{"id":"https://openalex.org/W7162759712","doi":"https://doi.org/10.2312/evs.20261017","title":"NL2SciVis: A Benchmark for Natural Language to Scientific Visualization","display_name":"NL2SciVis: A Benchmark for Natural Language to Scientific Visualization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7162759712","doi":"https://doi.org/10.2312/evs.20261017"},"language":null,"primary_location":{"id":"doi:10.2312/evs.20261017","is_oa":true,"landing_page_url":"https://doi.org/10.2312/evs.20261017","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2312/evs.20261017","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024102378","display_name":"Manish Mathai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathai, Manish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137350515","display_name":"Mengjiao Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Mengjiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137398143","display_name":"Janet Knowles","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Knowles, Janet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057462145","display_name":"Victor A. Mateevitsi","orcid":"https://orcid.org/0000-0002-6677-7520"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mateevitsi, Victor A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137364354","display_name":"Silvio Rizzi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rizzi, Silvio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015951381","display_name":"Hank Childs","orcid":"https://orcid.org/0000-0001-5816-1892"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Childs, Hank","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58896237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.5109000205993652,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.5109000205993652,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.19480000436306,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.08420000225305557,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.8129000067710876},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6456000208854675},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6233999729156494},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.519599974155426},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.43939998745918274},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3937000036239624},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.3440999984741211},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"Scientific discovery","score":0.32600000500679016}],"concepts":[{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.8129000067710876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871999740600586},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6456000208854675},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6233999729156494},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.519599974155426},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44749999046325684},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4316999912261963},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34950000047683716},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3440999984741211},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C183469790","wikidata":"https://www.wikidata.org/wiki/Q333501","display_name":"Crash","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C59740354","wikidata":"https://www.wikidata.org/wiki/Q2737866","display_name":"Scientific visualization","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2312/evs.20261017","is_oa":true,"landing_page_url":"https://doi.org/10.2312/evs.20261017","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.2312/evs.20261017","is_oa":true,"landing_page_url":"https://doi.org/10.2312/evs.20261017","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scientific":[0],"visualization":[1,70],"(SciVis)":[2],"tools":[3],"enable":[4],"exploration":[5],"of":[6,131],"complex":[7],"scientific":[8,69],"datasets":[9],"but":[10],"present":[11],"a":[12,118],"steep":[13],"learning":[14],"curve,":[15],"creating":[16],"hurdles":[17],"for":[18],"scientists":[19],"by":[20,30],"demanding":[21],"technical":[22],"expertise":[23],"beyond":[24],"their":[25,44],"domain.":[26],"AI":[27],"agents":[28],"powered":[29],"Large":[31],"Language":[32],"Models":[33],"(LLMs)":[34],"have":[35],"the":[36,60,93],"potential":[37],"to":[38],"address":[39,55],"this":[40,56],"issue,":[41],"and":[42,46,90,99,104],"yet":[43],"effectiveness":[45],"reliability":[47],"in":[48,72],"doing":[49],"so":[50],"are":[51],"currently":[52],"unclear.":[53],"To":[54,77],"gap,":[57],"we":[58,81],"introduce":[59],"NL2SciVis":[61],"benchmark":[62],"suite,":[63],"which":[64],"focuses":[65],"on":[66,92],"generating":[67],"atomic":[68],"operations":[71],"ParaView":[73],"via":[74],"Python":[75],"code.":[76],"demonstrate":[78],"its":[79],"utility,":[80],"evaluate":[82],"popular":[83],"LLMs":[84],"(Claude":[85],"Sonnet":[86,115],"4.5,":[87],"GPT-5,":[88],"GPT-4o,":[89],"GPT-OSS-120B)":[91],"suite":[94],"under":[95],"baseline,":[96],"prompt":[97],"modification,":[98],"scaffolding":[100],"conditions,":[101],"checking":[102],"execution":[103,136],"pipeline":[105],"validity":[106],"across":[107],"over":[108],"14,000":[109],"trials.":[110],"Our":[111],"evaluation":[112],"shows":[113],"that":[114],"4.5":[116],"achieves":[117],"96%":[119],"pass":[120],"rate":[121],"while":[122],"three":[123],"GPT-family":[124],"models":[125],"range":[126],"from":[127],"48\u201364%,":[128],"with":[129],"92%":[130],"failures":[132],"occurring":[133],"during":[134],"code":[135],"rather":[137],"than":[138],"task":[139],"misunderstanding.":[140]},"counts_by_year":[],"updated_date":"2026-05-30T06:22:53.267495","created_date":"2026-05-30T00:00:00"}