{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7DUADBYCM4A5RD4NJRJSPVCTYI","short_pith_number":"pith:7DUADBYC","schema_version":"1.0","canonical_sha256":"f8e80187026701d88f8d4c5327d453c218549a508f17523b9647f0a6c3e151bd","source":{"kind":"arxiv","id":"2404.09987","version":2},"attestation_state":"computed","paper":{"title":"OneChart: Purify the Chart Structural Extraction via One Auxiliary Token","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenglong Liu, Chunrui Han, Haoran Wei, Jianjian Sun, Jinyue Chen, Liang Zhao, Lingyu Kong, Xiangyu Zhang, Zheng Ge","submitted_at":"2024-04-15T17:58:57Z","abstract_excerpt":"Chart parsing poses a significant challenge due to the diversity of styles, values, texts, and so forth. Even advanced large vision-language models (LVLMs) with billions of parameters struggle to handle such tasks satisfactorily. To address this, we propose OneChart: a reliable agent specifically devised for the structural extraction of chart information. Similar to popular LVLMs, OneChart incorporates an autoregressive main body. Uniquely, to enhance the reliability of the numerical parts of the output, we introduce an auxiliary token placed at the beginning of the total tokens along with an "},"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":"2404.09987","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T17:58:57Z","cross_cats_sorted":[],"title_canon_sha256":"0bca7d3c500e7def6d60f1f7fdffbe62739b982681aaae10fc4f4b4e7be2a39e","abstract_canon_sha256":"781eedc5648afdcce69cce6da556e5fdd96d16b8d84ce65c8bd53121736b90e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:59.156735Z","signature_b64":"4rGrwHcrk/Teqpi6Wsx6dL6Bh2ifDdEBbx2/JhAlVp4l6LnnnNdtgxl+RHU3AJhxRdiH++sErw9wAlOA01/mAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8e80187026701d88f8d4c5327d453c218549a508f17523b9647f0a6c3e151bd","last_reissued_at":"2026-07-05T08:11:59.156257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:59.156257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OneChart: Purify the Chart Structural Extraction via One Auxiliary Token","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenglong Liu, Chunrui Han, Haoran Wei, Jianjian Sun, Jinyue Chen, Liang Zhao, Lingyu Kong, Xiangyu Zhang, Zheng Ge","submitted_at":"2024-04-15T17:58:57Z","abstract_excerpt":"Chart parsing poses a significant challenge due to the diversity of styles, values, texts, and so forth. Even advanced large vision-language models (LVLMs) with billions of parameters struggle to handle such tasks satisfactorily. To address this, we propose OneChart: a reliable agent specifically devised for the structural extraction of chart information. Similar to popular LVLMs, OneChart incorporates an autoregressive main body. Uniquely, to enhance the reliability of the numerical parts of the output, we introduce an auxiliary token placed at the beginning of the total tokens along with an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09987","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/2404.09987/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":"2404.09987","created_at":"2026-07-05T08:11:59.156322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09987v2","created_at":"2026-07-05T08:11:59.156322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09987","created_at":"2026-07-05T08:11:59.156322+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DUADBYCM4A5","created_at":"2026-07-05T08:11:59.156322+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DUADBYCM4A5RD4N","created_at":"2026-07-05T08:11:59.156322+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DUADBYC","created_at":"2026-07-05T08:11:59.156322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27195","citing_title":"EpiCurveBench: Evaluating VLMs on Epidemic Curve Digitization","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2410.21169","citing_title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2409.01704","citing_title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DUADBYCM4A5RD4NJRJSPVCTYI","json":"https://pith.science/pith/7DUADBYCM4A5RD4NJRJSPVCTYI.json","graph_json":"https://pith.science/api/pith-number/7DUADBYCM4A5RD4NJRJSPVCTYI/graph.json","events_json":"https://pith.science/api/pith-number/7DUADBYCM4A5RD4NJRJSPVCTYI/events.json","paper":"https://pith.science/paper/7DUADBYC"},"agent_actions":{"view_html":"https://pith.science/pith/7DUADBYCM4A5RD4NJRJSPVCTYI","download_json":"https://pith.science/pith/7DUADBYCM4A5RD4NJRJSPVCTYI.json","view_paper":"https://pith.science/paper/7DUADBYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09987&json=true","fetch_graph":"https://pith.science/api/pith-number/7DUADBYCM4A5RD4NJRJSPVCTYI/graph.json","fetch_events":"https://pith.science/api/pith-number/7DUADBYCM4A5RD4NJRJSPVCTYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DUADBYCM4A5RD4NJRJSPVCTYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DUADBYCM4A5RD4NJRJSPVCTYI/action/storage_attestation","attest_author":"https://pith.science/pith/7DUADBYCM4A5RD4NJRJSPVCTYI/action/author_attestation","sign_citation":"https://pith.science/pith/7DUADBYCM4A5RD4NJRJSPVCTYI/action/citation_signature","submit_replication":"https://pith.science/pith/7DUADBYCM4A5RD4NJRJSPVCTYI/action/replication_record"}},"created_at":"2026-07-05T08:11:59.156322+00:00","updated_at":"2026-07-05T08:11:59.156322+00:00"}