{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KVDIQ22YWEWEAJKUNBI6VRPIX7","short_pith_number":"pith:KVDIQ22Y","schema_version":"1.0","canonical_sha256":"5546886b58b12c4025546851eac5e8bfc8c5e952a9a3060aeb65dcd5eb7923e0","source":{"kind":"arxiv","id":"2402.11453","version":3},"attestation_state":"computed","paper":{"title":"MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Yu, Maosong Sun, Pengyuan Liu, Shuo Wang, Xiaodong Shi, Xin Cong, Xu Han, Yukun Yan, Zhenghao Liu, Zhixing Tan, Zhiyuan Liu, Zhiyu Yang, Zihan Zhou","submitted_at":"2024-02-18T04:28:28Z","abstract_excerpt":"Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Despite its importance, the use of Large Language Models (LLMs) for scientific data visualization remains rather unexplored. In this study, we introduce MatPlotAgent, an efficient model-agnostic LLM agent framework designed to automate scientific data visualization tasks. Leveraging the capabilities of both code LLMs and multi-modal LLMs, MatPlotAgent consists of three core modules: query understanding, code generation "},"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":"2402.11453","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T04:28:28Z","cross_cats_sorted":[],"title_canon_sha256":"a17b47489d79076842113e73a96b8cd65f6e500207521d30a4f3918591311daf","abstract_canon_sha256":"a6312b25e10828b2b12f43f38cd7e36b653df53cb4edd0a01a0052d23e72a868"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:49.887035Z","signature_b64":"zYJJm2WNKKf2NbIdlGeoi8h9L+xyv2nb/BufUsUYSybofww9Eslyf/qNA7rkmB59+9CuZ/45yF6bWydzbb2nDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5546886b58b12c4025546851eac5e8bfc8c5e952a9a3060aeb65dcd5eb7923e0","last_reissued_at":"2026-07-05T07:57:49.886533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:49.886533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Yu, Maosong Sun, Pengyuan Liu, Shuo Wang, Xiaodong Shi, Xin Cong, Xu Han, Yukun Yan, Zhenghao Liu, Zhixing Tan, Zhiyuan Liu, Zhiyu Yang, Zihan Zhou","submitted_at":"2024-02-18T04:28:28Z","abstract_excerpt":"Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Despite its importance, the use of Large Language Models (LLMs) for scientific data visualization remains rather unexplored. In this study, we introduce MatPlotAgent, an efficient model-agnostic LLM agent framework designed to automate scientific data visualization tasks. Leveraging the capabilities of both code LLMs and multi-modal LLMs, MatPlotAgent consists of three core modules: query understanding, code generation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11453","kind":"arxiv","version":3},"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/2402.11453/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":"2402.11453","created_at":"2026-07-05T07:57:49.886594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11453v3","created_at":"2026-07-05T07:57:49.886594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11453","created_at":"2026-07-05T07:57:49.886594+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVDIQ22YWEWE","created_at":"2026-07-05T07:57:49.886594+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVDIQ22YWEWEAJKU","created_at":"2026-07-05T07:57:49.886594+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVDIQ22Y","created_at":"2026-07-05T07:57:49.886594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15932","citing_title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09174","citing_title":"Demonstrating chart-plot: Closing the Last Mile of Academic Chart Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00370","citing_title":"Agentic Authoring of Interactive Multiview Visualizations in Genomics","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":236,"is_internal_anchor":false},{"citing_arxiv_id":"2602.05353","citing_title":"AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06079","citing_title":"Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVDIQ22YWEWEAJKUNBI6VRPIX7","json":"https://pith.science/pith/KVDIQ22YWEWEAJKUNBI6VRPIX7.json","graph_json":"https://pith.science/api/pith-number/KVDIQ22YWEWEAJKUNBI6VRPIX7/graph.json","events_json":"https://pith.science/api/pith-number/KVDIQ22YWEWEAJKUNBI6VRPIX7/events.json","paper":"https://pith.science/paper/KVDIQ22Y"},"agent_actions":{"view_html":"https://pith.science/pith/KVDIQ22YWEWEAJKUNBI6VRPIX7","download_json":"https://pith.science/pith/KVDIQ22YWEWEAJKUNBI6VRPIX7.json","view_paper":"https://pith.science/paper/KVDIQ22Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11453&json=true","fetch_graph":"https://pith.science/api/pith-number/KVDIQ22YWEWEAJKUNBI6VRPIX7/graph.json","fetch_events":"https://pith.science/api/pith-number/KVDIQ22YWEWEAJKUNBI6VRPIX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVDIQ22YWEWEAJKUNBI6VRPIX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVDIQ22YWEWEAJKUNBI6VRPIX7/action/storage_attestation","attest_author":"https://pith.science/pith/KVDIQ22YWEWEAJKUNBI6VRPIX7/action/author_attestation","sign_citation":"https://pith.science/pith/KVDIQ22YWEWEAJKUNBI6VRPIX7/action/citation_signature","submit_replication":"https://pith.science/pith/KVDIQ22YWEWEAJKUNBI6VRPIX7/action/replication_record"}},"created_at":"2026-07-05T07:57:49.886594+00:00","updated_at":"2026-07-05T07:57:49.886594+00:00"}