{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5QHHFX3QSIKZB24BOEONUUKX3B","short_pith_number":"pith:5QHHFX3Q","schema_version":"1.0","canonical_sha256":"ec0e72df70921590eb81711cda5157d87382f4934aed83b6c6ad4d0e1dbb073c","source":{"kind":"arxiv","id":"2412.12150","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Comprehensive Benchmark for Chart Understanding: A Perspective from Scientific Literature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Gaofeng Meng, Kun Ding, Lingdong Shen, Qigqi, Shiming Xiang","submitted_at":"2024-12-11T05:29:54Z","abstract_excerpt":"Scientific Literature charts often contain complex visual elements, including multi-plot figures, flowcharts, structural diagrams and etc. Evaluating multimodal models using these authentic and intricate charts provides a more accurate assessment of their understanding abilities. However, existing benchmarks face limitations: a narrow range of chart types, overly simplistic template-based questions and visual elements, and inadequate evaluation methods. These shortcomings lead to inflated performance scores that fail to hold up when models encounter real-world scientific charts. To address the"},"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":"2412.12150","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T05:29:54Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"0b4735cb84de267958ef37f012a7f7fc058f18f7db41c766994337f6c0ab3842","abstract_canon_sha256":"710260dcbe0a334215933f1c1675f8a190677cb3ad164dc505e506d91daea893"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:37.457410Z","signature_b64":"TOiPn2ujsmzxBp3S8qdJwM9cEjf22xd4zQTeg0v7ZZkKWG0RjANOlOKqt+xVxaTx73EKbLnDAZhmW7UEpii2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec0e72df70921590eb81711cda5157d87382f4934aed83b6c6ad4d0e1dbb073c","last_reissued_at":"2026-07-05T09:50:37.456919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:37.456919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Comprehensive Benchmark for Chart Understanding: A Perspective from Scientific Literature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Gaofeng Meng, Kun Ding, Lingdong Shen, Qigqi, Shiming Xiang","submitted_at":"2024-12-11T05:29:54Z","abstract_excerpt":"Scientific Literature charts often contain complex visual elements, including multi-plot figures, flowcharts, structural diagrams and etc. Evaluating multimodal models using these authentic and intricate charts provides a more accurate assessment of their understanding abilities. However, existing benchmarks face limitations: a narrow range of chart types, overly simplistic template-based questions and visual elements, and inadequate evaluation methods. These shortcomings lead to inflated performance scores that fail to hold up when models encounter real-world scientific charts. To address the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12150","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/2412.12150/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":"2412.12150","created_at":"2026-07-05T09:50:37.456971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12150v1","created_at":"2026-07-05T09:50:37.456971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12150","created_at":"2026-07-05T09:50:37.456971+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QHHFX3QSIKZ","created_at":"2026-07-05T09:50:37.456971+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QHHFX3QSIKZB24B","created_at":"2026-07-05T09:50:37.456971+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QHHFX3Q","created_at":"2026-07-05T09:50:37.456971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01328","citing_title":"LongChart VQA: A Comprehensive Benchmark for MLLMs with Complex Multi-Chart Reasoning","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QHHFX3QSIKZB24BOEONUUKX3B","json":"https://pith.science/pith/5QHHFX3QSIKZB24BOEONUUKX3B.json","graph_json":"https://pith.science/api/pith-number/5QHHFX3QSIKZB24BOEONUUKX3B/graph.json","events_json":"https://pith.science/api/pith-number/5QHHFX3QSIKZB24BOEONUUKX3B/events.json","paper":"https://pith.science/paper/5QHHFX3Q"},"agent_actions":{"view_html":"https://pith.science/pith/5QHHFX3QSIKZB24BOEONUUKX3B","download_json":"https://pith.science/pith/5QHHFX3QSIKZB24BOEONUUKX3B.json","view_paper":"https://pith.science/paper/5QHHFX3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12150&json=true","fetch_graph":"https://pith.science/api/pith-number/5QHHFX3QSIKZB24BOEONUUKX3B/graph.json","fetch_events":"https://pith.science/api/pith-number/5QHHFX3QSIKZB24BOEONUUKX3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QHHFX3QSIKZB24BOEONUUKX3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QHHFX3QSIKZB24BOEONUUKX3B/action/storage_attestation","attest_author":"https://pith.science/pith/5QHHFX3QSIKZB24BOEONUUKX3B/action/author_attestation","sign_citation":"https://pith.science/pith/5QHHFX3QSIKZB24BOEONUUKX3B/action/citation_signature","submit_replication":"https://pith.science/pith/5QHHFX3QSIKZB24BOEONUUKX3B/action/replication_record"}},"created_at":"2026-07-05T09:50:37.456971+00:00","updated_at":"2026-07-05T09:50:37.456971+00:00"}