{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VXR7U2U2QRKWY4GC3QJW3F5FCK","short_pith_number":"pith:VXR7U2U2","schema_version":"1.0","canonical_sha256":"ade3fa6a9a84556c70c2dc136d97a512bf0c9f83502e7f2648cf2946231b6038","source":{"kind":"arxiv","id":"2409.01577","version":2},"attestation_state":"computed","paper":{"title":"EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Lai, Jie Ma, Jun Liu, Lingling Zhang, Muye Huang, Wenjun Wu, Xinyu Zhang","submitted_at":"2024-09-03T03:23:00Z","abstract_excerpt":"Chart understanding enables automated data analysis for humans, which requires models to achieve highly accurate visual comprehension. While existing Visual Language Models (VLMs) have shown progress in chart understanding, the lack of high-quality training data and comprehensive evaluation benchmarks hinders VLM chart comprehension. In this paper, we introduce EvoChart, a novel self-training method for generating synthetic chart data to enhance VLMs' capabilities in real-world chart comprehension. We also propose EvoChart-QA, a noval benchmark for measuring models' chart comprehension 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":"2409.01577","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T03:23:00Z","cross_cats_sorted":[],"title_canon_sha256":"669a8b0d374efd1161363f2a910a6091913e4c8826d99cd5e6726c6b495d2a6d","abstract_canon_sha256":"55e30eb13e88f312c9786256d98898e814d6500f5f7cd63349e0cc91de0a82f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:51.900010Z","signature_b64":"tXSg+/+oo4Vk1sMY5wszLh5hBegs0Ku7df/goudEoHWneIDUhjstfhAco4xb2BppV+ToiZQ2+oMGB3vcWB4WBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ade3fa6a9a84556c70c2dc136d97a512bf0c9f83502e7f2648cf2946231b6038","last_reissued_at":"2026-07-05T09:59:51.899562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:51.899562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Lai, Jie Ma, Jun Liu, Lingling Zhang, Muye Huang, Wenjun Wu, Xinyu Zhang","submitted_at":"2024-09-03T03:23:00Z","abstract_excerpt":"Chart understanding enables automated data analysis for humans, which requires models to achieve highly accurate visual comprehension. While existing Visual Language Models (VLMs) have shown progress in chart understanding, the lack of high-quality training data and comprehensive evaluation benchmarks hinders VLM chart comprehension. In this paper, we introduce EvoChart, a novel self-training method for generating synthetic chart data to enhance VLMs' capabilities in real-world chart comprehension. We also propose EvoChart-QA, a noval benchmark for measuring models' chart comprehension abiliti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01577","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/2409.01577/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":"2409.01577","created_at":"2026-07-05T09:59:51.899613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01577v2","created_at":"2026-07-05T09:59:51.899613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01577","created_at":"2026-07-05T09:59:51.899613+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXR7U2U2QRKW","created_at":"2026-07-05T09:59:51.899613+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXR7U2U2QRKWY4GC","created_at":"2026-07-05T09:59:51.899613+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXR7U2U2","created_at":"2026-07-05T09:59:51.899613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18216","citing_title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13606","citing_title":"ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXR7U2U2QRKWY4GC3QJW3F5FCK","json":"https://pith.science/pith/VXR7U2U2QRKWY4GC3QJW3F5FCK.json","graph_json":"https://pith.science/api/pith-number/VXR7U2U2QRKWY4GC3QJW3F5FCK/graph.json","events_json":"https://pith.science/api/pith-number/VXR7U2U2QRKWY4GC3QJW3F5FCK/events.json","paper":"https://pith.science/paper/VXR7U2U2"},"agent_actions":{"view_html":"https://pith.science/pith/VXR7U2U2QRKWY4GC3QJW3F5FCK","download_json":"https://pith.science/pith/VXR7U2U2QRKWY4GC3QJW3F5FCK.json","view_paper":"https://pith.science/paper/VXR7U2U2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01577&json=true","fetch_graph":"https://pith.science/api/pith-number/VXR7U2U2QRKWY4GC3QJW3F5FCK/graph.json","fetch_events":"https://pith.science/api/pith-number/VXR7U2U2QRKWY4GC3QJW3F5FCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXR7U2U2QRKWY4GC3QJW3F5FCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXR7U2U2QRKWY4GC3QJW3F5FCK/action/storage_attestation","attest_author":"https://pith.science/pith/VXR7U2U2QRKWY4GC3QJW3F5FCK/action/author_attestation","sign_citation":"https://pith.science/pith/VXR7U2U2QRKWY4GC3QJW3F5FCK/action/citation_signature","submit_replication":"https://pith.science/pith/VXR7U2U2QRKWY4GC3QJW3F5FCK/action/replication_record"}},"created_at":"2026-07-05T09:59:51.899613+00:00","updated_at":"2026-07-05T09:59:51.899613+00:00"}