{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B2X332QAC3U6BOQPNJJWQGFZP5","short_pith_number":"pith:B2X332QA","schema_version":"1.0","canonical_sha256":"0eafbdea0016e9e0ba0f6a536818b97f7a0e0be2f5756884c80ab152acca795a","source":{"kind":"arxiv","id":"2507.18165","version":1},"attestation_state":"computed","paper":{"title":"ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Lin Gao, LiWen Fan, Siming Chen, Xueli Shu, Yuheng Zhao, Yu Zhang","submitted_at":"2025-07-24T08:02:35Z","abstract_excerpt":"Visual analytics (VA) is typically applied to complex data, thus requiring complex tools. While visual analytics empowers analysts in data analysis, analysts may get lost in the complexity occasionally. This highlights the need for intelligent assistance mechanisms. However, even the latest LLM-assisted VA systems only provide help when explicitly requested by the user, making them insufficiently intelligent to offer suggestions when analysts need them the most. We propose a ProactiveVA framework in which LLM-powered UI agent monitors user interactions and delivers context-aware assistance pro"},"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":"2507.18165","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-24T08:02:35Z","cross_cats_sorted":[],"title_canon_sha256":"0042315327620832fc88b09e322f3ec78017a662280b35e9f7e25217c9d93994","abstract_canon_sha256":"9ca3aee1cb79c0b4839e25af4733a24042b6ff32fe81e04479a9b4190e63ea9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:42.908368Z","signature_b64":"XQU9L1AZeFjSXeThu/lhmu/ILfr6Br4TjcO55O7LEUQZLwbDzGMi/CJTPUpR7sDUrfNkXOy32dzjt/a509+qBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eafbdea0016e9e0ba0f6a536818b97f7a0e0be2f5756884c80ab152acca795a","last_reissued_at":"2026-07-05T11:42:42.907884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:42.907884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Lin Gao, LiWen Fan, Siming Chen, Xueli Shu, Yuheng Zhao, Yu Zhang","submitted_at":"2025-07-24T08:02:35Z","abstract_excerpt":"Visual analytics (VA) is typically applied to complex data, thus requiring complex tools. While visual analytics empowers analysts in data analysis, analysts may get lost in the complexity occasionally. This highlights the need for intelligent assistance mechanisms. However, even the latest LLM-assisted VA systems only provide help when explicitly requested by the user, making them insufficiently intelligent to offer suggestions when analysts need them the most. We propose a ProactiveVA framework in which LLM-powered UI agent monitors user interactions and delivers context-aware assistance pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18165","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/2507.18165/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":"2507.18165","created_at":"2026-07-05T11:42:42.907943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18165v1","created_at":"2026-07-05T11:42:42.907943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18165","created_at":"2026-07-05T11:42:42.907943+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2X332QAC3U6","created_at":"2026-07-05T11:42:42.907943+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2X332QAC3U6BOQP","created_at":"2026-07-05T11:42:42.907943+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2X332QA","created_at":"2026-07-05T11:42:42.907943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00445","citing_title":"Gaze-Informed Proactive AI Assistance for Children's Picture Exploration","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08491","citing_title":"Figures as Interfaces: Toward LLM-Native Artifacts for Scientific Discovery","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14668","citing_title":"Beyond Chat and Clicks: GUI Agents for In-Situ Assistance via Live Interface Transformation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17002","citing_title":"Intelligent Drill-Down: Large Language Model-Driven Drill-Down Technique for Human-AI Collaborative Visual Exploration","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B2X332QAC3U6BOQPNJJWQGFZP5","json":"https://pith.science/pith/B2X332QAC3U6BOQPNJJWQGFZP5.json","graph_json":"https://pith.science/api/pith-number/B2X332QAC3U6BOQPNJJWQGFZP5/graph.json","events_json":"https://pith.science/api/pith-number/B2X332QAC3U6BOQPNJJWQGFZP5/events.json","paper":"https://pith.science/paper/B2X332QA"},"agent_actions":{"view_html":"https://pith.science/pith/B2X332QAC3U6BOQPNJJWQGFZP5","download_json":"https://pith.science/pith/B2X332QAC3U6BOQPNJJWQGFZP5.json","view_paper":"https://pith.science/paper/B2X332QA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18165&json=true","fetch_graph":"https://pith.science/api/pith-number/B2X332QAC3U6BOQPNJJWQGFZP5/graph.json","fetch_events":"https://pith.science/api/pith-number/B2X332QAC3U6BOQPNJJWQGFZP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2X332QAC3U6BOQPNJJWQGFZP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2X332QAC3U6BOQPNJJWQGFZP5/action/storage_attestation","attest_author":"https://pith.science/pith/B2X332QAC3U6BOQPNJJWQGFZP5/action/author_attestation","sign_citation":"https://pith.science/pith/B2X332QAC3U6BOQPNJJWQGFZP5/action/citation_signature","submit_replication":"https://pith.science/pith/B2X332QAC3U6BOQPNJJWQGFZP5/action/replication_record"}},"created_at":"2026-07-05T11:42:42.907943+00:00","updated_at":"2026-07-05T11:42:42.907943+00:00"}