{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:46H2ZY75KOSNWJDAWA2MEYM6KB","short_pith_number":"pith:46H2ZY75","schema_version":"1.0","canonical_sha256":"e78face3fd53a4db2460b034c2619e506be05ada955511a460b619ac96a849b6","source":{"kind":"arxiv","id":"2401.02384","version":3},"attestation_state":"computed","paper":{"title":"ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanqing Meng, Kaipeng Zhang, Peng Gao, Ping Luo, Quanfeng Lu, Wenqi Shao, Yu Qiao","submitted_at":"2024-01-04T17:51:48Z","abstract_excerpt":"Charts play a vital role in data visualization, understanding data patterns, and informed decision-making. However, their unique combination of graphical elements (e.g., bars, lines) and textual components (e.g., labels, legends) poses challenges for general-purpose multimodal models. While vision-language models trained on chart data excel in comprehension, they struggle with generalization. To address these challenges, we propose ChartAssistant, a chart-based vision-language model for universal chart comprehension and reasoning. ChartAssistant leverages ChartSFT, a comprehensive dataset cove"},"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":"2401.02384","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T17:51:48Z","cross_cats_sorted":[],"title_canon_sha256":"8febbb7e522223818d627075067555de54c8e9db8be416326ff41e51efa97dc9","abstract_canon_sha256":"40e2f8ba0f9010780b77bdd5eddc5a6f6dcd0de0963ce55e1679478e92215810"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:32.233358Z","signature_b64":"GO9rYAX6tWN8p9RaN0yIowFdhbd01srATdaUV1bYhPDZg2Qx6FziX+wxF4ybPZcGQQXR7qNvlmmyczXNweC3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e78face3fd53a4db2460b034c2619e506be05ada955511a460b619ac96a849b6","last_reissued_at":"2026-07-05T07:45:32.232832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:32.232832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanqing Meng, Kaipeng Zhang, Peng Gao, Ping Luo, Quanfeng Lu, Wenqi Shao, Yu Qiao","submitted_at":"2024-01-04T17:51:48Z","abstract_excerpt":"Charts play a vital role in data visualization, understanding data patterns, and informed decision-making. However, their unique combination of graphical elements (e.g., bars, lines) and textual components (e.g., labels, legends) poses challenges for general-purpose multimodal models. While vision-language models trained on chart data excel in comprehension, they struggle with generalization. To address these challenges, we propose ChartAssistant, a chart-based vision-language model for universal chart comprehension and reasoning. ChartAssistant leverages ChartSFT, a comprehensive dataset cove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02384","kind":"arxiv","version":3},"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/2401.02384/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":"2401.02384","created_at":"2026-07-05T07:45:32.232894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02384v3","created_at":"2026-07-05T07:45:32.232894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02384","created_at":"2026-07-05T07:45:32.232894+00:00"},{"alias_kind":"pith_short_12","alias_value":"46H2ZY75KOSN","created_at":"2026-07-05T07:45:32.232894+00:00"},{"alias_kind":"pith_short_16","alias_value":"46H2ZY75KOSNWJDA","created_at":"2026-07-05T07:45:32.232894+00:00"},{"alias_kind":"pith_short_8","alias_value":"46H2ZY75","created_at":"2026-07-05T07:45:32.232894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23694","citing_title":"ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models","ref_index":42,"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":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23694","citing_title":"ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models","ref_index":42,"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":24,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13606","citing_title":"ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/46H2ZY75KOSNWJDAWA2MEYM6KB","json":"https://pith.science/pith/46H2ZY75KOSNWJDAWA2MEYM6KB.json","graph_json":"https://pith.science/api/pith-number/46H2ZY75KOSNWJDAWA2MEYM6KB/graph.json","events_json":"https://pith.science/api/pith-number/46H2ZY75KOSNWJDAWA2MEYM6KB/events.json","paper":"https://pith.science/paper/46H2ZY75"},"agent_actions":{"view_html":"https://pith.science/pith/46H2ZY75KOSNWJDAWA2MEYM6KB","download_json":"https://pith.science/pith/46H2ZY75KOSNWJDAWA2MEYM6KB.json","view_paper":"https://pith.science/paper/46H2ZY75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02384&json=true","fetch_graph":"https://pith.science/api/pith-number/46H2ZY75KOSNWJDAWA2MEYM6KB/graph.json","fetch_events":"https://pith.science/api/pith-number/46H2ZY75KOSNWJDAWA2MEYM6KB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46H2ZY75KOSNWJDAWA2MEYM6KB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46H2ZY75KOSNWJDAWA2MEYM6KB/action/storage_attestation","attest_author":"https://pith.science/pith/46H2ZY75KOSNWJDAWA2MEYM6KB/action/author_attestation","sign_citation":"https://pith.science/pith/46H2ZY75KOSNWJDAWA2MEYM6KB/action/citation_signature","submit_replication":"https://pith.science/pith/46H2ZY75KOSNWJDAWA2MEYM6KB/action/replication_record"}},"created_at":"2026-07-05T07:45:32.232894+00:00","updated_at":"2026-07-05T07:45:32.232894+00:00"}