{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TXD6EJVCB233TYALTG5AEAMSIR","short_pith_number":"pith:TXD6EJVC","schema_version":"1.0","canonical_sha256":"9dc7e226a20eb7b9e00b99ba020192446160d494b7b163c433fabd3fc37386d9","source":{"kind":"arxiv","id":"2503.04110","version":2},"attestation_state":"computed","paper":{"title":"InterChat: Enhancing Generative Visual Analytics using Multimodal Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Dongyu Liu, Jiajing Guo, Jiang Wu, Jorge Piazentin Ono, Juntong Chen, Liu Ren, Vikram Mohanty, WenBin He, Xueming Li","submitted_at":"2025-03-06T05:35:19Z","abstract_excerpt":"The rise of Large Language Models (LLMs) and generative visual analytics systems has transformed data-driven insights, yet significant challenges persist in accurately interpreting users' analytical and interaction intents. While language inputs offer flexibility, they often lack precision, making the expression of complex intents inefficient, error-prone, and time-intensive. To address these limitations, we investigate the design space of multimodal interactions for generative visual analytics through a literature review and pilot brainstorming sessions. Building on these insights, we introdu"},"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":"2503.04110","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-03-06T05:35:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"72f50a9fbf559425058aa03edc8b5b5a092234e3086273c29e654361198b75d8","abstract_canon_sha256":"a5c4dc01027c32974f3ea09302dc851ec09d132366073771e7f812f2b78b014b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:52.028102Z","signature_b64":"WOX+kAphEWKioolmtNxQeRrUw5hYEUa5iLAg9RNiLdezs6WyBQv5v7Jdle4brGshbsWuT/A0so7hkzNqDDGKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dc7e226a20eb7b9e00b99ba020192446160d494b7b163c433fabd3fc37386d9","last_reissued_at":"2026-07-05T10:49:52.027619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:52.027619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InterChat: Enhancing Generative Visual Analytics using Multimodal Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Dongyu Liu, Jiajing Guo, Jiang Wu, Jorge Piazentin Ono, Juntong Chen, Liu Ren, Vikram Mohanty, WenBin He, Xueming Li","submitted_at":"2025-03-06T05:35:19Z","abstract_excerpt":"The rise of Large Language Models (LLMs) and generative visual analytics systems has transformed data-driven insights, yet significant challenges persist in accurately interpreting users' analytical and interaction intents. While language inputs offer flexibility, they often lack precision, making the expression of complex intents inefficient, error-prone, and time-intensive. To address these limitations, we investigate the design space of multimodal interactions for generative visual analytics through a literature review and pilot brainstorming sessions. Building on these insights, we introdu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04110","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/2503.04110/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":"2503.04110","created_at":"2026-07-05T10:49:52.027678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04110v2","created_at":"2026-07-05T10:49:52.027678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04110","created_at":"2026-07-05T10:49:52.027678+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXD6EJVCB233","created_at":"2026-07-05T10:49:52.027678+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXD6EJVCB233TYAL","created_at":"2026-07-05T10:49:52.027678+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXD6EJVC","created_at":"2026-07-05T10:49:52.027678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03142","citing_title":"Disentangling Visual and Factual Correctness in LVLMs' Visualization Literacy","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08914","citing_title":"Vibe Visualizing: How Visualization Novices Try (and Fail) to Generate and Interpret Visualizations with Conversational AI","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXD6EJVCB233TYALTG5AEAMSIR","json":"https://pith.science/pith/TXD6EJVCB233TYALTG5AEAMSIR.json","graph_json":"https://pith.science/api/pith-number/TXD6EJVCB233TYALTG5AEAMSIR/graph.json","events_json":"https://pith.science/api/pith-number/TXD6EJVCB233TYALTG5AEAMSIR/events.json","paper":"https://pith.science/paper/TXD6EJVC"},"agent_actions":{"view_html":"https://pith.science/pith/TXD6EJVCB233TYALTG5AEAMSIR","download_json":"https://pith.science/pith/TXD6EJVCB233TYALTG5AEAMSIR.json","view_paper":"https://pith.science/paper/TXD6EJVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04110&json=true","fetch_graph":"https://pith.science/api/pith-number/TXD6EJVCB233TYALTG5AEAMSIR/graph.json","fetch_events":"https://pith.science/api/pith-number/TXD6EJVCB233TYALTG5AEAMSIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXD6EJVCB233TYALTG5AEAMSIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXD6EJVCB233TYALTG5AEAMSIR/action/storage_attestation","attest_author":"https://pith.science/pith/TXD6EJVCB233TYALTG5AEAMSIR/action/author_attestation","sign_citation":"https://pith.science/pith/TXD6EJVCB233TYALTG5AEAMSIR/action/citation_signature","submit_replication":"https://pith.science/pith/TXD6EJVCB233TYALTG5AEAMSIR/action/replication_record"}},"created_at":"2026-07-05T10:49:52.027678+00:00","updated_at":"2026-07-05T10:49:52.027678+00:00"}