{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BN7A3P3SC3NDR2T6VUI4NKRP26","short_pith_number":"pith:BN7A3P3S","schema_version":"1.0","canonical_sha256":"0b7e0dbf7216da38ea7ead11c6aa2fd7b0bfe5912e25fea477963aee082f1983","source":{"kind":"arxiv","id":"2402.12185","version":6},"attestation_state":"computed","paper":{"title":"ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Botian Shi, Bo Zhang, Hancheng Ye, Hongbin Zhou, Junchi Yan, Min Dou, Peng Ye, Qi Liu, Renqiu Xia, Xiangchao Yan, Yu Qiao, Zijun Chen","submitted_at":"2024-02-19T14:48:23Z","abstract_excerpt":"Recently, many versatile Multi-modal Large Language Models (MLLMs) have emerged continuously. However, their capacity to query information depicted in visual charts and engage in reasoning based on the queried contents remains under-explored. In this paper, to comprehensively and rigorously benchmark the ability of the off-the-shelf MLLMs in the chart domain, we construct ChartX, a multi-modal evaluation set covering 18 chart types, 7 chart tasks, 22 disciplinary topics, and high-quality chart data. Besides, we develop ChartVLM to offer a new perspective on handling multi-modal tasks that stro"},"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":"2402.12185","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-19T14:48:23Z","cross_cats_sorted":[],"title_canon_sha256":"e6a7f9aef4241e5dd0dea0ecdce9304be001a431becf5c9e379aa3828bb7b002","abstract_canon_sha256":"5233a6426fc116c96de34609ba0520ba168e5878fbdb7a859e68085c6e68a5de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:31.743306Z","signature_b64":"3XIrSKm3uX3N2P+DZwHlIwurlHzyn2yTSQNNfbj9i7jy7+WAOITgqSfAnc/g7kMr71EXbADQPd9vuwEoLn69BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b7e0dbf7216da38ea7ead11c6aa2fd7b0bfe5912e25fea477963aee082f1983","last_reissued_at":"2026-07-05T10:54:31.742716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:31.742716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Botian Shi, Bo Zhang, Hancheng Ye, Hongbin Zhou, Junchi Yan, Min Dou, Peng Ye, Qi Liu, Renqiu Xia, Xiangchao Yan, Yu Qiao, Zijun Chen","submitted_at":"2024-02-19T14:48:23Z","abstract_excerpt":"Recently, many versatile Multi-modal Large Language Models (MLLMs) have emerged continuously. However, their capacity to query information depicted in visual charts and engage in reasoning based on the queried contents remains under-explored. In this paper, to comprehensively and rigorously benchmark the ability of the off-the-shelf MLLMs in the chart domain, we construct ChartX, a multi-modal evaluation set covering 18 chart types, 7 chart tasks, 22 disciplinary topics, and high-quality chart data. Besides, we develop ChartVLM to offer a new perspective on handling multi-modal tasks that stro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12185","kind":"arxiv","version":6},"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/2402.12185/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":"2402.12185","created_at":"2026-07-05T10:54:31.742798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12185v6","created_at":"2026-07-05T10:54:31.742798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12185","created_at":"2026-07-05T10:54:31.742798+00:00"},{"alias_kind":"pith_short_12","alias_value":"BN7A3P3SC3ND","created_at":"2026-07-05T10:54:31.742798+00:00"},{"alias_kind":"pith_short_16","alias_value":"BN7A3P3SC3NDR2T6","created_at":"2026-07-05T10:54:31.742798+00:00"},{"alias_kind":"pith_short_8","alias_value":"BN7A3P3S","created_at":"2026-07-05T10:54:31.742798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22938","citing_title":"Large language model-enabled automated data extraction for concrete materials informatics","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29446","citing_title":"CrystalXRD-Bench: Benchmarking Vision-Language Models for XRD Peak Indexing Across Diverse Crystalline Materials","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2410.05970","citing_title":"PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2410.21169","citing_title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","ref_index":262,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00321","citing_title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13606","citing_title":"ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13232","citing_title":"PlotChain: Deterministic Checkpointed Evaluation of Multimodal LLMs on Engineering Plot Reading","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03157","citing_title":"Chart-RL: Policy Optimization Reinforcement Learning for Enhanced Visual Reasoning in Chart Question Answering with Vision Language Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22938","citing_title":"Large language model-enabled automated data extraction for concrete materials informatics","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06021","citing_title":"PlotPick: AI-powered batch extraction of numerical data from scientific figures","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BN7A3P3SC3NDR2T6VUI4NKRP26","json":"https://pith.science/pith/BN7A3P3SC3NDR2T6VUI4NKRP26.json","graph_json":"https://pith.science/api/pith-number/BN7A3P3SC3NDR2T6VUI4NKRP26/graph.json","events_json":"https://pith.science/api/pith-number/BN7A3P3SC3NDR2T6VUI4NKRP26/events.json","paper":"https://pith.science/paper/BN7A3P3S"},"agent_actions":{"view_html":"https://pith.science/pith/BN7A3P3SC3NDR2T6VUI4NKRP26","download_json":"https://pith.science/pith/BN7A3P3SC3NDR2T6VUI4NKRP26.json","view_paper":"https://pith.science/paper/BN7A3P3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12185&json=true","fetch_graph":"https://pith.science/api/pith-number/BN7A3P3SC3NDR2T6VUI4NKRP26/graph.json","fetch_events":"https://pith.science/api/pith-number/BN7A3P3SC3NDR2T6VUI4NKRP26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BN7A3P3SC3NDR2T6VUI4NKRP26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BN7A3P3SC3NDR2T6VUI4NKRP26/action/storage_attestation","attest_author":"https://pith.science/pith/BN7A3P3SC3NDR2T6VUI4NKRP26/action/author_attestation","sign_citation":"https://pith.science/pith/BN7A3P3SC3NDR2T6VUI4NKRP26/action/citation_signature","submit_replication":"https://pith.science/pith/BN7A3P3SC3NDR2T6VUI4NKRP26/action/replication_record"}},"created_at":"2026-07-05T10:54:31.742798+00:00","updated_at":"2026-07-05T10:54:31.742798+00:00"}