{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SMXYYZ5SZBZ65HZLJX6KFUBPFU","short_pith_number":"pith:SMXYYZ5S","schema_version":"1.0","canonical_sha256":"932f8c67b2c873ee9f2b4dfca2d02f2d194dd2eb02e8514afd783ba1f1e70879","source":{"kind":"arxiv","id":"2505.23242","version":1},"attestation_state":"computed","paper":{"title":"ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bihui Yu, Gaowei Wu, Jingxuan Wei, Junnan Zhu, Lei Wang, Nan Xu, Yanni Hao","submitted_at":"2025-05-29T08:46:03Z","abstract_excerpt":"Chart question answering (CQA) has become a critical multimodal task for evaluating the reasoning capabilities of vision-language models. While early approaches have shown promising performance by focusing on visual features or leveraging large-scale pre-training, most existing evaluations rely on rigid output formats and objective metrics, thus ignoring the complex, real-world demands of practical chart analysis. In this paper, we introduce ChartMind, a new benchmark designed for complex CQA tasks in real-world settings. ChartMind covers seven task categories, incorporates multilingual contex"},"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":"2505.23242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T08:46:03Z","cross_cats_sorted":[],"title_canon_sha256":"6b54d3ddf685c410788ec83ff782e43093e2208e5c2a31c99319dc322fe276b2","abstract_canon_sha256":"06cc3486d0a194d34b046f346b8a431a3ae917306f6ae1d1806d3119f36c070d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:58.240295Z","signature_b64":"Tqio/hIgPzt1SyqL+m80uszJVw2/YBB16lEwLN3+JvbtB7PECC5vSGDnTy1uVtFFdnChFmZ0x35Zc3G+9KrJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"932f8c67b2c873ee9f2b4dfca2d02f2d194dd2eb02e8514afd783ba1f1e70879","last_reissued_at":"2026-07-05T11:11:58.239710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:58.239710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bihui Yu, Gaowei Wu, Jingxuan Wei, Junnan Zhu, Lei Wang, Nan Xu, Yanni Hao","submitted_at":"2025-05-29T08:46:03Z","abstract_excerpt":"Chart question answering (CQA) has become a critical multimodal task for evaluating the reasoning capabilities of vision-language models. While early approaches have shown promising performance by focusing on visual features or leveraging large-scale pre-training, most existing evaluations rely on rigid output formats and objective metrics, thus ignoring the complex, real-world demands of practical chart analysis. In this paper, we introduce ChartMind, a new benchmark designed for complex CQA tasks in real-world settings. ChartMind covers seven task categories, incorporates multilingual contex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23242","kind":"arxiv","version":1},"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/2505.23242/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":"2505.23242","created_at":"2026-07-05T11:11:58.239782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23242v1","created_at":"2026-07-05T11:11:58.239782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23242","created_at":"2026-07-05T11:11:58.239782+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMXYYZ5SZBZ6","created_at":"2026-07-05T11:11:58.239782+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMXYYZ5SZBZ65HZL","created_at":"2026-07-05T11:11:58.239782+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMXYYZ5S","created_at":"2026-07-05T11:11:58.239782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01249","citing_title":"Trust Region On-Policy Distillation","ref_index":298,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMXYYZ5SZBZ65HZLJX6KFUBPFU","json":"https://pith.science/pith/SMXYYZ5SZBZ65HZLJX6KFUBPFU.json","graph_json":"https://pith.science/api/pith-number/SMXYYZ5SZBZ65HZLJX6KFUBPFU/graph.json","events_json":"https://pith.science/api/pith-number/SMXYYZ5SZBZ65HZLJX6KFUBPFU/events.json","paper":"https://pith.science/paper/SMXYYZ5S"},"agent_actions":{"view_html":"https://pith.science/pith/SMXYYZ5SZBZ65HZLJX6KFUBPFU","download_json":"https://pith.science/pith/SMXYYZ5SZBZ65HZLJX6KFUBPFU.json","view_paper":"https://pith.science/paper/SMXYYZ5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23242&json=true","fetch_graph":"https://pith.science/api/pith-number/SMXYYZ5SZBZ65HZLJX6KFUBPFU/graph.json","fetch_events":"https://pith.science/api/pith-number/SMXYYZ5SZBZ65HZLJX6KFUBPFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMXYYZ5SZBZ65HZLJX6KFUBPFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMXYYZ5SZBZ65HZLJX6KFUBPFU/action/storage_attestation","attest_author":"https://pith.science/pith/SMXYYZ5SZBZ65HZLJX6KFUBPFU/action/author_attestation","sign_citation":"https://pith.science/pith/SMXYYZ5SZBZ65HZLJX6KFUBPFU/action/citation_signature","submit_replication":"https://pith.science/pith/SMXYYZ5SZBZ65HZLJX6KFUBPFU/action/replication_record"}},"created_at":"2026-07-05T11:11:58.239782+00:00","updated_at":"2026-07-05T11:11:58.239782+00:00"}