{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PDTMQVXMXAMRMCIRYF2XJR5HDR","short_pith_number":"pith:PDTMQVXM","schema_version":"1.0","canonical_sha256":"78e6c856ecb819160911c17574c7a71c60f3c53028e7161f87c8d61c9a76237b","source":{"kind":"arxiv","id":"2112.12926","version":1},"attestation_state":"computed","paper":{"title":"nvBench: A Large-Scale Synthesized Dataset for Cross-Domain Natural Language to Visualization Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Guoliang Li, Jiawei Tang, Yuyu Luo","submitted_at":"2021-12-24T03:33:20Z","abstract_excerpt":"NL2VIS - which translates natural language (NL) queries to corresponding visualizations (VIS) - has attracted more and more attention both in commercial visualization vendors and academic researchers. In the last few years, the advanced deep learning-based models have achieved human-like abilities in many natural language processing (NLP) tasks, which clearly tells us that the deep learning-based technique is a good choice to push the field of NL2VIS. However, a big balk is the lack of benchmarks with lots of (NL, VIS) pairs. We present nvBench, the first large-scale NL2VIS benchmark, containi"},"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":"2112.12926","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2021-12-24T03:33:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d15a08a15302ea9074494b3734b9b4447ad8a3ee8d1180f1bdbd34d010c8a2b","abstract_canon_sha256":"43106dd67d06901be0499f4b148282e5c3aedf37788f34e1cb662767c2369c21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:48.270090Z","signature_b64":"iPSktpQQRJRoUJmMeHA/jzvzr9KhuEZkp9xM9Xp0bx21+IilIWA3qN7I5FVbazR1vEl+T80+Lg6hD3NQhM5/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78e6c856ecb819160911c17574c7a71c60f3c53028e7161f87c8d61c9a76237b","last_reissued_at":"2026-07-05T03:43:48.269710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:48.269710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"nvBench: A Large-Scale Synthesized Dataset for Cross-Domain Natural Language to Visualization Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Guoliang Li, Jiawei Tang, Yuyu Luo","submitted_at":"2021-12-24T03:33:20Z","abstract_excerpt":"NL2VIS - which translates natural language (NL) queries to corresponding visualizations (VIS) - has attracted more and more attention both in commercial visualization vendors and academic researchers. In the last few years, the advanced deep learning-based models have achieved human-like abilities in many natural language processing (NLP) tasks, which clearly tells us that the deep learning-based technique is a good choice to push the field of NL2VIS. However, a big balk is the lack of benchmarks with lots of (NL, VIS) pairs. We present nvBench, the first large-scale NL2VIS benchmark, containi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12926","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/2112.12926/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":"2112.12926","created_at":"2026-07-05T03:43:48.269765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.12926v1","created_at":"2026-07-05T03:43:48.269765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12926","created_at":"2026-07-05T03:43:48.269765+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDTMQVXMXAMR","created_at":"2026-07-05T03:43:48.269765+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDTMQVXMXAMRMCIR","created_at":"2026-07-05T03:43:48.269765+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDTMQVXM","created_at":"2026-07-05T03:43:48.269765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15932","citing_title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29808","citing_title":"Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2512.19173","citing_title":"CycleChart: A Unified Consistency-Based Learning Framework for Bidirectional Chart Understanding and Generation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDTMQVXMXAMRMCIRYF2XJR5HDR","json":"https://pith.science/pith/PDTMQVXMXAMRMCIRYF2XJR5HDR.json","graph_json":"https://pith.science/api/pith-number/PDTMQVXMXAMRMCIRYF2XJR5HDR/graph.json","events_json":"https://pith.science/api/pith-number/PDTMQVXMXAMRMCIRYF2XJR5HDR/events.json","paper":"https://pith.science/paper/PDTMQVXM"},"agent_actions":{"view_html":"https://pith.science/pith/PDTMQVXMXAMRMCIRYF2XJR5HDR","download_json":"https://pith.science/pith/PDTMQVXMXAMRMCIRYF2XJR5HDR.json","view_paper":"https://pith.science/paper/PDTMQVXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.12926&json=true","fetch_graph":"https://pith.science/api/pith-number/PDTMQVXMXAMRMCIRYF2XJR5HDR/graph.json","fetch_events":"https://pith.science/api/pith-number/PDTMQVXMXAMRMCIRYF2XJR5HDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDTMQVXMXAMRMCIRYF2XJR5HDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDTMQVXMXAMRMCIRYF2XJR5HDR/action/storage_attestation","attest_author":"https://pith.science/pith/PDTMQVXMXAMRMCIRYF2XJR5HDR/action/author_attestation","sign_citation":"https://pith.science/pith/PDTMQVXMXAMRMCIRYF2XJR5HDR/action/citation_signature","submit_replication":"https://pith.science/pith/PDTMQVXMXAMRMCIRYF2XJR5HDR/action/replication_record"}},"created_at":"2026-07-05T03:43:48.269765+00:00","updated_at":"2026-07-05T03:43:48.269765+00:00"}