{"id":"https://openalex.org/W7202243794","doi":"https://doi.org/10.1007/978-3-032-35390-0_18","title":"A Controlled Study of Tokenizer Scale in SMILES-Based Foundation Models","display_name":"A Controlled Study of Tokenizer Scale in SMILES-Based Foundation Models","publication_year":2026,"publication_date":"2026-08-12","ids":{"openalex":"https://openalex.org/W7202243794","doi":"https://doi.org/10.1007/978-3-032-35390-0_18"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-35390-0_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-35390-0_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007926961","display_name":"SeongIk Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I4210132857","display_name":"Ghent University Global Campus","ror":"https://ror.org/041bygf77","country_code":"KR","type":"education","lineage":["https://openalex.org/I32597200","https://openalex.org/I4210132857"]}],"countries":["BE","KR"],"is_corresponding":true,"raw_author_name":"Seongik Choi","raw_affiliation_strings":["Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, South Korea","Department of Electronics and Information Systems, Ghent University, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0009-0004-5241-0391","affiliations":[{"raw_affiliation_string":"Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, South Korea","institution_ids":["https://openalex.org/I4210132857"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140145502","display_name":"Ju Hyung Lee","orcid":"https://orcid.org/0009-0001-5191-7420"},"institutions":[{"id":"https://openalex.org/I4210132857","display_name":"Ghent University Global Campus","ror":"https://ror.org/041bygf77","country_code":"KR","type":"education","lineage":["https://openalex.org/I32597200","https://openalex.org/I4210132857"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ju Hyung Lee","raw_affiliation_strings":["Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, South Korea"],"raw_orcid":"https://orcid.org/0009-0001-5191-7420","affiliations":[{"raw_affiliation_string":"Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, South Korea","institution_ids":["https://openalex.org/I4210132857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008707729","display_name":"Utku \u00d6zbulak","orcid":"https://orcid.org/0000-0003-3084-6034"},"institutions":[{"id":"https://openalex.org/I146429904","display_name":"Incheon National University","ror":"https://ror.org/02xf7p935","country_code":"KR","type":"education","lineage":["https://openalex.org/I146429904"]},{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I4210132857","display_name":"Ghent University Global Campus","ror":"https://ror.org/041bygf77","country_code":"KR","type":"education","lineage":["https://openalex.org/I32597200","https://openalex.org/I4210132857"]}],"countries":["BE","KR","US"],"is_corresponding":false,"raw_author_name":"Utku Ozbulak","raw_affiliation_strings":["Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, South Korea","Computational Data Sciences Department, George Mason University Korea, Incheon, South Korea","Department of Electronics and Information Systems, Ghent University, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0003-3084-6034","affiliations":[{"raw_affiliation_string":"Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, South Korea","institution_ids":["https://openalex.org/I4210132857"]},{"raw_affiliation_string":"Computational Data Sciences Department, George Mason University Korea, Incheon, South Korea","institution_ids":["https://openalex.org/I146429904","https://openalex.org/I162714631"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012688473","display_name":"Joris Vankerschaver","orcid":"https://orcid.org/0000-0002-5813-5659"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I4210132857","display_name":"Ghent University Global Campus","ror":"https://ror.org/041bygf77","country_code":"KR","type":"education","lineage":["https://openalex.org/I32597200","https://openalex.org/I4210132857"]}],"countries":["BE","KR"],"is_corresponding":false,"raw_author_name":"Joris Vankerschaver","raw_affiliation_strings":["Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, South Korea","Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-5813-5659","affiliations":[{"raw_affiliation_string":"Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, South Korea","institution_ids":["https://openalex.org/I4210132857"]},{"raw_affiliation_string":"Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029555436","display_name":"Wesley De Neve","orcid":"https://orcid.org/0000-0002-8190-3839"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I4210132857","display_name":"Ghent University Global Campus","ror":"https://ror.org/041bygf77","country_code":"KR","type":"education","lineage":["https://openalex.org/I32597200","https://openalex.org/I4210132857"]}],"countries":["BE","KR"],"is_corresponding":false,"raw_author_name":"Wesley De Neve","raw_affiliation_strings":["Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, South Korea","Department of Electronics and Information Systems, Ghent University, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-8190-3839","affiliations":[{"raw_affiliation_string":"Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, South Korea","institution_ids":["https://openalex.org/I4210132857"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007926961"],"corresponding_institution_ids":["https://openalex.org/I32597200","https://openalex.org/I4210132857"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.715499997138977},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.6571999788284302},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6413999795913696},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6004999876022339},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5659000277519226},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.534500002861023},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4966000020503998},{"id":"https://openalex.org/keywords/rapid-serial-visual-presentation","display_name":"Rapid serial visual presentation","score":0.4731000065803528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8463000059127808},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.715499997138977},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.6571999788284302},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6413999795913696},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6004999876022339},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.534500002861023},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C2779668609","wikidata":"https://www.wikidata.org/wiki/Q623092","display_name":"Rapid serial visual presentation","level":3,"score":0.4731000065803528},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.4564000070095062},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37940001487731934},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-35390-0_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-35390-0_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1601495365","https://openalex.org/W1975147762","https://openalex.org/W2594183968","https://openalex.org/W2963341956","https://openalex.org/W3138781613","https://openalex.org/W3198212015","https://openalex.org/W4313485929","https://openalex.org/W4382132796","https://openalex.org/W4386566638","https://openalex.org/W4403256806","https://openalex.org/W4403691894","https://openalex.org/W4403785850","https://openalex.org/W4406201162","https://openalex.org/W4406817136","https://openalex.org/W4408815288","https://openalex.org/W4412421282","https://openalex.org/W4412889581","https://openalex.org/W7118092645","https://openalex.org/W7131803778"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-08-13T00:00:00"}