{"id":"https://openalex.org/W4221054065","doi":"https://doi.org/10.1021/acs.jcim.2c00079","title":"Perplexity-Based Molecule Ranking and Bias Estimation of Chemical Language Models","display_name":"Perplexity-Based Molecule Ranking and Bias Estimation of Chemical Language Models","publication_year":2022,"publication_date":"2022-02-22","ids":{"openalex":"https://openalex.org/W4221054065","doi":"https://doi.org/10.1021/acs.jcim.2c00079","pmid":"https://pubmed.ncbi.nlm.nih.gov/35191696"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.2c00079","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c00079","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1021/acs.jcim.2c00079","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026925271","display_name":"Micha\u00ebl Moret","orcid":"https://orcid.org/0000-0002-8672-3386"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michael Moret","raw_affiliation_strings":["Department of Chemistry and Applied Biosciences, ETH Zurich, RETHINK, Vladimir-Prelog-Weg 4, Zurich 8093, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Applied Biosciences, ETH Zurich, RETHINK, Vladimir-Prelog-Weg 4, Zurich 8093, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078946433","display_name":"Francesca Grisoni","orcid":"https://orcid.org/0000-0001-8552-6615"},"institutions":[{"id":"https://openalex.org/I3018483916","display_name":"University Medical Center Utrecht","ror":"https://ror.org/0575yy874","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I3018483916"]},{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Francesca Grisoni","raw_affiliation_strings":["Center for Living Technologies, Alliance TU/e, WUR, UU, UMC Utrecht, Princetonlaan 6, Utrecht 3584 CB, The Netherlands","Institute for Complex Molecular Systems, Department of Biomedical Engineering, Eindhoven University of Technology, Groene Loper 7, Eindhoven 5612AZ, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-8552-6615","affiliations":[{"raw_affiliation_string":"Center for Living Technologies, Alliance TU/e, WUR, UU, UMC Utrecht, Princetonlaan 6, Utrecht 3584 CB, The Netherlands","institution_ids":["https://openalex.org/I3018483916"]},{"raw_affiliation_string":"Institute for Complex Molecular Systems, Department of Biomedical Engineering, Eindhoven University of Technology, Groene Loper 7, Eindhoven 5612AZ, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087053476","display_name":"Paul Katzberger","orcid":"https://orcid.org/0000-0003-4937-4911"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Paul Katzberger","raw_affiliation_strings":["Department of Chemistry and Applied Biosciences, ETH Zurich, RETHINK, Vladimir-Prelog-Weg 4, Zurich 8093, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Applied Biosciences, ETH Zurich, RETHINK, Vladimir-Prelog-Weg 4, Zurich 8093, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028135456","display_name":"Gisbert Schneider","orcid":"https://orcid.org/0000-0001-6706-1084"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Gisbert Schneider","raw_affiliation_strings":["Department of Chemistry and Applied Biosciences, ETH Zurich, RETHINK, Vladimir-Prelog-Weg 4, Zurich 8093, Switzerland","ETH Singapore SEC Ltd., 1 CREATE Way, #06-01 CREATE Tower, Singapore 138602, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6706-1084","affiliations":[{"raw_affiliation_string":"Department of Chemistry and Applied Biosciences, ETH Zurich, RETHINK, Vladimir-Prelog-Weg 4, Zurich 8093, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Singapore SEC Ltd., 1 CREATE Way, #06-01 CREATE Tower, Singapore 138602, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028135456","https://openalex.org/A5078946433"],"corresponding_institution_ids":["https://openalex.org/I3018483916","https://openalex.org/I35440088","https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":3.4695,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.93393448,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"62","issue":"5","first_page":"1199","last_page":"1206"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9995999932289124,"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/T13180","display_name":"Chemistry and Chemical Engineering","score":0.9717000126838684,"subfield":{"id":"https://openalex.org/subfields/2304","display_name":"Environmental Chemistry"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.9809584617614746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7048472166061401},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6885236501693726},{"id":"https://openalex.org/keywords/multinomial-distribution","display_name":"Multinomial distribution","score":0.6478663086891174},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6381028890609741},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5550697445869446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48004448413848877},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46695977449417114},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43595099449157715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42113351821899414},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3633776903152466},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20447823405265808},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13482195138931274},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.08205923438072205}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9809584617614746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7048472166061401},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6885236501693726},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.6478663086891174},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6381028890609741},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5550697445869446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48004448413848877},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46695977449417114},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43595099449157715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42113351821899414},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3633776903152466},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20447823405265808},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13482195138931274},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.08205923438072205},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1021/acs.jcim.2c00079","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c00079","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:35191696","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35191696","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of chemical information and modeling","raw_type":null},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/71aafb1d-baef-479d-939d-5ec587ba3acc","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/71aafb1d-baef-479d-939d-5ec587ba3acc","pdf_url":"https://pure.tue.nl/ws/files/201232806/acs.jcim.2c00079.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Moret, M, Grisoni, F, Katzberger, P & Schneider, G 2022, 'Perplexity-Based Molecule Ranking and Bias Estimation of Chemical Language Models', Journal of Chemical Information and Modeling, vol. 62, no. 5, pp. 1199-1206. https://doi.org/10.1021/acs.jcim.2c00079","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pubmedcentral.nih.gov:8924923","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8924923","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"J Chem Inf Model","raw_type":"Text"},{"id":"pmh:tue:oai:pure.tue.nl:publications/71aafb1d-baef-479d-939d-5ec587ba3acc","is_oa":true,"landing_page_url":"https://research.tue.nl/nl/publications/71aafb1d-baef-479d-939d-5ec587ba3acc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"Journal of Chemical Information and Modeling, 62(5), 1199 - 1206. American Chemical Society","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.2c00079","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c00079","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3608669926","display_name":null,"funder_award_id":"205321_182176","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320321652","display_name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich","ror":"https://ror.org/05a28rw58"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1574901103","https://openalex.org/W1861765464","https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W2038287971","https://openalex.org/W2064675550","https://openalex.org/W2076063813","https://openalex.org/W2164700406","https://openalex.org/W2204575588","https://openalex.org/W2529996553","https://openalex.org/W2558999090","https://openalex.org/W2578240541","https://openalex.org/W2594328795","https://openalex.org/W2610148085","https://openalex.org/W2765224015","https://openalex.org/W2784270883","https://openalex.org/W2790808809","https://openalex.org/W2798613236","https://openalex.org/W2805002767","https://openalex.org/W2883583109","https://openalex.org/W2889555425","https://openalex.org/W2897337442","https://openalex.org/W2900090807","https://openalex.org/W2914635984","https://openalex.org/W2915175970","https://openalex.org/W2956961449","https://openalex.org/W2962764565","https://openalex.org/W2963028280","https://openalex.org/W2970352191","https://openalex.org/W2971690404","https://openalex.org/W2989615256","https://openalex.org/W3011286504","https://openalex.org/W3034510440","https://openalex.org/W3043969542","https://openalex.org/W3098269892","https://openalex.org/W3104956673","https://openalex.org/W3106536628","https://openalex.org/W3116865743","https://openalex.org/W3127493072","https://openalex.org/W3133523400","https://openalex.org/W3174777205","https://openalex.org/W3185391990","https://openalex.org/W4236044224","https://openalex.org/W4281619372","https://openalex.org/W4313703391"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2084531783","https://openalex.org/W2902731467"],"abstract_inverted_index":{"Chemical":[0],"language":[1],"models":[2],"(CLMs)":[3],"can":[4],"be":[5],"employed":[6],"to":[7,46,58,62,97,122,140],"design":[8,73],"molecules":[9,43,65],"with":[10,102],"desired":[11,72],"properties.":[12],"CLMs":[13],"generate":[14],"new":[15,137],"chemical":[16],"structures":[17],"in":[18],"the":[19,26,36,55,60,64,71,82,89,93,133],"form":[20],"of":[21,38,112,135],"textual":[22],"representations,":[23],"such":[24],"as":[25],"simplified":[27],"molecular":[28,85],"input":[29],"line":[30],"entry":[31],"system":[32,139],"(SMILES)":[33],"strings.":[34],"However,":[35],"quality":[37],"these":[39],"de":[40],"novo":[41],"generated":[42,66],"is":[44,120],"difficult":[45],"assess":[47],"a":[48,68,136],"priori.":[49],"In":[50],"this":[51],"study,":[52],"we":[53],"apply":[54],"perplexity":[56,96,118],"metric":[57],"determine":[59],"degree":[61],"which":[63],"by":[67,92],"CLM":[69],"match":[70],"objectives.":[74],"This":[75],"model-intrinsic":[76],"score":[77],"allows":[78,132],"identifying":[79],"and":[80,131],"ranking":[81,138],"most":[83],"promising":[84],"designs":[86],"based":[87],"on":[88],"probabilities":[90],"learned":[91],"CLM.":[94],"Using":[95],"compare":[98],"\"greedy\"":[99],"(beam":[100],"search)":[101],"\"explorative\"":[103],"(multinomial":[104],"sampling)":[105],"methods":[106],"for":[107],"SMILES":[108],"generation,":[109],"certain":[110],"advantages":[111],"multinomial":[113],"sampling":[114],"become":[115],"apparent.":[116],"Additionally,":[117],"scoring":[119],"performed":[121],"identify":[123],"undesired":[124,143],"model":[125,129],"biases":[126],"introduced":[127],"during":[128],"training":[130],"development":[134],"remove":[141],"those":[142],"biases.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
