{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W7TL6IAWTGIOFKQXZSFB4Y27CW","short_pith_number":"pith:W7TL6IAW","schema_version":"1.0","canonical_sha256":"b7e6bf20169990e2aa17cc8a1e635f15a970929b70edc1ee0cef3ac2d8c2f448","source":{"kind":"arxiv","id":"2504.05506","version":2},"attestation_state":"computed","paper":{"title":"ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaryaman Kartha, Aayush Bajaj, Ahmed Masry, Enamul Hoque, Firoz Kabir, Mahir Ahmed, Md Rizwan Parvez, Md Tahmid Rahman Laskar, Megh Thakkar, Mehrad Shahmohammadi, Mizanur Rahman, Mohammed Saidul Islam, Shadikur Rahman, Shafiq Joty","submitted_at":"2025-04-07T21:05:06Z","abstract_excerpt":"Charts are ubiquitous, as people often use them to analyze data, answer questions, and discover critical insights. However, performing complex analytical tasks with charts requires significant perceptual and cognitive effort. Chart Question Answering (CQA) systems automate this process by enabling models to interpret and reason with visual representations of data. However, existing benchmarks like ChartQA lack real-world diversity and have recently shown performance saturation with modern large vision-language models (LVLMs). To address these limitations, we introduce ChartQAPro, a new benchma"},"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":"2504.05506","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T21:05:06Z","cross_cats_sorted":[],"title_canon_sha256":"01cbca18428f35c472187589777df290047727ada8503d72d049fd5cfeeb9f1e","abstract_canon_sha256":"2119f472e9edfb2228f7ed0bd8a4b7def087953270189ad2bbd61fae0c40ec65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:02.524174Z","signature_b64":"lGAoy4ZPJ/EE+Pl8leMuLl89zYzephrCMk0Jz0RNLWsMyccX7jk9z42F6qez5KOio7YgM8TYV/wD5Jx5dIj6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7e6bf20169990e2aa17cc8a1e635f15a970929b70edc1ee0cef3ac2d8c2f448","last_reissued_at":"2026-07-05T10:47:02.523659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:02.523659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaryaman Kartha, Aayush Bajaj, Ahmed Masry, Enamul Hoque, Firoz Kabir, Mahir Ahmed, Md Rizwan Parvez, Md Tahmid Rahman Laskar, Megh Thakkar, Mehrad Shahmohammadi, Mizanur Rahman, Mohammed Saidul Islam, Shadikur Rahman, Shafiq Joty","submitted_at":"2025-04-07T21:05:06Z","abstract_excerpt":"Charts are ubiquitous, as people often use them to analyze data, answer questions, and discover critical insights. However, performing complex analytical tasks with charts requires significant perceptual and cognitive effort. Chart Question Answering (CQA) systems automate this process by enabling models to interpret and reason with visual representations of data. However, existing benchmarks like ChartQA lack real-world diversity and have recently shown performance saturation with modern large vision-language models (LVLMs). To address these limitations, we introduce ChartQAPro, a new benchma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05506","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/2504.05506/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":"2504.05506","created_at":"2026-07-05T10:47:02.523727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05506v2","created_at":"2026-07-05T10:47:02.523727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05506","created_at":"2026-07-05T10:47:02.523727+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7TL6IAWTGIO","created_at":"2026-07-05T10:47:02.523727+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7TL6IAWTGIOFKQX","created_at":"2026-07-05T10:47:02.523727+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7TL6IAW","created_at":"2026-07-05T10:47:02.523727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23997","citing_title":"ChartWalker: Benchmarking the Cross-Chart RAG Task with Hierarchical Knowledge Graphs","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00248","citing_title":"Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01599","citing_title":"TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL","ref_index":24,"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":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27195","citing_title":"EpiCurveBench: Evaluating VLMs on Epidemic Curve Digitization","ref_index":6,"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":41,"is_internal_anchor":false},{"citing_arxiv_id":"2512.19173","citing_title":"CycleChart: A Unified Consistency-Based Learning Framework for Bidirectional Chart Understanding and Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13606","citing_title":"ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27064","citing_title":"ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding","ref_index":39,"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":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11634","citing_title":"Unlocking UML Class Diagram Understanding in Vision Language Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W7TL6IAWTGIOFKQXZSFB4Y27CW","json":"https://pith.science/pith/W7TL6IAWTGIOFKQXZSFB4Y27CW.json","graph_json":"https://pith.science/api/pith-number/W7TL6IAWTGIOFKQXZSFB4Y27CW/graph.json","events_json":"https://pith.science/api/pith-number/W7TL6IAWTGIOFKQXZSFB4Y27CW/events.json","paper":"https://pith.science/paper/W7TL6IAW"},"agent_actions":{"view_html":"https://pith.science/pith/W7TL6IAWTGIOFKQXZSFB4Y27CW","download_json":"https://pith.science/pith/W7TL6IAWTGIOFKQXZSFB4Y27CW.json","view_paper":"https://pith.science/paper/W7TL6IAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05506&json=true","fetch_graph":"https://pith.science/api/pith-number/W7TL6IAWTGIOFKQXZSFB4Y27CW/graph.json","fetch_events":"https://pith.science/api/pith-number/W7TL6IAWTGIOFKQXZSFB4Y27CW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7TL6IAWTGIOFKQXZSFB4Y27CW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7TL6IAWTGIOFKQXZSFB4Y27CW/action/storage_attestation","attest_author":"https://pith.science/pith/W7TL6IAWTGIOFKQXZSFB4Y27CW/action/author_attestation","sign_citation":"https://pith.science/pith/W7TL6IAWTGIOFKQXZSFB4Y27CW/action/citation_signature","submit_replication":"https://pith.science/pith/W7TL6IAWTGIOFKQXZSFB4Y27CW/action/replication_record"}},"created_at":"2026-07-05T10:47:02.523727+00:00","updated_at":"2026-07-05T10:47:02.523727+00:00"}