{"id":"https://openalex.org/W4416554267","doi":"https://doi.org/10.48550/arxiv.2511.16366","title":"From Patents to Dataset: Scraping for Oxide Glass Compositions and Properties","display_name":"From Patents to Dataset: Scraping for Oxide Glass Compositions and Properties","publication_year":2025,"publication_date":"2025-11-20","ids":{"openalex":"https://openalex.org/W4416554267","doi":"https://doi.org/10.48550/arxiv.2511.16366"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2511.16366","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.16366","pdf_url":"https://arxiv.org/pdf/2511.16366","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.16366","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120467817","display_name":"Gustavo Laranja Thomaello","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Thomaello, Gustavo Laranja","raw_affiliation_strings":["Department of Chemical Engineering , Federal University of S\u00e3o Carlos , S\u00e3o Carlos , S\u00e3o Paulo , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering , Federal University of S\u00e3o Carlos , S\u00e3o Carlos , S\u00e3o Paulo , Brazil","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120374105","display_name":"Thomaz Yeiden Busnardo Aguena","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aguena, Thomaz Yeiden Busnardo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120513957","display_name":"Eric Trevelato Costa","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Costa, Eric Trevelato","raw_affiliation_strings":["Department of Statistics , Federal University of S\u00e3o Carlos , S\u00e3o Carlos , S\u00e3o Paulo , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics , Federal University of S\u00e3o Carlos , S\u00e3o Carlos , S\u00e3o Paulo , Brazil","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120421732","display_name":"Rafael Bas\u00e1glia Rosante","orcid":"https://orcid.org/0009-0004-4589-6186","observed_orcids":["https://orcid.org/0009-0004-4589-6186"]},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rosante, Rafael Bas\u00e1glia","raw_affiliation_strings":["Department of Materials Engineering , Federal University of S\u00e3o Carlos , S\u00e3o Carlos , S\u00e3o Paulo , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Materials Engineering , Federal University of S\u00e3o Carlos , S\u00e3o Carlos , S\u00e3o Paulo , Brazil","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ramos, Thiago Rodrigo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ramos, Thiago Rodrigo","raw_affiliation_strings":["Department of Statistics , Federal University of S\u00e3o Carlos , S\u00e3o Carlos , S\u00e3o Paulo , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics , Federal University of S\u00e3o Carlos , S\u00e3o Carlos , S\u00e3o Paulo , Brazil","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061860646","display_name":"Daiane Aparecida Zuanetti","orcid":"https://orcid.org/0000-0003-1591-959X","observed_orcids":["https://orcid.org/0000-0003-1591-959X"]},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Zuanetti, Daiane Aparecida","raw_affiliation_strings":["Department of Statistics , Federal University of S\u00e3o Carlos , S\u00e3o Carlos , S\u00e3o Paulo , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics , Federal University of S\u00e3o Carlos , S\u00e3o Carlos , S\u00e3o Paulo , Brazil","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077075644","display_name":"Edgar Dutra Zanotto","orcid":"https://orcid.org/0000-0003-4931-4505","observed_orcids":["https://orcid.org/0000-0003-4931-4505"]},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Zanotto, Edgar Dutra","raw_affiliation_strings":["Department of Materials Engineering , Federal University of S\u00e3o Carlos , S\u00e3o Carlos , S\u00e3o Paulo , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Materials Engineering , Federal University of S\u00e3o Carlos , S\u00e3o Carlos , S\u00e3o Paulo , Brazil","institution_ids":["https://openalex.org/I177909021"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"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":0.9965999722480774,"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":0.9965999722480774,"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/T10544","display_name":"Glass properties and applications","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/2503","display_name":"Ceramics and Composites"},"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/T11212","display_name":"Cultural Heritage Materials Analysis","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1204","display_name":"Archeology (arts and humanities)"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/glass-properties","display_name":"glass properties","score":0.6290000081062317},{"id":"https://openalex.org/keywords/patent-data","display_name":"patent information","score":0.5350000262260437},{"id":"https://openalex.org/keywords/web-scraping","display_name":"web scraping","score":0.9929999709129333},{"id":"https://openalex.org/keywords/liquidus-temperature","display_name":"liquidus temperature","score":0.9860000014305115},{"id":"https://openalex.org/keywords/refractive-index","display_name":"refractive index","score":1.0},{"id":"https://openalex.org/keywords/abbe-number","display_name":"Abbe number","score":1.0},{"id":"https://openalex.org/keywords/glass-design","display_name":"glass design","score":0.6439999938011169}],"concepts":[{"id":"https://openalex.org/C145653223","wikidata":"https://www.wikidata.org/wiki/Q899386","display_name":"Liquidus","level":3,"score":0.8779000043869019},{"id":"https://openalex.org/C531131001","wikidata":"https://www.wikidata.org/wiki/Q941","display_name":"Yttrium","level":3,"score":0.5900999903678894},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5437999963760376},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C2779851234","wikidata":"https://www.wikidata.org/wiki/Q50690","display_name":"Oxide","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4429999887943268},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.435699999332428},{"id":"https://openalex.org/C199289684","wikidata":"https://www.wikidata.org/wiki/Q83353","display_name":"Mineralogy","level":1,"score":0.38119998574256897},{"id":"https://openalex.org/C42067758","wikidata":"https://www.wikidata.org/wiki/Q174102","display_name":"Refractive index","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C2781147490","wikidata":"https://www.wikidata.org/wiki/Q5156808","display_name":"Compositional data","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.3228999972343445},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3003000020980835},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C2994228675","wikidata":"https://www.wikidata.org/wiki/Q512599","display_name":"Property value","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.16366","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.16366","pdf_url":"https://arxiv.org/pdf/2511.16366","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.16366","doi":"https://doi.org/10.48550/arxiv.2511.16366","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.16366","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.16366","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.16366","pdf_url":"https://arxiv.org/pdf/2511.16366","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416554267.pdf","grobid_xml":"https://content.openalex.org/works/W4416554267.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4385571746","https://openalex.org/W4414597361"],"related_works":["https://openalex.org/W3083574719","https://openalex.org/W4410331378","https://openalex.org/W3160734749","https://openalex.org/W3046593251","https://openalex.org/W3206163778","https://openalex.org/W4411466319","https://openalex.org/W3015646671","https://openalex.org/W3112725209","https://openalex.org/W3170956459","https://openalex.org/W4407220306"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"present":[4],"web":[5],"scraping":[6],"techniques":[7],"to":[8,27,38,50,73],"extract":[9],"in-":[10],"formation":[11],"from":[12,56],"patent":[13],"tables,":[14],"clean":[15],"and":[16,34,44,69,116,149,174],"structure":[17],"them":[18,46],"for":[19,109,113,118,152],"future":[20],"use":[21],"in":[22,141],"predictive":[23],"machine":[24],"learning":[25],"models":[26],"develop":[28],"new":[29,42,163],"glasses.":[30],"We":[31,60,156],"extracted":[32,78,128],"compositions":[33,94,131,160],"three":[35],"properties":[36],"relevant":[37],"the":[39,63,66,74,84,103,126,146,159,162,180],"development":[40],"of":[41,65,161,179],"glasses":[43],"structured":[45],"into":[47],"a":[48],"database":[49,164],"be":[51],"used":[52],"together":[53],"with":[54,95,132],"information":[55,67,105],"other":[57],"available":[58,104],"datasets.":[59],"also":[61],"analyzed":[62],"consistency":[64],"obtained":[68],"what":[70],"it":[71],"adds":[72],"existing":[75,142,181],"databases.":[76],"The":[77,98,121],"liquidus":[79,110],"temperatures":[80],"comprise":[81],"5,696":[82],"compositions;":[83],"second":[85],"subset":[86],"includes":[87],"4,298":[88],"refractive":[89,114],"indexes":[90],"and,":[91],"finally,":[92],"1,771":[93],"Abbe":[96,119],"numbers.":[97],"extraction":[99],"performed":[100],"here":[101],"increases":[102],"by":[106],"approximately":[107],"10.4%":[108],"temperature,":[111],"6.6%":[112],"index,":[115],"4.9%":[117],"number.":[120],"impact":[122],"extends":[123],"beyond":[124],"quantity:":[125],"newly":[127],"data":[129],"introduce":[130],"property":[133,150],"values":[134],"that":[135,158],"are":[136],"more":[137,167],"diverse":[138],"than":[139,177],"those":[140,178],"databases,":[143],"thereby":[144],"expanding":[145],"accessible":[147],"compositional":[148],"space":[151],"glass":[153],"modeling":[154],"applications.":[155],"emphasize":[157],"contain":[165],"relatively":[166],"titanium,":[168],"magnesium,":[169],"zirconium,":[170],"niobium,":[171],"iron,":[172],"tin,":[173],"yttrium":[175],"oxides":[176],"bases.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-11-23T00:00:00"}
