{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SCQEXMK6KMAV44LKA6AR6Y2JVC","short_pith_number":"pith:SCQEXMK6","schema_version":"1.0","canonical_sha256":"90a04bb15e53015e716a07811f6349a8882ea4667b16879155a99ae23bccb910","source":{"kind":"arxiv","id":"2503.16632","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Visual Language Models on Standardized Visualization Literacy Tests","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Alvitta Ottley, Saugat Pandey","submitted_at":"2025-03-20T18:36:02Z","abstract_excerpt":"The increasing integration of Visual Language Models (VLMs) into visualization systems demands a comprehensive understanding of their visual interpretation capabilities and constraints. While existing research has examined individual models, systematic comparisons of VLMs' visualization literacy remain unexplored. We bridge this gap through a rigorous, first-of-its-kind evaluation of four leading VLMs (GPT-4, Claude, Gemini, and Llama) using standardized assessments: the Visualization Literacy Assessment Test (VLAT) and Critical Thinking Assessment for Literacy in Visualizations (CALVI). Our m"},"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":"2503.16632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-20T18:36:02Z","cross_cats_sorted":[],"title_canon_sha256":"990aa17ded4d1e84af0c48957e2efaf3a33aca592e4f3913259744b120c26287","abstract_canon_sha256":"a5fce38f6b1033063e53ce90eefb388d15822c0abe0028f0672043c3414a1c07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:46.091182Z","signature_b64":"psjj/s/xrnkyceKuqD+2jkGnEvnzlclqCqtT+WlQ2tueYbziwnvoMHmJPbowA2gUWX9F1dXEl9Da2u/i4soBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90a04bb15e53015e716a07811f6349a8882ea4667b16879155a99ae23bccb910","last_reissued_at":"2026-07-05T10:36:46.090704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:46.090704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Visual Language Models on Standardized Visualization Literacy Tests","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Alvitta Ottley, Saugat Pandey","submitted_at":"2025-03-20T18:36:02Z","abstract_excerpt":"The increasing integration of Visual Language Models (VLMs) into visualization systems demands a comprehensive understanding of their visual interpretation capabilities and constraints. While existing research has examined individual models, systematic comparisons of VLMs' visualization literacy remain unexplored. We bridge this gap through a rigorous, first-of-its-kind evaluation of four leading VLMs (GPT-4, Claude, Gemini, and Llama) using standardized assessments: the Visualization Literacy Assessment Test (VLAT) and Critical Thinking Assessment for Literacy in Visualizations (CALVI). Our m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16632","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/2503.16632/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":"2503.16632","created_at":"2026-07-05T10:36:46.090761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16632v1","created_at":"2026-07-05T10:36:46.090761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16632","created_at":"2026-07-05T10:36:46.090761+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCQEXMK6KMAV","created_at":"2026-07-05T10:36:46.090761+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCQEXMK6KMAV44LK","created_at":"2026-07-05T10:36:46.090761+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCQEXMK6","created_at":"2026-07-05T10:36:46.090761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03142","citing_title":"Disentangling Visual and Factual Correctness in LVLMs' Visualization Literacy","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SCQEXMK6KMAV44LKA6AR6Y2JVC","json":"https://pith.science/pith/SCQEXMK6KMAV44LKA6AR6Y2JVC.json","graph_json":"https://pith.science/api/pith-number/SCQEXMK6KMAV44LKA6AR6Y2JVC/graph.json","events_json":"https://pith.science/api/pith-number/SCQEXMK6KMAV44LKA6AR6Y2JVC/events.json","paper":"https://pith.science/paper/SCQEXMK6"},"agent_actions":{"view_html":"https://pith.science/pith/SCQEXMK6KMAV44LKA6AR6Y2JVC","download_json":"https://pith.science/pith/SCQEXMK6KMAV44LKA6AR6Y2JVC.json","view_paper":"https://pith.science/paper/SCQEXMK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16632&json=true","fetch_graph":"https://pith.science/api/pith-number/SCQEXMK6KMAV44LKA6AR6Y2JVC/graph.json","fetch_events":"https://pith.science/api/pith-number/SCQEXMK6KMAV44LKA6AR6Y2JVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCQEXMK6KMAV44LKA6AR6Y2JVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCQEXMK6KMAV44LKA6AR6Y2JVC/action/storage_attestation","attest_author":"https://pith.science/pith/SCQEXMK6KMAV44LKA6AR6Y2JVC/action/author_attestation","sign_citation":"https://pith.science/pith/SCQEXMK6KMAV44LKA6AR6Y2JVC/action/citation_signature","submit_replication":"https://pith.science/pith/SCQEXMK6KMAV44LKA6AR6Y2JVC/action/replication_record"}},"created_at":"2026-07-05T10:36:46.090761+00:00","updated_at":"2026-07-05T10:36:46.090761+00:00"}