":"arxiv","id":"2407.00981","version":2},"attestation_state":"computed","paper":{"title":"VisEval: A Benchmark for Data Visualization in the Era of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.HC","authors_text":"Jiahang Xu, Kan Ren, Nan Chen, Yuge Zhang, Yuqing Yang","submitted_at":"2024-07-01T05:35:30Z","abstract_excerpt":"Translating natural language to visualization (NL2VIS) has shown great promise for visual data analysis, but it remains a challenging task that requires multiple low-level implementations, such as natural language processing and visualization design. Recent advancements in pre-trained large language models (LLMs) are opening new avenues for generating visualizations from natural language. However, the lack of a comprehensive and reliable benchmark hinders our understanding of LLMs' capabilities in visualization generation. In this paper, we address this gap by proposing a new NL2VIS benchmark "},"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":"2407.00981","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-07-01T05:35:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6e1b53366bfddcc905895202e4dc981f138d12f4ce102fb6661ae943ccd85417","abstract_canon_sha256":"d879df102b182e6c3fc2880b341bf704cf61fb859065f71114eb501a2b46ace6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:55.213701Z","signature_b64":"lqUVeU/zxbF8an73TxFAveU5iVjOrPFfJXChIq31SGqMGphU+CdC+GeLIpeDpnjVz046XPHF9CZpkSTiG66KBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf7f057e5893e1f5155a4087b6049c90587fa5756003ae1587222c3f7631b7f7","last_reissued_at":"2026-07-05T08:52:55.213282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:55.213282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisEval: A Benchmark for Data Visualization in the Era of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.HC","authors_text":"Jiahang Xu, Kan Ren, Nan Chen, Yuge Zhang, Yuqing Yang","submitted_at":"2024-07-01T05:35:30Z","abstract_excerpt":"Translating natural language to visualization (NL2VIS) has shown great promise for visual data analysis, but it remains a challenging task that requires multiple low-level implementations, such as natural language processing and visualization design. Recent advancements in pre-trained large language models (LLMs) are opening new avenues for generating visualizations from natural language. However, the lack of a comprehensive and reliable benchmark hinders our understanding of LLMs' capabilities in visualization generation. In this paper, we address this gap by proposing a new NL2VIS benchmark "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00981","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/2407.00981/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":"2407.00981","created_at":"2026-07-05T08:52:55.213338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00981v2","created_at":"2026-07-05T08:52:55.213338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00981","created_at":"2026-07-05T08:52:55.213338+00:00"},{"alias_kind":"pith_short_12","alias_value":"X57QK7SYSPQ7","created_at":"2026-07-05T08:52:55.213338+00:00"},{"alias_kind":"pith_short_16","alias_value":"X57QK7SYSPQ7KFK2","created_at":"2026-07-05T08:52:55.213338+00:00"},{"alias_kind":"pith_short_8","alias_value":"X57QK7SY","created_at":"2026-07-05T08:52:55.213338+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/X57QK7SYSPQ7KFK2ICD3MBE4SB","json":"https://pith.science/pith/X57QK7SYSPQ7KFK2ICD3MBE4SB.json","graph_json":"https://pith.science/api/pith-number/X57QK7SYSPQ7KFK2ICD3MBE4SB/graph.json","events_json":"https://pith.science/api/pith-number/X57QK7SYSPQ7KFK2ICD3MBE4SB/events.json","paper":"https://pith.science/paper/X57QK7SY"},"agent_actions":{"view_html":"https://pith.science/pith/X57QK7SYSPQ7KFK2ICD3MBE4SB","download_json":"https://pith.science/pith/X57QK7SYSPQ7KFK2ICD3MBE4SB.json","view_paper":"https://pith.science/paper/X57QK7SY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00981&json=true","fetch_graph":"https://pith.science/api/pith-number/X57QK7SYSPQ7KFK2ICD3MBE4SB/graph.json","fetch_events":"https://pith.science/api/pith-number/X57QK7SYSPQ7KFK2ICD3MBE4SB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X57QK7SYSPQ7KFK2ICD3MBE4SB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X57QK7SYSPQ7KFK2ICD3MBE4SB/action/storage_attestation","attest_author":"https://pith.science/pith/X57QK7SYSPQ7KFK2ICD3MBE4SB/action/author_attestation","sign_citation":"https://pith.science/pith/X57QK7SYSPQ7KFK2ICD3MBE4SB/action/citation_signature","submit_replication":"https://pith.science/pith/X57QK7SYSPQ7KFK2ICD3MBE4SB/action/replication_record"}},"created_at":"2026-07-05T08:52:55.213338+00:00","updated_at":"2026-07-05T08:52:55.213338+00:00"}