{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QOVXOC5XZVYECOIRVBYACP6PHF","short_pith_number":"pith:QOVXOC5X","schema_version":"1.0","canonical_sha256":"83ab770bb7cd70413911a870013fcf39594751f372e04cfe7f786f9614863e06","source":{"kind":"arxiv","id":"2506.21319","version":3},"attestation_state":"computed","paper":{"title":"SimVecVis: A Dataset for Enhancing MLLMs in Visualization Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.HC","authors_text":"Can Liu, Chunlin Da, Xiaoxiao Long, Yong Wang, Yuxiao Yang, Yu Zhang","submitted_at":"2025-06-26T14:35:59Z","abstract_excerpt":"Current multimodal large language models (MLLMs), while effective in natural image understanding, struggle with visualization understanding due to their inability to decode the data-to-visual mapping and extract structured information. To address these challenges, we propose SimVec, a novel simplified vector format that encodes chart elements such as mark type, position, and size. The effectiveness of SimVec is demonstrated by using MLLMs to reconstruct chart information from SimVec formats. Then, we build a new visualization dataset, SimVecVis, to enhance the performance of MLLMs in visualiza"},"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":"2506.21319","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-06-26T14:35:59Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d3b4724d4717969a9cd963edb71bffd9c4290b310b333a3ba2f1208b8c995f1e","abstract_canon_sha256":"b61b5eaa3f99682b7ae7ec058858f5319b1107941aa6f682980b3284e55e62fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:45.435713Z","signature_b64":"0roqR7DfSVf6gFxn7FpSbySnInEC5Dq9wcOXTczzgCGYavF9WGjXiE0h77O7L2YO3TAmexsGOnp+338zpSjrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83ab770bb7cd70413911a870013fcf39594751f372e04cfe7f786f9614863e06","last_reissued_at":"2026-07-05T11:30:45.435191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:45.435191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimVecVis: A Dataset for Enhancing MLLMs in Visualization Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.HC","authors_text":"Can Liu, Chunlin Da, Xiaoxiao Long, Yong Wang, Yuxiao Yang, Yu Zhang","submitted_at":"2025-06-26T14:35:59Z","abstract_excerpt":"Current multimodal large language models (MLLMs), while effective in natural image understanding, struggle with visualization understanding due to their inability to decode the data-to-visual mapping and extract structured information. To address these challenges, we propose SimVec, a novel simplified vector format that encodes chart elements such as mark type, position, and size. The effectiveness of SimVec is demonstrated by using MLLMs to reconstruct chart information from SimVec formats. Then, we build a new visualization dataset, SimVecVis, to enhance the performance of MLLMs in visualiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21319","kind":"arxiv","version":3},"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/2506.21319/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":"2506.21319","created_at":"2026-07-05T11:30:45.435250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21319v3","created_at":"2026-07-05T11:30:45.435250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21319","created_at":"2026-07-05T11:30:45.435250+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOVXOC5XZVYE","created_at":"2026-07-05T11:30:45.435250+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOVXOC5XZVYECOIR","created_at":"2026-07-05T11:30:45.435250+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOVXOC5X","created_at":"2026-07-05T11:30:45.435250+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/QOVXOC5XZVYECOIRVBYACP6PHF","json":"https://pith.science/pith/QOVXOC5XZVYECOIRVBYACP6PHF.json","graph_json":"https://pith.science/api/pith-number/QOVXOC5XZVYECOIRVBYACP6PHF/graph.json","events_json":"https://pith.science/api/pith-number/QOVXOC5XZVYECOIRVBYACP6PHF/events.json","paper":"https://pith.science/paper/QOVXOC5X"},"agent_actions":{"view_html":"https://pith.science/pith/QOVXOC5XZVYECOIRVBYACP6PHF","download_json":"https://pith.science/pith/QOVXOC5XZVYECOIRVBYACP6PHF.json","view_paper":"https://pith.science/paper/QOVXOC5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21319&json=true","fetch_graph":"https://pith.science/api/pith-number/QOVXOC5XZVYECOIRVBYACP6PHF/graph.json","fetch_events":"https://pith.science/api/pith-number/QOVXOC5XZVYECOIRVBYACP6PHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOVXOC5XZVYECOIRVBYACP6PHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOVXOC5XZVYECOIRVBYACP6PHF/action/storage_attestation","attest_author":"https://pith.science/pith/QOVXOC5XZVYECOIRVBYACP6PHF/action/author_attestation","sign_citation":"https://pith.science/pith/QOVXOC5XZVYECOIRVBYACP6PHF/action/citation_signature","submit_replication":"https://pith.science/pith/QOVXOC5XZVYECOIRVBYACP6PHF/action/replication_record"}},"created_at":"2026-07-05T11:30:45.435250+00:00","updated_at":"2026-07-05T11:30:45.435250+00:00"}