{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BRI72GWEFZ3L4FOI4GZSRHGIJM","short_pith_number":"pith:BRI72GWE","schema_version":"1.0","canonical_sha256":"0c51fd1ac42e76be15c8e1b3289cc84b1d302851ad56486e099148cd2584d4b7","source":{"kind":"arxiv","id":"2403.09028","version":1},"attestation_state":"computed","paper":{"title":"ChartInstruct: Instruction Tuning 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, Md Rizwan Parvez, Mehrad Shahmohammadi, Shafiq Joty","submitted_at":"2024-03-14T01:40:23Z","abstract_excerpt":"Charts provide visual representations of data and are widely used for analyzing information, addressing queries, and conveying insights to others. Various chart-related downstream tasks have emerged recently, such as question-answering and summarization. A common strategy to solve these tasks is to fine-tune various models originally trained on vision tasks language. However, such task-specific models are not capable of solving a wide range of chart-related tasks, constraining their real-world applicability. To overcome these challenges, we introduce ChartInstruct: a novel chart-specific visio"},"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":"2403.09028","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T01:40:23Z","cross_cats_sorted":[],"title_canon_sha256":"ee7499c325846c40466d3f05fbed667c7ffdf2d5cf54d6bacc0f7fd0b7bea120","abstract_canon_sha256":"b0120d80132a728e75b6e66a1093f84306789b2d96baecc3b0e7168c49f11f62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:50.804832Z","signature_b64":"LvW3FgY3bDqymgugBDP60hV2GK9+dyATXzQF9CNcJE6ps4xqoBUM1lzwYLcNsdERRyR5w+lVyp15lJaUcS4xBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c51fd1ac42e76be15c8e1b3289cc84b1d302851ad56486e099148cd2584d4b7","last_reissued_at":"2026-07-05T07:55:50.804355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:50.804355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChartInstruct: Instruction Tuning 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, Md Rizwan Parvez, Mehrad Shahmohammadi, Shafiq Joty","submitted_at":"2024-03-14T01:40:23Z","abstract_excerpt":"Charts provide visual representations of data and are widely used for analyzing information, addressing queries, and conveying insights to others. Various chart-related downstream tasks have emerged recently, such as question-answering and summarization. A common strategy to solve these tasks is to fine-tune various models originally trained on vision tasks language. However, such task-specific models are not capable of solving a wide range of chart-related tasks, constraining their real-world applicability. To overcome these challenges, we introduce ChartInstruct: a novel chart-specific visio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09028","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/2403.09028/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":"2403.09028","created_at":"2026-07-05T07:55:50.804416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09028v1","created_at":"2026-07-05T07:55:50.804416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09028","created_at":"2026-07-05T07:55:50.804416+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRI72GWEFZ3L","created_at":"2026-07-05T07:55:50.804416+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRI72GWEFZ3L4FOI","created_at":"2026-07-05T07:55:50.804416+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRI72GWE","created_at":"2026-07-05T07:55:50.804416+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.19173","citing_title":"CycleChart: A Unified Consistency-Based Learning Framework for Bidirectional Chart Understanding and Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13606","citing_title":"ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRI72GWEFZ3L4FOI4GZSRHGIJM","json":"https://pith.science/pith/BRI72GWEFZ3L4FOI4GZSRHGIJM.json","graph_json":"https://pith.science/api/pith-number/BRI72GWEFZ3L4FOI4GZSRHGIJM/graph.json","events_json":"https://pith.science/api/pith-number/BRI72GWEFZ3L4FOI4GZSRHGIJM/events.json","paper":"https://pith.science/paper/BRI72GWE"},"agent_actions":{"view_html":"https://pith.science/pith/BRI72GWEFZ3L4FOI4GZSRHGIJM","download_json":"https://pith.science/pith/BRI72GWEFZ3L4FOI4GZSRHGIJM.json","view_paper":"https://pith.science/paper/BRI72GWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09028&json=true","fetch_graph":"https://pith.science/api/pith-number/BRI72GWEFZ3L4FOI4GZSRHGIJM/graph.json","fetch_events":"https://pith.science/api/pith-number/BRI72GWEFZ3L4FOI4GZSRHGIJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRI72GWEFZ3L4FOI4GZSRHGIJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRI72GWEFZ3L4FOI4GZSRHGIJM/action/storage_attestation","attest_author":"https://pith.science/pith/BRI72GWEFZ3L4FOI4GZSRHGIJM/action/author_attestation","sign_citation":"https://pith.science/pith/BRI72GWEFZ3L4FOI4GZSRHGIJM/action/citation_signature","submit_replication":"https://pith.science/pith/BRI72GWEFZ3L4FOI4GZSRHGIJM/action/replication_record"}},"created_at":"2026-07-05T07:55:50.804416+00:00","updated_at":"2026-07-05T07:55:50.804416+00:00"}