{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M7K6O6G2GW6XGNOK75FMU4X5GP","short_pith_number":"pith:M7K6O6G2","schema_version":"1.0","canonical_sha256":"67d5e778da35bd7335caff4aca72fd33fbcddb8f1ac3af03ed9ef919a301bcbf","source":{"kind":"arxiv","id":"2606.29808","version":1},"attestation_state":"computed","paper":{"title":"Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Dazhen Deng, Kuilin Peng, Liqi Cheng, Peizhi Ying, Yingcai Wu, Yuan Tian, Yuchen He","submitted_at":"2026-06-29T05:40:35Z","abstract_excerpt":"Chart data extraction, which reverse-engineers data tables from chart images, is essential for reproducibility, analysis, retrieval, and redesign. Existing interactive tools are reliable but tedious, and mixed-initiative systems, while more efficient, lack generalizability. Recent multimodal large language models (MLLMs) offer a unified interface for chart interpretation, yet their ability to extract accurate data tables, especially without visible labels, remains unclear. We build a benchmark featuring diverse real-world charts without data labels to evaluate this capability. Results show tha"},"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":"2606.29808","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2026-06-29T05:40:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c8453f5f85d5046a41c14859ceb961c8707c7483d281295475e56c86133c4d3","abstract_canon_sha256":"61e43ebee4e401db400d140aada50e4517a0f15307248fe66e943ba41b2f5e42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:36.145009Z","signature_b64":"AYgw1ZuvM9RWmFcTUz0JzdS2U75Tj5D9MHUN86vZ8whHCPlMOgb7Ewa7k+rSbR9pE5ZQMmhsuQr6FEBNaFtmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67d5e778da35bd7335caff4aca72fd33fbcddb8f1ac3af03ed9ef919a301bcbf","last_reissued_at":"2026-06-30T02:17:36.144163Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:36.144163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Dazhen Deng, Kuilin Peng, Liqi Cheng, Peizhi Ying, Yingcai Wu, Yuan Tian, Yuchen He","submitted_at":"2026-06-29T05:40:35Z","abstract_excerpt":"Chart data extraction, which reverse-engineers data tables from chart images, is essential for reproducibility, analysis, retrieval, and redesign. Existing interactive tools are reliable but tedious, and mixed-initiative systems, while more efficient, lack generalizability. Recent multimodal large language models (MLLMs) offer a unified interface for chart interpretation, yet their ability to extract accurate data tables, especially without visible labels, remains unclear. We build a benchmark featuring diverse real-world charts without data labels to evaluate this capability. Results show tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29808","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/2606.29808/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":"2606.29808","created_at":"2026-06-30T02:17:36.144275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29808v1","created_at":"2026-06-30T02:17:36.144275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29808","created_at":"2026-06-30T02:17:36.144275+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7K6O6G2GW6X","created_at":"2026-06-30T02:17:36.144275+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7K6O6G2GW6XGNOK","created_at":"2026-06-30T02:17:36.144275+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7K6O6G2","created_at":"2026-06-30T02:17:36.144275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7K6O6G2GW6XGNOK75FMU4X5GP","json":"https://pith.science/pith/M7K6O6G2GW6XGNOK75FMU4X5GP.json","graph_json":"https://pith.science/api/pith-number/M7K6O6G2GW6XGNOK75FMU4X5GP/graph.json","events_json":"https://pith.science/api/pith-number/M7K6O6G2GW6XGNOK75FMU4X5GP/events.json","paper":"https://pith.science/paper/M7K6O6G2"},"agent_actions":{"view_html":"https://pith.science/pith/M7K6O6G2GW6XGNOK75FMU4X5GP","download_json":"https://pith.science/pith/M7K6O6G2GW6XGNOK75FMU4X5GP.json","view_paper":"https://pith.science/paper/M7K6O6G2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29808&json=true","fetch_graph":"https://pith.science/api/pith-number/M7K6O6G2GW6XGNOK75FMU4X5GP/graph.json","fetch_events":"https://pith.science/api/pith-number/M7K6O6G2GW6XGNOK75FMU4X5GP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7K6O6G2GW6XGNOK75FMU4X5GP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7K6O6G2GW6XGNOK75FMU4X5GP/action/storage_attestation","attest_author":"https://pith.science/pith/M7K6O6G2GW6XGNOK75FMU4X5GP/action/author_attestation","sign_citation":"https://pith.science/pith/M7K6O6G2GW6XGNOK75FMU4X5GP/action/citation_signature","submit_replication":"https://pith.science/pith/M7K6O6G2GW6XGNOK75FMU4X5GP/action/replication_record"}},"created_at":"2026-06-30T02:17:36.144275+00:00","updated_at":"2026-06-30T02:17:36.144275+00:00"}