{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PDP3NWT5BGCY7PKAJYAHJISOHL","short_pith_number":"pith:PDP3NWT5","schema_version":"1.0","canonical_sha256":"78dfb6da7d09858fbd404e0074a24e3ada9e620792022ed5f602b7d6a72336cb","source":{"kind":"arxiv","id":"2502.14864","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Jiang Zhong, Jingpeng Gao, Jingwang Huang, Jingyuan Zhang, KaiWen Wei, Li Jin, Qing Liu, Rui Jiang, Yang Bai, Yuming Yang","submitted_at":"2025-02-20T18:59:42Z","abstract_excerpt":"Multimodal Retrieval-Augmented Generation (MRAG) enhances reasoning capabilities by integrating external knowledge. However, existing benchmarks primarily focus on simple image-text interactions, overlooking complex visual formats like charts that are prevalent in real-world applications. In this work, we introduce a novel task, Chart-based MRAG, to address this limitation. To semi-automatically generate high-quality evaluation samples, we propose CHARt-based document question-answering GEneration (CHARGE), a framework that produces evaluation data through structured keypoint extraction, cross"},"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":"2502.14864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-20T18:59:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c72bfa412b5a519b334353bda9a228192b9b80e2bcacd73ddd45d2b7e7f98087","abstract_canon_sha256":"d30153d18ed3c98f70c45876df8890df923d1612c41da56dd72b7f7c1fd36a31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:33.693927Z","signature_b64":"Inpk+EPo1DdWkBcS9T1l7cDDoCmu5CGV+Trap+HN1svqN5xqY9XeVpzteyK+jTd9i1Vp+ZcVw80/FUC8qStXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78dfb6da7d09858fbd404e0074a24e3ada9e620792022ed5f602b7d6a72336cb","last_reissued_at":"2026-07-05T10:17:33.693418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:33.693418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Jiang Zhong, Jingpeng Gao, Jingwang Huang, Jingyuan Zhang, KaiWen Wei, Li Jin, Qing Liu, Rui Jiang, Yang Bai, Yuming Yang","submitted_at":"2025-02-20T18:59:42Z","abstract_excerpt":"Multimodal Retrieval-Augmented Generation (MRAG) enhances reasoning capabilities by integrating external knowledge. However, existing benchmarks primarily focus on simple image-text interactions, overlooking complex visual formats like charts that are prevalent in real-world applications. In this work, we introduce a novel task, Chart-based MRAG, to address this limitation. To semi-automatically generate high-quality evaluation samples, we propose CHARt-based document question-answering GEneration (CHARGE), a framework that produces evaluation data through structured keypoint extraction, cross"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14864","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/2502.14864/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":"2502.14864","created_at":"2026-07-05T10:17:33.693478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14864v1","created_at":"2026-07-05T10:17:33.693478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14864","created_at":"2026-07-05T10:17:33.693478+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDP3NWT5BGCY","created_at":"2026-07-05T10:17:33.693478+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDP3NWT5BGCY7PKA","created_at":"2026-07-05T10:17:33.693478+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDP3NWT5","created_at":"2026-07-05T10:17:33.693478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDP3NWT5BGCY7PKAJYAHJISOHL","json":"https://pith.science/pith/PDP3NWT5BGCY7PKAJYAHJISOHL.json","graph_json":"https://pith.science/api/pith-number/PDP3NWT5BGCY7PKAJYAHJISOHL/graph.json","events_json":"https://pith.science/api/pith-number/PDP3NWT5BGCY7PKAJYAHJISOHL/events.json","paper":"https://pith.science/paper/PDP3NWT5"},"agent_actions":{"view_html":"https://pith.science/pith/PDP3NWT5BGCY7PKAJYAHJISOHL","download_json":"https://pith.science/pith/PDP3NWT5BGCY7PKAJYAHJISOHL.json","view_paper":"https://pith.science/paper/PDP3NWT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14864&json=true","fetch_graph":"https://pith.science/api/pith-number/PDP3NWT5BGCY7PKAJYAHJISOHL/graph.json","fetch_events":"https://pith.science/api/pith-number/PDP3NWT5BGCY7PKAJYAHJISOHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDP3NWT5BGCY7PKAJYAHJISOHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDP3NWT5BGCY7PKAJYAHJISOHL/action/storage_attestation","attest_author":"https://pith.science/pith/PDP3NWT5BGCY7PKAJYAHJISOHL/action/author_attestation","sign_citation":"https://pith.science/pith/PDP3NWT5BGCY7PKAJYAHJISOHL/action/citation_signature","submit_replication":"https://pith.science/pith/PDP3NWT5BGCY7PKAJYAHJISOHL/action/replication_record"}},"created_at":"2026-07-05T10:17:33.693478+00:00","updated_at":"2026-07-05T10:17:33.693478+00:00"}