{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XJ3FGVL34WI42ZXA4W2BBB6QRF","short_pith_number":"pith:XJ3FGVL3","schema_version":"1.0","canonical_sha256":"ba7653557be591cd66e0e5b41087d08971c32a24385e56ef95cde9edbb8e542b","source":{"kind":"arxiv","id":"2411.00257","version":1},"attestation_state":"computed","paper":{"title":"Understanding Graphical Perception in Data Visualization through Zero-shot Prompting of Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Grace Guo, Hanspeter Pfister, Jenna Jiayi Kang, Raj Sanjay Shah, Sashank Varma","submitted_at":"2024-10-31T23:24:46Z","abstract_excerpt":"Vision Language Models (VLMs) have been successful at many chart comprehension tasks that require attending to both the images of charts and their accompanying textual descriptions. However, it is not well established how VLM performance profiles map to human-like behaviors. If VLMs can be shown to have human-like chart comprehension abilities, they can then be applied to a broader range of tasks, such as designing and evaluating visualizations for human readers. This paper lays the foundations for such applications by evaluating the accuracy of zero-shot prompting of VLMs on graphical percept"},"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":"2411.00257","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-31T23:24:46Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5498a71b0f35b2732a2ebc2fb9bcb7a5c4b06ef299f18c43a36c04a3e7b39619","abstract_canon_sha256":"16584ac9fd4259ad68f6310ce78e7ef70f4ee13c4dcaa5007ba4961844855232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:39.797491Z","signature_b64":"cX2HIVhMZ5FfujWfpz1IyC0D+SzB6HlNC2NCCwr7C5Xpgz8SbZ8pzg6A5Ch3A2W5WQbfMbUlbng3BlAkNIz7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba7653557be591cd66e0e5b41087d08971c32a24385e56ef95cde9edbb8e542b","last_reissued_at":"2026-07-05T09:29:39.796940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:39.796940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Graphical Perception in Data Visualization through Zero-shot Prompting of Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Grace Guo, Hanspeter Pfister, Jenna Jiayi Kang, Raj Sanjay Shah, Sashank Varma","submitted_at":"2024-10-31T23:24:46Z","abstract_excerpt":"Vision Language Models (VLMs) have been successful at many chart comprehension tasks that require attending to both the images of charts and their accompanying textual descriptions. However, it is not well established how VLM performance profiles map to human-like behaviors. If VLMs can be shown to have human-like chart comprehension abilities, they can then be applied to a broader range of tasks, such as designing and evaluating visualizations for human readers. This paper lays the foundations for such applications by evaluating the accuracy of zero-shot prompting of VLMs on graphical percept"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00257","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/2411.00257/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":"2411.00257","created_at":"2026-07-05T09:29:39.796989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00257v1","created_at":"2026-07-05T09:29:39.796989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00257","created_at":"2026-07-05T09:29:39.796989+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJ3FGVL34WI4","created_at":"2026-07-05T09:29:39.796989+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJ3FGVL34WI42ZXA","created_at":"2026-07-05T09:29:39.796989+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJ3FGVL3","created_at":"2026-07-05T09:29:39.796989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16466","citing_title":"SceneLoom: Communicating Data with Scene Context","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJ3FGVL34WI42ZXA4W2BBB6QRF","json":"https://pith.science/pith/XJ3FGVL34WI42ZXA4W2BBB6QRF.json","graph_json":"https://pith.science/api/pith-number/XJ3FGVL34WI42ZXA4W2BBB6QRF/graph.json","events_json":"https://pith.science/api/pith-number/XJ3FGVL34WI42ZXA4W2BBB6QRF/events.json","paper":"https://pith.science/paper/XJ3FGVL3"},"agent_actions":{"view_html":"https://pith.science/pith/XJ3FGVL34WI42ZXA4W2BBB6QRF","download_json":"https://pith.science/pith/XJ3FGVL34WI42ZXA4W2BBB6QRF.json","view_paper":"https://pith.science/paper/XJ3FGVL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00257&json=true","fetch_graph":"https://pith.science/api/pith-number/XJ3FGVL34WI42ZXA4W2BBB6QRF/graph.json","fetch_events":"https://pith.science/api/pith-number/XJ3FGVL34WI42ZXA4W2BBB6QRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJ3FGVL34WI42ZXA4W2BBB6QRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJ3FGVL34WI42ZXA4W2BBB6QRF/action/storage_attestation","attest_author":"https://pith.science/pith/XJ3FGVL34WI42ZXA4W2BBB6QRF/action/author_attestation","sign_citation":"https://pith.science/pith/XJ3FGVL34WI42ZXA4W2BBB6QRF/action/citation_signature","submit_replication":"https://pith.science/pith/XJ3FGVL34WI42ZXA4W2BBB6QRF/action/replication_record"}},"created_at":"2026-07-05T09:29:39.796989+00:00","updated_at":"2026-07-05T09:29:39.796989+00:00"}