{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F75FGJOSXC2WJPDGYFEYZY7KUD","short_pith_number":"pith:F75FGJOS","schema_version":"1.0","canonical_sha256":"2ffa5325d2b8b564bc66c1498ce3eaa0dca090341679a39301ff998bc2a4dc6b","source":{"kind":"arxiv","id":"2410.04280","version":1},"attestation_state":"computed","paper":{"title":"The Visualization JUDGE : Can Multimodal Foundation Models Guide Visualization Design Through Visual Perception?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Matthew Berger, Shusen Liu","submitted_at":"2024-10-05T20:30:55Z","abstract_excerpt":"Foundation models for vision and language are the basis of AI applications across numerous sectors of society. The success of these models stems from their ability to mimic human capabilities, namely visual perception in vision models, and analytical reasoning in large language models. As visual perception and analysis are fundamental to data visualization, in this position paper we ask: how can we harness foundation models to advance progress in visualization design? Specifically, how can multimodal foundation models (MFMs) guide visualization design through visual perception? We approach the"},"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":"2410.04280","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-10-05T20:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"060dc3e0651dbb3ce0506d01996338d168462d77984772fbfe50106c54164cb0","abstract_canon_sha256":"dbebebc6d0150b37f987ed5c29b70572fcca53474ca4b91970374145bdb8f897"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:32.296274Z","signature_b64":"P0Fr7PiSVtUqlkYDQYCXF65sK3T+34fZbPnUFVBq0MJrC+vZRD90AblLvUR9Bk7TXV1UyGKGQdhlTSmwcI/SAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ffa5325d2b8b564bc66c1498ce3eaa0dca090341679a39301ff998bc2a4dc6b","last_reissued_at":"2026-07-05T09:16:32.295819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:32.295819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Visualization JUDGE : Can Multimodal Foundation Models Guide Visualization Design Through Visual Perception?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Matthew Berger, Shusen Liu","submitted_at":"2024-10-05T20:30:55Z","abstract_excerpt":"Foundation models for vision and language are the basis of AI applications across numerous sectors of society. The success of these models stems from their ability to mimic human capabilities, namely visual perception in vision models, and analytical reasoning in large language models. As visual perception and analysis are fundamental to data visualization, in this position paper we ask: how can we harness foundation models to advance progress in visualization design? Specifically, how can multimodal foundation models (MFMs) guide visualization design through visual perception? We approach the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04280","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/2410.04280/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":"2410.04280","created_at":"2026-07-05T09:16:32.295875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04280v1","created_at":"2026-07-05T09:16:32.295875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04280","created_at":"2026-07-05T09:16:32.295875+00:00"},{"alias_kind":"pith_short_12","alias_value":"F75FGJOSXC2W","created_at":"2026-07-05T09:16:32.295875+00:00"},{"alias_kind":"pith_short_16","alias_value":"F75FGJOSXC2WJPDG","created_at":"2026-07-05T09:16:32.295875+00:00"},{"alias_kind":"pith_short_8","alias_value":"F75FGJOS","created_at":"2026-07-05T09:16:32.295875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00988","citing_title":"PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F75FGJOSXC2WJPDGYFEYZY7KUD","json":"https://pith.science/pith/F75FGJOSXC2WJPDGYFEYZY7KUD.json","graph_json":"https://pith.science/api/pith-number/F75FGJOSXC2WJPDGYFEYZY7KUD/graph.json","events_json":"https://pith.science/api/pith-number/F75FGJOSXC2WJPDGYFEYZY7KUD/events.json","paper":"https://pith.science/paper/F75FGJOS"},"agent_actions":{"view_html":"https://pith.science/pith/F75FGJOSXC2WJPDGYFEYZY7KUD","download_json":"https://pith.science/pith/F75FGJOSXC2WJPDGYFEYZY7KUD.json","view_paper":"https://pith.science/paper/F75FGJOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04280&json=true","fetch_graph":"https://pith.science/api/pith-number/F75FGJOSXC2WJPDGYFEYZY7KUD/graph.json","fetch_events":"https://pith.science/api/pith-number/F75FGJOSXC2WJPDGYFEYZY7KUD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F75FGJOSXC2WJPDGYFEYZY7KUD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F75FGJOSXC2WJPDGYFEYZY7KUD/action/storage_attestation","attest_author":"https://pith.science/pith/F75FGJOSXC2WJPDGYFEYZY7KUD/action/author_attestation","sign_citation":"https://pith.science/pith/F75FGJOSXC2WJPDGYFEYZY7KUD/action/citation_signature","submit_replication":"https://pith.science/pith/F75FGJOSXC2WJPDGYFEYZY7KUD/action/replication_record"}},"created_at":"2026-07-05T09:16:32.295875+00:00","updated_at":"2026-07-05T09:16:32.295875+00:00"}