{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BUB7E45D3UJ6INBS2DFOLOTDB2","short_pith_number":"pith:BUB7E45D","schema_version":"1.0","canonical_sha256":"0d03f273a3dd13e43432d0cae5ba630e8bf7858dab8f58cc391fecdff4832a5e","source":{"kind":"arxiv","id":"2310.07652","version":2},"attestation_state":"computed","paper":{"title":"LLM4Vis: Explainable Visualization Recommendation using ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.HC","authors_text":"Ee-Peng Lim, Lei Wang, Songheng Zhang, Yong Wang, Yun Wang","submitted_at":"2023-10-11T16:51:46Z","abstract_excerpt":"Data visualization is a powerful tool for exploring and communicating insights in various domains. To automate visualization choice for datasets, a task known as visualization recommendation has been proposed. Various machine-learning-based approaches have been developed for this purpose, but they often require a large corpus of dataset-visualization pairs for training and lack natural explanations for their results. To address this research gap, we propose LLM4Vis, a novel ChatGPT-based prompting approach to perform visualization recommendation and return human-like explanations using very fe"},"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":"2310.07652","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-10-11T16:51:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a237a0cea2bbacfc74dd7ee7d4bec7dabdd6f4d57bba6876a7963debaec2ed2a","abstract_canon_sha256":"bb2b738a122d22514c1bab8c899dde51ee61ba2a70f450fac159775ff6e7396e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:06.959637Z","signature_b64":"7HxQyhKKT33DYe1bVfISril6zFquZWgGfybvlhHTfsCfb5HSYx/Su4SksxmNfuxDCK0+9h1rMS1Bwe6WzwfxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d03f273a3dd13e43432d0cae5ba630e8bf7858dab8f58cc391fecdff4832a5e","last_reissued_at":"2026-07-05T07:01:06.959160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:06.959160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM4Vis: Explainable Visualization Recommendation using ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.HC","authors_text":"Ee-Peng Lim, Lei Wang, Songheng Zhang, Yong Wang, Yun Wang","submitted_at":"2023-10-11T16:51:46Z","abstract_excerpt":"Data visualization is a powerful tool for exploring and communicating insights in various domains. To automate visualization choice for datasets, a task known as visualization recommendation has been proposed. Various machine-learning-based approaches have been developed for this purpose, but they often require a large corpus of dataset-visualization pairs for training and lack natural explanations for their results. To address this research gap, we propose LLM4Vis, a novel ChatGPT-based prompting approach to perform visualization recommendation and return human-like explanations using very fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07652","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/2310.07652/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":"2310.07652","created_at":"2026-07-05T07:01:06.959216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07652v2","created_at":"2026-07-05T07:01:06.959216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07652","created_at":"2026-07-05T07:01:06.959216+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUB7E45D3UJ6","created_at":"2026-07-05T07:01:06.959216+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUB7E45D3UJ6INBS","created_at":"2026-07-05T07:01:06.959216+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUB7E45D","created_at":"2026-07-05T07:01:06.959216+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31311","citing_title":"From Idea to Prototype in an Afternoon: Scaffolded, AI-Assisted Rapid VA Prototyping","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2502.16759","citing_title":"Can Explanations Improve Recommendations? Evidence from Prediction-Informed Explanations","ref_index":87,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BUB7E45D3UJ6INBS2DFOLOTDB2","json":"https://pith.science/pith/BUB7E45D3UJ6INBS2DFOLOTDB2.json","graph_json":"https://pith.science/api/pith-number/BUB7E45D3UJ6INBS2DFOLOTDB2/graph.json","events_json":"https://pith.science/api/pith-number/BUB7E45D3UJ6INBS2DFOLOTDB2/events.json","paper":"https://pith.science/paper/BUB7E45D"},"agent_actions":{"view_html":"https://pith.science/pith/BUB7E45D3UJ6INBS2DFOLOTDB2","download_json":"https://pith.science/pith/BUB7E45D3UJ6INBS2DFOLOTDB2.json","view_paper":"https://pith.science/paper/BUB7E45D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07652&json=true","fetch_graph":"https://pith.science/api/pith-number/BUB7E45D3UJ6INBS2DFOLOTDB2/graph.json","fetch_events":"https://pith.science/api/pith-number/BUB7E45D3UJ6INBS2DFOLOTDB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUB7E45D3UJ6INBS2DFOLOTDB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUB7E45D3UJ6INBS2DFOLOTDB2/action/storage_attestation","attest_author":"https://pith.science/pith/BUB7E45D3UJ6INBS2DFOLOTDB2/action/author_attestation","sign_citation":"https://pith.science/pith/BUB7E45D3UJ6INBS2DFOLOTDB2/action/citation_signature","submit_replication":"https://pith.science/pith/BUB7E45D3UJ6INBS2DFOLOTDB2/action/replication_record"}},"created_at":"2026-07-05T07:01:06.959216+00:00","updated_at":"2026-07-05T07:01:06.959216+00:00"}