{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ODDCD2DVXQH654F3U5SADSBCXG","short_pith_number":"pith:ODDCD2DV","schema_version":"1.0","canonical_sha256":"70c621e875bc0feef0bba76401c822b99754b4a929535cc9cd3a2695ff2fa7a2","source":{"kind":"arxiv","id":"2406.09961","version":2},"attestation_state":"computed","paper":{"title":"ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.SE","authors_text":"Bo Shui, Cheng Yang, Chufan Shi, Deng Cai, Gongye Liu, Junjie Wang, Linran Xu, Mohan Jing, Siheng Li, Xiaomei Nie, Xinyu Zhu, Yaxin Liu, Yujiu Yang, Yuxiang Zhang","submitted_at":"2024-06-14T12:10:51Z","abstract_excerpt":"We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded code generation capabilities of large multimodal models (LMMs). ChartMimic utilizes information-intensive visual charts and textual instructions as inputs, requiring LMMs to generate the corresponding code for chart rendering. ChartMimic includes 4,800 human-curated (figure, instruction, code) triplets, which represent the authentic chart use cases found in scientific papers across various domains (e.g., Physics, Computer Science, Economics, etc). These charts span 18 regular types and 4 advanced types, diversif"},"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":"2406.09961","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-14T12:10:51Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"404f2a39bd34e7592e070a858a68d262c01e122461e8f2a93fe4fe3c98b3e143","abstract_canon_sha256":"ca6ffa9d5edd7912d6680aa29c04952dbd13988dd63a09255836085231775400"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:20.808449Z","signature_b64":"SsnIxanErBdsGG8ax+bouLxd6Wv6EbOr5bTKX4G1jtuNXB/MkuQLJUxEEY/ocQHFX2Lw9U+Y2icMN5YdFaYXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70c621e875bc0feef0bba76401c822b99754b4a929535cc9cd3a2695ff2fa7a2","last_reissued_at":"2026-07-05T10:21:20.807925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:20.807925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.SE","authors_text":"Bo Shui, Cheng Yang, Chufan Shi, Deng Cai, Gongye Liu, Junjie Wang, Linran Xu, Mohan Jing, Siheng Li, Xiaomei Nie, Xinyu Zhu, Yaxin Liu, Yujiu Yang, Yuxiang Zhang","submitted_at":"2024-06-14T12:10:51Z","abstract_excerpt":"We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded code generation capabilities of large multimodal models (LMMs). ChartMimic utilizes information-intensive visual charts and textual instructions as inputs, requiring LMMs to generate the corresponding code for chart rendering. ChartMimic includes 4,800 human-curated (figure, instruction, code) triplets, which represent the authentic chart use cases found in scientific papers across various domains (e.g., Physics, Computer Science, Economics, etc). These charts span 18 regular types and 4 advanced types, diversif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09961","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/2406.09961/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":"2406.09961","created_at":"2026-07-05T10:21:20.807987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09961v2","created_at":"2026-07-05T10:21:20.807987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09961","created_at":"2026-07-05T10:21:20.807987+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODDCD2DVXQH6","created_at":"2026-07-05T10:21:20.807987+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODDCD2DVXQH654F3","created_at":"2026-07-05T10:21:20.807987+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODDCD2DV","created_at":"2026-07-05T10:21:20.807987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01883","citing_title":"PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":280,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10334","citing_title":"Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29808","citing_title":"Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08945","citing_title":"FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13224","citing_title":"Visual-ERM: Reward Modeling for Visual Equivalence","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22192","citing_title":"CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06079","citing_title":"Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15781","citing_title":"ReVis: Towards Reusable Image-Based Visualizations with MLLMs","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODDCD2DVXQH654F3U5SADSBCXG","json":"https://pith.science/pith/ODDCD2DVXQH654F3U5SADSBCXG.json","graph_json":"https://pith.science/api/pith-number/ODDCD2DVXQH654F3U5SADSBCXG/graph.json","events_json":"https://pith.science/api/pith-number/ODDCD2DVXQH654F3U5SADSBCXG/events.json","paper":"https://pith.science/paper/ODDCD2DV"},"agent_actions":{"view_html":"https://pith.science/pith/ODDCD2DVXQH654F3U5SADSBCXG","download_json":"https://pith.science/pith/ODDCD2DVXQH654F3U5SADSBCXG.json","view_paper":"https://pith.science/paper/ODDCD2DV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09961&json=true","fetch_graph":"https://pith.science/api/pith-number/ODDCD2DVXQH654F3U5SADSBCXG/graph.json","fetch_events":"https://pith.science/api/pith-number/ODDCD2DVXQH654F3U5SADSBCXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODDCD2DVXQH654F3U5SADSBCXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODDCD2DVXQH654F3U5SADSBCXG/action/storage_attestation","attest_author":"https://pith.science/pith/ODDCD2DVXQH654F3U5SADSBCXG/action/author_attestation","sign_citation":"https://pith.science/pith/ODDCD2DVXQH654F3U5SADSBCXG/action/citation_signature","submit_replication":"https://pith.science/pith/ODDCD2DVXQH654F3U5SADSBCXG/action/replication_record"}},"created_at":"2026-07-05T10:21:20.807987+00:00","updated_at":"2026-07-05T10:21:20.807987+00:00"}