{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6J7AOHSZGEG624ECVRHWSNQFO4","short_pith_number":"pith:6J7AOHSZ","schema_version":"1.0","canonical_sha256":"f27e071e59310ded7082ac4f693605773d45106452ed9ee63be104d92f1431da","source":{"kind":"arxiv","id":"2305.14761","version":3},"attestation_state":"computed","paper":{"title":"UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Masry, Enamul Hoque, Parsa Kavehzadeh, Shafiq Joty, Xuan Long Do","submitted_at":"2023-05-24T06:11:17Z","abstract_excerpt":"Charts are very popular for analyzing data, visualizing key insights and answering complex reasoning questions about data. To facilitate chart-based data analysis using natural language, several downstream tasks have been introduced recently such as chart question answering and chart summarization. However, most of the methods that solve these tasks use pretraining on language or vision-language tasks that do not attempt to explicitly model the structure of the charts (e.g., how data is visually encoded and how chart elements are related to each other). To address this, we first build a large "},"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":"2305.14761","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T06:11:17Z","cross_cats_sorted":[],"title_canon_sha256":"821dbc82c0bb505c1cd4a262ffa9c733dc4043c3671c8503e8f9bbc86b2184dd","abstract_canon_sha256":"b90240a1447dd165632e6a2fc92a321c3a82a1cd7da76308fc6f4c06ebfe6f6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:32.239684Z","signature_b64":"+xKwQ3gz4cfXbl3af8hVsxdLdfmg2uiXQvvv/RQ+KanJCp0IxFftWpJW00ppOzf6UMsMnq14YutSwDtrxf3bAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f27e071e59310ded7082ac4f693605773d45106452ed9ee63be104d92f1431da","last_reissued_at":"2026-07-05T06:59:32.239228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:32.239228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Masry, Enamul Hoque, Parsa Kavehzadeh, Shafiq Joty, Xuan Long Do","submitted_at":"2023-05-24T06:11:17Z","abstract_excerpt":"Charts are very popular for analyzing data, visualizing key insights and answering complex reasoning questions about data. To facilitate chart-based data analysis using natural language, several downstream tasks have been introduced recently such as chart question answering and chart summarization. However, most of the methods that solve these tasks use pretraining on language or vision-language tasks that do not attempt to explicitly model the structure of the charts (e.g., how data is visually encoded and how chart elements are related to each other). To address this, we first build a large "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14761","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/2305.14761/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":"2305.14761","created_at":"2026-07-05T06:59:32.239292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14761v3","created_at":"2026-07-05T06:59:32.239292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14761","created_at":"2026-07-05T06:59:32.239292+00:00"},{"alias_kind":"pith_short_12","alias_value":"6J7AOHSZGEG6","created_at":"2026-07-05T06:59:32.239292+00:00"},{"alias_kind":"pith_short_16","alias_value":"6J7AOHSZGEG624EC","created_at":"2026-07-05T06:59:32.239292+00:00"},{"alias_kind":"pith_short_8","alias_value":"6J7AOHSZ","created_at":"2026-07-05T06:59:32.239292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29808","citing_title":"Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27978","citing_title":"ABot-OCR Technical Report","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2410.14702","citing_title":"Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2409.01704","citing_title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","ref_index":31,"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":21,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24326","citing_title":"Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2403.05525","citing_title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":182,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6J7AOHSZGEG624ECVRHWSNQFO4","json":"https://pith.science/pith/6J7AOHSZGEG624ECVRHWSNQFO4.json","graph_json":"https://pith.science/api/pith-number/6J7AOHSZGEG624ECVRHWSNQFO4/graph.json","events_json":"https://pith.science/api/pith-number/6J7AOHSZGEG624ECVRHWSNQFO4/events.json","paper":"https://pith.science/paper/6J7AOHSZ"},"agent_actions":{"view_html":"https://pith.science/pith/6J7AOHSZGEG624ECVRHWSNQFO4","download_json":"https://pith.science/pith/6J7AOHSZGEG624ECVRHWSNQFO4.json","view_paper":"https://pith.science/paper/6J7AOHSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14761&json=true","fetch_graph":"https://pith.science/api/pith-number/6J7AOHSZGEG624ECVRHWSNQFO4/graph.json","fetch_events":"https://pith.science/api/pith-number/6J7AOHSZGEG624ECVRHWSNQFO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6J7AOHSZGEG624ECVRHWSNQFO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6J7AOHSZGEG624ECVRHWSNQFO4/action/storage_attestation","attest_author":"https://pith.science/pith/6J7AOHSZGEG624ECVRHWSNQFO4/action/author_attestation","sign_citation":"https://pith.science/pith/6J7AOHSZGEG624ECVRHWSNQFO4/action/citation_signature","submit_replication":"https://pith.science/pith/6J7AOHSZGEG624ECVRHWSNQFO4/action/replication_record"}},"created_at":"2026-07-05T06:59:32.239292+00:00","updated_at":"2026-07-05T06:59:32.239292+00:00"}