{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IEJG6HMDBMQUUMFZNOWJMTRON7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e76a3378d8c9bc39d49c26b797025e3f6d083634ed18d8de4218449851d1eb09","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-08T17:59:10Z","title_canon_sha256":"e3d14b12184287bf0a9b81b7b151e62ebef1573758e8c4978af363c8582d6578"},"schema_version":"1.0","source":{"id":"2508.06492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06492","created_at":"2026-07-05T11:50:57Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06492v1","created_at":"2026-07-05T11:50:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06492","created_at":"2026-07-05T11:50:57Z"},{"alias_kind":"pith_short_12","alias_value":"IEJG6HMDBMQU","created_at":"2026-07-05T11:50:57Z"},{"alias_kind":"pith_short_16","alias_value":"IEJG6HMDBMQUUMFZ","created_at":"2026-07-05T11:50:57Z"},{"alias_kind":"pith_short_8","alias_value":"IEJG6HMD","created_at":"2026-07-05T11:50:57Z"}],"graph_snapshots":[{"event_id":"sha256:72c45a1825254f796fa2447a234c3c0751616cee470a0c399dff4fb55a21d1ea","target":"graph","created_at":"2026-07-05T11:50:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.06492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language models (MLLMs), especially open-source ones, are still falling behind with a typical success rate of 30%-50% on challenging benchmarks. Previous studies on fine-tuning MLLMs with synthetic charts are often restricted by their inadequate similarity to the real charts, which could compromise model training and performance on complex real-world charts. In this study, we show that modularizing chart generation and diver","authors_text":"Ali Payani, Gaowen Liu, Liang Zheng, Yuan-Sen Ting, Yunzhong Hou, Yuwei Yang, Zeyu Zhang, Zhuowan Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-08T17:59:10Z","title":"Effective Training Data Synthesis for Improving MLLM Chart Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06492","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a2369662f30144aea5d5b0491cfc7b8eee01929cb3c7b7bf19fc0f01ea6e4f46","target":"record","created_at":"2026-07-05T11:50:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e76a3378d8c9bc39d49c26b797025e3f6d083634ed18d8de4218449851d1eb09","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-08T17:59:10Z","title_canon_sha256":"e3d14b12184287bf0a9b81b7b151e62ebef1573758e8c4978af363c8582d6578"},"schema_version":"1.0","source":{"id":"2508.06492","kind":"arxiv","version":1}},"canonical_sha256":"41126f1d830b214a30b96bac964e2e6fc21c373f02cb6fdae263a20d142dbeac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41126f1d830b214a30b96bac964e2e6fc21c373f02cb6fdae263a20d142dbeac","first_computed_at":"2026-07-05T11:50:57.240586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:57.240586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"in+O99MkT6oetRikRsMKvwR8/cWpbOoXML+QHknUv1yFy2gucwTi+l5kvoETYtIPZAlYW0lOyviZqk9Z3T3sCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:57.241078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.06492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2369662f30144aea5d5b0491cfc7b8eee01929cb3c7b7bf19fc0f01ea6e4f46","sha256:72c45a1825254f796fa2447a234c3c0751616cee470a0c399dff4fb55a21d1ea"],"state_sha256":"fbdbf105b2a7340d4298f31dbe9274410b2f4ce6021a3b7e9541d493b100c096"}