{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QX4UWYFMD2GVZ3TKXU6WMCMUYH","short_pith_number":"pith:QX4UWYFM","schema_version":"1.0","canonical_sha256":"85f94b60ac1e8d5cee6abd3d660994c1d970c38ecb95b3058f6507f452107456","source":{"kind":"arxiv","id":"2505.19076","version":1},"attestation_state":"computed","paper":{"title":"ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhi Xu, Han Lai, Jie Ma, Jun Liu, Lingling Zhang, Muye Huang, Wenjun Wu, Yaqiang Wu, Yifei Li","submitted_at":"2025-05-25T10:21:29Z","abstract_excerpt":"Charts are high-density visualization carriers for complex data, serving as a crucial medium for information extraction and analysis. Automated chart understanding poses significant challenges to existing multimodal large language models (MLLMs) due to the need for precise and complex visual reasoning. Current step-by-step reasoning models primarily focus on text-based logical reasoning for chart understanding. However, they struggle to refine or correct their reasoning when errors stem from flawed visual understanding, as they lack the ability to leverage multimodal interaction for deeper com"},"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":"2505.19076","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.CV","submitted_at":"2025-05-25T10:21:29Z","cross_cats_sorted":[],"title_canon_sha256":"a068918226658891868a0eb4be14220846893360024777d6404f2ca52ce53252","abstract_canon_sha256":"6394fbbdd3f59d9983513a8700ba03cee4154774f8491c7043d604786047d46f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T08:42:24.854762Z","signature_b64":"t+FPdXuK283/M9PhDFjHi+G7y949nNvCurYh+PmF+ahGR0ir0gjFGqyHUA4Xy/IFNu1gbVbqlnb1dxuW6G9KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85f94b60ac1e8d5cee6abd3d660994c1d970c38ecb95b3058f6507f452107456","last_reissued_at":"2026-07-02T08:42:24.854236Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T08:42:24.854236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhi Xu, Han Lai, Jie Ma, Jun Liu, Lingling Zhang, Muye Huang, Wenjun Wu, Yaqiang Wu, Yifei Li","submitted_at":"2025-05-25T10:21:29Z","abstract_excerpt":"Charts are high-density visualization carriers for complex data, serving as a crucial medium for information extraction and analysis. Automated chart understanding poses significant challenges to existing multimodal large language models (MLLMs) due to the need for precise and complex visual reasoning. Current step-by-step reasoning models primarily focus on text-based logical reasoning for chart understanding. However, they struggle to refine or correct their reasoning when errors stem from flawed visual understanding, as they lack the ability to leverage multimodal interaction for deeper com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19076","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/2505.19076/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":"2505.19076","created_at":"2026-07-02T08:42:24.854293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19076v1","created_at":"2026-07-02T08:42:24.854293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19076","created_at":"2026-07-02T08:42:24.854293+00:00"},{"alias_kind":"pith_short_12","alias_value":"QX4UWYFMD2GV","created_at":"2026-07-02T08:42:24.854293+00:00"},{"alias_kind":"pith_short_16","alias_value":"QX4UWYFMD2GVZ3TK","created_at":"2026-07-02T08:42:24.854293+00:00"},{"alias_kind":"pith_short_8","alias_value":"QX4UWYFM","created_at":"2026-07-02T08:42:24.854293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00096","citing_title":"Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03157","citing_title":"Chart-RL: Policy Optimization Reinforcement Learning for Enhanced Visual Reasoning in Chart Question Answering with Vision Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01882","citing_title":"Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QX4UWYFMD2GVZ3TKXU6WMCMUYH","json":"https://pith.science/pith/QX4UWYFMD2GVZ3TKXU6WMCMUYH.json","graph_json":"https://pith.science/api/pith-number/QX4UWYFMD2GVZ3TKXU6WMCMUYH/graph.json","events_json":"https://pith.science/api/pith-number/QX4UWYFMD2GVZ3TKXU6WMCMUYH/events.json","paper":"https://pith.science/paper/QX4UWYFM"},"agent_actions":{"view_html":"https://pith.science/pith/QX4UWYFMD2GVZ3TKXU6WMCMUYH","download_json":"https://pith.science/pith/QX4UWYFMD2GVZ3TKXU6WMCMUYH.json","view_paper":"https://pith.science/paper/QX4UWYFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19076&json=true","fetch_graph":"https://pith.science/api/pith-number/QX4UWYFMD2GVZ3TKXU6WMCMUYH/graph.json","fetch_events":"https://pith.science/api/pith-number/QX4UWYFMD2GVZ3TKXU6WMCMUYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QX4UWYFMD2GVZ3TKXU6WMCMUYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QX4UWYFMD2GVZ3TKXU6WMCMUYH/action/storage_attestation","attest_author":"https://pith.science/pith/QX4UWYFMD2GVZ3TKXU6WMCMUYH/action/author_attestation","sign_citation":"https://pith.science/pith/QX4UWYFMD2GVZ3TKXU6WMCMUYH/action/citation_signature","submit_replication":"https://pith.science/pith/QX4UWYFMD2GVZ3TKXU6WMCMUYH/action/replication_record"}},"created_at":"2026-07-02T08:42:24.854293+00:00","updated_at":"2026-07-02T08:42:24.854293+00:00"}