{"id":"https://openalex.org/W4414156393","doi":"https://doi.org/10.3390/fi17090412","title":"GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries","display_name":"GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W4414156393","doi":"https://doi.org/10.3390/fi17090412"},"language":"en","primary_location":{"id":"doi:10.3390/fi17090412","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi17090412","pdf_url":"https://www.mdpi.com/1999-5903/17/9/412/pdf?version=1757569386","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-5903/17/9/412/pdf?version=1757569386","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036991749","display_name":"Nuno Fachada","orcid":"https://orcid.org/0000-0002-8487-5837"},"institutions":[{"id":"https://openalex.org/I4210127031","display_name":"Uninova","ror":"https://ror.org/0373te416","country_code":"PT","type":"funder","lineage":["https://openalex.org/I4210127031"]},{"id":"https://openalex.org/I88596544","display_name":"Universidade Lus\u00f3fona","ror":"https://ror.org/05xxfer42","country_code":"PT","type":"education","lineage":["https://openalex.org/I88596544"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Nuno Fachada","raw_affiliation_strings":["Center of Technology and Systems (UNINOVA-CTS) and Associated Lab of Intelligent Systems (LASI), 2829-516 Caparica, Portugal","Copelabs, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-8487-5837","affiliations":[{"raw_affiliation_string":"Center of Technology and Systems (UNINOVA-CTS) and Associated Lab of Intelligent Systems (LASI), 2829-516 Caparica, Portugal","institution_ids":["https://openalex.org/I4210127031"]},{"raw_affiliation_string":"Copelabs, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal","institution_ids":["https://openalex.org/I88596544"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021305920","display_name":"Daniel Fernandes","orcid":"https://orcid.org/0000-0002-1356-9349"},"institutions":[{"id":"https://openalex.org/I88596544","display_name":"Universidade Lus\u00f3fona","ror":"https://ror.org/05xxfer42","country_code":"PT","type":"education","lineage":["https://openalex.org/I88596544"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Daniel Fernandes","raw_affiliation_strings":["Copelabs, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-1356-9349","affiliations":[{"raw_affiliation_string":"Copelabs, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal","institution_ids":["https://openalex.org/I88596544"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048165006","display_name":"Carlos M. Fernandes","orcid":"https://orcid.org/0000-0002-1594-6785"},"institutions":[{"id":"https://openalex.org/I4210127031","display_name":"Uninova","ror":"https://ror.org/0373te416","country_code":"PT","type":"funder","lineage":["https://openalex.org/I4210127031"]},{"id":"https://openalex.org/I88596544","display_name":"Universidade Lus\u00f3fona","ror":"https://ror.org/05xxfer42","country_code":"PT","type":"education","lineage":["https://openalex.org/I88596544"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Carlos M. Fernandes","raw_affiliation_strings":["Center of Technology and Systems (UNINOVA-CTS) and Associated Lab of Intelligent Systems (LASI), 2829-516 Caparica, Portugal","Copelabs, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-1594-6785","affiliations":[{"raw_affiliation_string":"Center of Technology and Systems (UNINOVA-CTS) and Associated Lab of Intelligent Systems (LASI), 2829-516 Caparica, Portugal","institution_ids":["https://openalex.org/I4210127031"]},{"raw_affiliation_string":"Copelabs, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal","institution_ids":["https://openalex.org/I88596544"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092252083","display_name":"Bruno D. Ferreira-Saraiva","orcid":"https://orcid.org/0000-0001-8839-7222"},"institutions":[{"id":"https://openalex.org/I88596544","display_name":"Universidade Lus\u00f3fona","ror":"https://ror.org/05xxfer42","country_code":"PT","type":"education","lineage":["https://openalex.org/I88596544"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Bruno D. Ferreira-Saraiva","raw_affiliation_strings":["CICANT, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal","Copelabs, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-8839-7222","affiliations":[{"raw_affiliation_string":"CICANT, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal","institution_ids":["https://openalex.org/I88596544"]},{"raw_affiliation_string":"Copelabs, Lus\u00f3fona University, Campo Grande, 376, 1749-024 Lisboa, Portugal","institution_ids":["https://openalex.org/I88596544"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087112775","display_name":"Jo\u00e3o P. Matos-Carvalho","orcid":"https://orcid.org/0000-0001-9409-7736"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]},{"id":"https://openalex.org/I4210127031","display_name":"Uninova","ror":"https://ror.org/0373te416","country_code":"PT","type":"funder","lineage":["https://openalex.org/I4210127031"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o P. Matos-Carvalho","raw_affiliation_strings":["Center of Technology and Systems (UNINOVA-CTS) and Associated Lab of Intelligent Systems (LASI), 2829-516 Caparica, Portugal","LASIGE and Departamento de Inform\u00e1tica, Faculdade de Ci\u00eancias, University of Lisbon, Campo Grande, 1749-016 Lisboa, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-9409-7736","affiliations":[{"raw_affiliation_string":"Center of Technology and Systems (UNINOVA-CTS) and Associated Lab of Intelligent Systems (LASI), 2829-516 Caparica, Portugal","institution_ids":["https://openalex.org/I4210127031"]},{"raw_affiliation_string":"LASIGE and Departamento de Inform\u00e1tica, Faculdade de Ci\u00eancias, University of Lisbon, Campo Grande, 1749-016 Lisboa, Portugal","institution_ids":["https://openalex.org/I141596103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036991749"],"corresponding_institution_ids":["https://openalex.org/I4210127031","https://openalex.org/I88596544"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":8.6844,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.97506305,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"17","issue":"9","first_page":"412","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer 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":0.9850000143051147,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.8511000275611877},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.8108000159263611},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6341999769210815},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.60589998960495},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.566100001335144},{"id":"https://openalex.org/keywords/interpreter","display_name":"Interpreter","score":0.4828999936580658},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4609000086784363},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4147999882698059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8860999941825867},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8511000275611877},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.8108000159263611},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6978999972343445},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6341999769210815},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.60589998960495},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4672999978065491},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4609000086784363},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C92966194","wikidata":"https://www.wikidata.org/wiki/Q651794","display_name":"Compiled language","level":4,"score":0.2953999936580658},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C81587897","wikidata":"https://www.wikidata.org/wiki/Q181702","display_name":"Software documentation","level":5,"score":0.25679999589920044},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.25209999084472656},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3390/fi17090412","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi17090412","pdf_url":"https://www.mdpi.com/1999-5903/17/9/412/pdf?version=1757569386","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2508.00033","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00033","pdf_url":"https://arxiv.org/pdf/2508.00033","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:0b7290b02eba46929e6de40288c33a7e","is_oa":true,"landing_page_url":"https://doaj.org/article/0b7290b02eba46929e6de40288c33a7e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet, Vol 17, Iss 9, p 412 (2025)","raw_type":"article"},{"id":"pmh:oai:recil.ulusofona.pt:10437/15547","is_oa":true,"landing_page_url":"http://hdl.handle.net/10437/15547","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"},{"id":"pmh:oai:recil.ulusofona.pt:10437/15547","is_oa":true,"landing_page_url":"https://hdl.handle.net/10437/15547","pdf_url":null,"source":{"id":"https://openalex.org/S7407055201","display_name":"Lusophone University Repository","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:run.unl.pt:10362/200379","is_oa":true,"landing_page_url":"http://hdl.handle.net/10362/200379","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.3390/fi17090412","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi17090412","pdf_url":"https://www.mdpi.com/1999-5903/17/9/412/pdf?version=1757569386","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1927536394","display_name":"LASIGE Computer Science and Engineering Research Centre","funder_award_id":"UID/00408/2025","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G2089664753","display_name":"LASIGE - Extreme Computing","funder_award_id":"UIDB/00408/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3080209416","display_name":"Centre of Technology and Systems","funder_award_id":"UIDB/00066/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3945898234","display_name":"Not Available","funder_award_id":"CEECINST/00002/2021/CP2788/CT0001","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G6120445142","display_name":"COPELABS - Cognitive and People-centric Computing R","funder_award_id":"UIDB/04111/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414156393.pdf","grobid_xml":"https://content.openalex.org/works/W4414156393.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1964962870","https://openalex.org/W1972978214","https://openalex.org/W2110065044","https://openalex.org/W2282610808","https://openalex.org/W2290195878","https://openalex.org/W2311305321","https://openalex.org/W2963389090","https://openalex.org/W2997591727","https://openalex.org/W3003257820","https://openalex.org/W3035965352","https://openalex.org/W3099878876","https://openalex.org/W4284676027","https://openalex.org/W4383097638","https://openalex.org/W4385231624","https://openalex.org/W4388800948","https://openalex.org/W4389523833","https://openalex.org/W4394828156","https://openalex.org/W4399863911","https://openalex.org/W4403007658","https://openalex.org/W4404783497","https://openalex.org/W4408994067","https://openalex.org/W4409110242","https://openalex.org/W4409415146","https://openalex.org/W4411552560","https://openalex.org/W4412887940"],"related_works":["https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W3116064965","https://openalex.org/W4287027380","https://openalex.org/W3193760048","https://openalex.org/W2207495067","https://openalex.org/W1906486629"],"abstract_inverted_index":{"Large":[0],"language":[1,203],"models":[2,115,137],"(LLMs)":[3],"have":[4],"advanced":[5],"rapidly":[6],"as":[7,169],"tools":[8],"for":[9,26,47,87,184,192],"automating":[10],"code":[11,46,104],"generation":[12,62],"in":[13,42,130,139,165,202],"scientific":[14,186],"research,":[15],"yet":[16],"their":[17],"ability":[18],"to":[19,156],"interpret":[20],"and":[21,59,63,67,90,96,149,188,199],"use":[22,71],"unfamiliar":[23],"Python":[24,45],"APIs":[25],"complex":[27],"computational":[28],"experiments":[29,70],"remains":[30],"poorly":[31],"characterized.":[32],"This":[33],"study":[34],"systematically":[35],"benchmarks":[36],"a":[37,111,123],"selection":[38],"of":[39,114,143,182],"state-of-the-art":[40],"LLMs":[41,183],"generating":[43],"functional":[44,88],"two":[48],"increasingly":[49],"challenging":[50],"scenarios:":[51],"conversational":[52],"data":[53,61],"analysis":[54],"with":[55,146],"the":[56,100,144,190],"ParShift":[57],"library,":[58],"synthetic":[60],"clustering":[64],"using":[65],"pyclugen":[66],"scikit-learn.":[68],"Both":[69],"structured,":[72],"zero-shot":[73],"prompts":[74],"specifying":[75],"detailed":[76],"requirements":[77],"but":[78],"omitting":[79],"in-context":[80],"examples.":[81],"Model":[82],"outputs":[83],"are":[84],"evaluated":[85],"quantitatively":[86],"correctness":[89],"prompt":[91,194],"compliance":[92],"over":[93],"multiple":[94],"runs,":[95,145],"qualitatively":[97],"by":[98],"analyzing":[99],"errors":[101],"produced":[102],"when":[103],"execution":[105],"fails.":[106],"Results":[107],"show":[108],"that":[109],"only":[110,147],"small":[112],"subset":[113],"consistently":[116],"generate":[117],"correct,":[118],"executable":[119],"code.":[120],"GPT-4.1":[121],"achieved":[122],"100%":[124],"success":[125],"rate":[126],"across":[127],"all":[128],"runs":[129],"both":[131],"experimental":[132],"tasks,":[133],"whereas":[134],"most":[135],"other":[136],"succeeded":[138],"fewer":[140],"than":[141],"half":[142],"Grok-3":[148],"Mistral-Large":[150],"approaching":[151],"comparable":[152],"performance.":[153],"In":[154],"addition":[155],"benchmarking":[157],"LLM":[158],"performance,":[159],"this":[160],"approach":[161],"helps":[162],"identify":[163],"shortcomings":[164],"third-party":[166],"libraries,":[167],"such":[168],"unclear":[170],"documentation":[171],"or":[172],"obscure":[173],"implementation":[174],"bugs.":[175],"Overall,":[176],"these":[177],"findings":[178],"highlight":[179],"current":[180],"limitations":[181],"end-to-end":[185],"automation":[187],"emphasize":[189],"need":[191],"careful":[193],"design,":[195],"comprehensive":[196],"library":[197],"documentation,":[198],"continued":[200],"advances":[201],"model":[204],"capabilities.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":6}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-09-12T00:00:00"}
