{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VKZ74NFP45XBQWSAEPR7C6RSD2","short_pith_number":"pith:VKZ74NFP","schema_version":"1.0","canonical_sha256":"aab3fe34afe76e185a4023e3f17a321ea9c42549cb52e5beb14e9b9043fd38bf","source":{"kind":"arxiv","id":"2311.10774","version":2},"attestation_state":"computed","paper":{"title":"MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Fuxiao Liu, Jianshu Chen, Kaiqiang Song, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Yaser Yacoob","submitted_at":"2023-11-15T23:36:42Z","abstract_excerpt":"With the rapid development of large language models (LLMs) and their integration into large multimodal models (LMMs), there has been impressive progress in zero-shot completion of user-oriented vision-language tasks. However, a gap remains in the domain of chart image understanding due to the distinct abstract components in charts. To address this, we introduce a large-scale MultiModal Chart Instruction (\\textbf{MMC-Instruction}) dataset comprising 600k instances supporting diverse tasks and chart types. Leveraging this data, we develop MultiModal Chart Assistant (\\textbf{MMCA}), an LMM that a"},"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":"2311.10774","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T23:36:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0fc0646de981856323633f2f731cd6816d1335a2c7d6975266d8da9bdfc3d9cb","abstract_canon_sha256":"c76b4e8f23ec21c51d0b53a085f689d8ab4334c3ff3ae825524753510caf6114"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:59.762404Z","signature_b64":"Nl3I7G2J1OU4Z/GXazAOT0sUlrovM6tcX/dn7LEs1N8Hm1IZQqbl5TN0RiMVf4yFwz3YxkmCMVXTJnjZEP2XAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aab3fe34afe76e185a4023e3f17a321ea9c42549cb52e5beb14e9b9043fd38bf","last_reissued_at":"2026-07-05T08:07:59.761891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:59.761891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Fuxiao Liu, Jianshu Chen, Kaiqiang Song, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Yaser Yacoob","submitted_at":"2023-11-15T23:36:42Z","abstract_excerpt":"With the rapid development of large language models (LLMs) and their integration into large multimodal models (LMMs), there has been impressive progress in zero-shot completion of user-oriented vision-language tasks. However, a gap remains in the domain of chart image understanding due to the distinct abstract components in charts. To address this, we introduce a large-scale MultiModal Chart Instruction (\\textbf{MMC-Instruction}) dataset comprising 600k instances supporting diverse tasks and chart types. Leveraging this data, we develop MultiModal Chart Assistant (\\textbf{MMCA}), an LMM that a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10774","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/2311.10774/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":"2311.10774","created_at":"2026-07-05T08:07:59.761958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10774v2","created_at":"2026-07-05T08:07:59.761958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10774","created_at":"2026-07-05T08:07:59.761958+00:00"},{"alias_kind":"pith_short_12","alias_value":"VKZ74NFP45XB","created_at":"2026-07-05T08:07:59.761958+00:00"},{"alias_kind":"pith_short_16","alias_value":"VKZ74NFP45XBQWSA","created_at":"2026-07-05T08:07:59.761958+00:00"},{"alias_kind":"pith_short_8","alias_value":"VKZ74NFP","created_at":"2026-07-05T08:07:59.761958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29446","citing_title":"CrystalXRD-Bench: Benchmarking Vision-Language Models for XRD Peak Indexing Across Diverse Crystalline Materials","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2407.03320","citing_title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2401.16420","citing_title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13606","citing_title":"ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2409.17146","citing_title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00161","citing_title":"Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16821","citing_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13106","citing_title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":149,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VKZ74NFP45XBQWSAEPR7C6RSD2","json":"https://pith.science/pith/VKZ74NFP45XBQWSAEPR7C6RSD2.json","graph_json":"https://pith.science/api/pith-number/VKZ74NFP45XBQWSAEPR7C6RSD2/graph.json","events_json":"https://pith.science/api/pith-number/VKZ74NFP45XBQWSAEPR7C6RSD2/events.json","paper":"https://pith.science/paper/VKZ74NFP"},"agent_actions":{"view_html":"https://pith.science/pith/VKZ74NFP45XBQWSAEPR7C6RSD2","download_json":"https://pith.science/pith/VKZ74NFP45XBQWSAEPR7C6RSD2.json","view_paper":"https://pith.science/paper/VKZ74NFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10774&json=true","fetch_graph":"https://pith.science/api/pith-number/VKZ74NFP45XBQWSAEPR7C6RSD2/graph.json","fetch_events":"https://pith.science/api/pith-number/VKZ74NFP45XBQWSAEPR7C6RSD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VKZ74NFP45XBQWSAEPR7C6RSD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VKZ74NFP45XBQWSAEPR7C6RSD2/action/storage_attestation","attest_author":"https://pith.science/pith/VKZ74NFP45XBQWSAEPR7C6RSD2/action/author_attestation","sign_citation":"https://pith.science/pith/VKZ74NFP45XBQWSAEPR7C6RSD2/action/citation_signature","submit_replication":"https://pith.science/pith/VKZ74NFP45XBQWSAEPR7C6RSD2/action/replication_record"}},"created_at":"2026-07-05T08:07:59.761958+00:00","updated_at":"2026-07-05T08:07:59.761958+00:00"}