{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3TN3MQE3CDIZSLXZ3ZE22KUAWH","short_pith_number":"pith:3TN3MQE3","schema_version":"1.0","canonical_sha256":"dcdbb6409b10d1992ef9de49ad2a80b1caa0595e879be9ef92184d5d9562dc6f","source":{"kind":"arxiv","id":"2407.04172","version":2},"attestation_state":"computed","paper":{"title":"ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Aaryaman Kartha, Aayush Bajaj, Ahmed Masry, Enamul Hoque, Megh Thakkar, Shafiq Joty","submitted_at":"2024-07-04T22:16:40Z","abstract_excerpt":"Given the ubiquity of charts as a data analysis, visualization, and decision-making tool across industries and sciences, there has been a growing interest in developing pre-trained foundation models as well as general purpose instruction-tuned models for chart understanding and reasoning. However, existing methods suffer crucial drawbacks across two critical axes affecting the performance of chart representation models: they are trained on data generated from underlying data tables of the charts, ignoring the visual trends and patterns in chart images, and use weakly aligned vision-language ba"},"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":"2407.04172","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-04T22:16:40Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"d7ebea0dce2cfa9e5d423afa2e10a5325c090be5f7dbb2389a3efc1749b1f0dc","abstract_canon_sha256":"aeecfc9b75c6d72f87af757d93fcc62a1be6bbceb9e635ee937fc7bfe34710c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:18.470762Z","signature_b64":"wqDdsp5IY7pphZhNvP3z4Pq/El832NgC02U0PZpDFC9TYksMl5Rj4YrHFx6sRXJEoPQIbHCtyjpVBywjWNNJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcdbb6409b10d1992ef9de49ad2a80b1caa0595e879be9ef92184d5d9562dc6f","last_reissued_at":"2026-07-05T09:30:18.470240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:18.470240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Aaryaman Kartha, Aayush Bajaj, Ahmed Masry, Enamul Hoque, Megh Thakkar, Shafiq Joty","submitted_at":"2024-07-04T22:16:40Z","abstract_excerpt":"Given the ubiquity of charts as a data analysis, visualization, and decision-making tool across industries and sciences, there has been a growing interest in developing pre-trained foundation models as well as general purpose instruction-tuned models for chart understanding and reasoning. However, existing methods suffer crucial drawbacks across two critical axes affecting the performance of chart representation models: they are trained on data generated from underlying data tables of the charts, ignoring the visual trends and patterns in chart images, and use weakly aligned vision-language ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04172","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/2407.04172/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":"2407.04172","created_at":"2026-07-05T09:30:18.470307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04172v2","created_at":"2026-07-05T09:30:18.470307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04172","created_at":"2026-07-05T09:30:18.470307+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TN3MQE3CDIZ","created_at":"2026-07-05T09:30:18.470307+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TN3MQE3CDIZSLXZ","created_at":"2026-07-05T09:30:18.470307+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TN3MQE3","created_at":"2026-07-05T09:30:18.470307+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01599","citing_title":"TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01831","citing_title":"Routing-Based Continual Learning for Multimodal Large Language Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01882","citing_title":"Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04304","citing_title":"Hierarchical Visual Agent: Managing Contexts in Joint Image-Text Space for Advanced Chart Reasoning","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TN3MQE3CDIZSLXZ3ZE22KUAWH","json":"https://pith.science/pith/3TN3MQE3CDIZSLXZ3ZE22KUAWH.json","graph_json":"https://pith.science/api/pith-number/3TN3MQE3CDIZSLXZ3ZE22KUAWH/graph.json","events_json":"https://pith.science/api/pith-number/3TN3MQE3CDIZSLXZ3ZE22KUAWH/events.json","paper":"https://pith.science/paper/3TN3MQE3"},"agent_actions":{"view_html":"https://pith.science/pith/3TN3MQE3CDIZSLXZ3ZE22KUAWH","download_json":"https://pith.science/pith/3TN3MQE3CDIZSLXZ3ZE22KUAWH.json","view_paper":"https://pith.science/paper/3TN3MQE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04172&json=true","fetch_graph":"https://pith.science/api/pith-number/3TN3MQE3CDIZSLXZ3ZE22KUAWH/graph.json","fetch_events":"https://pith.science/api/pith-number/3TN3MQE3CDIZSLXZ3ZE22KUAWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TN3MQE3CDIZSLXZ3ZE22KUAWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TN3MQE3CDIZSLXZ3ZE22KUAWH/action/storage_attestation","attest_author":"https://pith.science/pith/3TN3MQE3CDIZSLXZ3ZE22KUAWH/action/author_attestation","sign_citation":"https://pith.science/pith/3TN3MQE3CDIZSLXZ3ZE22KUAWH/action/citation_signature","submit_replication":"https://pith.science/pith/3TN3MQE3CDIZSLXZ3ZE22KUAWH/action/replication_record"}},"created_at":"2026-07-05T09:30:18.470307+00:00","updated_at":"2026-07-05T09:30:18.470307+00:00"}