{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JWEKTDUAGELTDWGGQTGQ2QLFXX","short_pith_number":"pith:JWEKTDUA","schema_version":"1.0","canonical_sha256":"4d88a98e80311731d8c684cd0d4165bdff4024e7c5fa05eee580936db2f947da","source":{"kind":"arxiv","id":"2406.00257","version":2},"attestation_state":"computed","paper":{"title":"Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of LVLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Masry, Enamul Hoque, Md Tahmid Rahman Laskar, Mir Tafseer Nayeem, Mohammed Saidul Islam, Raian Rahman","submitted_at":"2024-06-01T01:43:30Z","abstract_excerpt":"Natural language is a powerful complementary modality of communication for data visualizations, such as bar and line charts. To facilitate chart-based reasoning using natural language, various downstream tasks have been introduced recently such as chart question answering, chart summarization, and fact-checking with charts. These tasks pose a unique challenge, demanding both vision-language reasoning and a nuanced understanding of chart data tables, visual encodings, and natural language prompts. Despite the recent success of Large Language Models (LLMs) across diverse NLP tasks, their abiliti"},"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":"2406.00257","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-01T01:43:30Z","cross_cats_sorted":[],"title_canon_sha256":"f7411138b224e72447f40d95650a405a02c680c0475d8f5d501687848fd6964d","abstract_canon_sha256":"62166bb5b6f6c79879af76abf31cfc8391364cc8b63506d685f6990f4b3b7093"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:33.198185Z","signature_b64":"sIRxjomh+AYVySYF3TrmbDQY8/HvVAI9FXGNyLwifocniqYrBuoqDOPxo7S9mDPzeL1FMahotEb+pinNrnSDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d88a98e80311731d8c684cd0d4165bdff4024e7c5fa05eee580936db2f947da","last_reissued_at":"2026-07-05T09:15:33.197645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:33.197645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of LVLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Masry, Enamul Hoque, Md Tahmid Rahman Laskar, Mir Tafseer Nayeem, Mohammed Saidul Islam, Raian Rahman","submitted_at":"2024-06-01T01:43:30Z","abstract_excerpt":"Natural language is a powerful complementary modality of communication for data visualizations, such as bar and line charts. To facilitate chart-based reasoning using natural language, various downstream tasks have been introduced recently such as chart question answering, chart summarization, and fact-checking with charts. These tasks pose a unique challenge, demanding both vision-language reasoning and a nuanced understanding of chart data tables, visual encodings, and natural language prompts. Despite the recent success of Large Language Models (LLMs) across diverse NLP tasks, their abiliti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00257","kind":"arxiv","version":2},"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/2406.00257/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":"2406.00257","created_at":"2026-07-05T09:15:33.197707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00257v2","created_at":"2026-07-05T09:15:33.197707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00257","created_at":"2026-07-05T09:15:33.197707+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWEKTDUAGELT","created_at":"2026-07-05T09:15:33.197707+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWEKTDUAGELTDWGG","created_at":"2026-07-05T09:15:33.197707+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWEKTDUA","created_at":"2026-07-05T09:15:33.197707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05222","citing_title":"A Multimodal Reasoning Typology for Grounding Chart-Image Coherence in Science Communication","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWEKTDUAGELTDWGGQTGQ2QLFXX","json":"https://pith.science/pith/JWEKTDUAGELTDWGGQTGQ2QLFXX.json","graph_json":"https://pith.science/api/pith-number/JWEKTDUAGELTDWGGQTGQ2QLFXX/graph.json","events_json":"https://pith.science/api/pith-number/JWEKTDUAGELTDWGGQTGQ2QLFXX/events.json","paper":"https://pith.science/paper/JWEKTDUA"},"agent_actions":{"view_html":"https://pith.science/pith/JWEKTDUAGELTDWGGQTGQ2QLFXX","download_json":"https://pith.science/pith/JWEKTDUAGELTDWGGQTGQ2QLFXX.json","view_paper":"https://pith.science/paper/JWEKTDUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00257&json=true","fetch_graph":"https://pith.science/api/pith-number/JWEKTDUAGELTDWGGQTGQ2QLFXX/graph.json","fetch_events":"https://pith.science/api/pith-number/JWEKTDUAGELTDWGGQTGQ2QLFXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWEKTDUAGELTDWGGQTGQ2QLFXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWEKTDUAGELTDWGGQTGQ2QLFXX/action/storage_attestation","attest_author":"https://pith.science/pith/JWEKTDUAGELTDWGGQTGQ2QLFXX/action/author_attestation","sign_citation":"https://pith.science/pith/JWEKTDUAGELTDWGGQTGQ2QLFXX/action/citation_signature","submit_replication":"https://pith.science/pith/JWEKTDUAGELTDWGGQTGQ2QLFXX/action/replication_record"}},"created_at":"2026-07-05T09:15:33.197707+00:00","updated_at":"2026-07-05T09:15:33.197707+00:00"}