{"id":"https://openalex.org/W6967740052","doi":"https://doi.org/10.5281/zenodo.14430369","title":"Inconsistency of LLMs in Molecular Representations","display_name":"Inconsistency of LLMs in Molecular Representations","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W6967740052","doi":"https://doi.org/10.5281/zenodo.14430369"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14430369","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14430369","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14430369","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yan, Bing","orcid":"https://orcid.org/0000-0001-7874-725X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan, Bing","raw_affiliation_strings":["New York University"],"raw_orcid":"https://orcid.org/0000-0001-7874-725X","affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Angelica","orcid":"https://orcid.org/0000-0002-1744-3209"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Angelica","raw_affiliation_strings":["New York University"],"raw_orcid":"https://orcid.org/0000-0002-1744-3209","affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":null,"display_name":"Cho, Kyunghyun","orcid":"https://orcid.org/0000-0003-1669-3211"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cho, Kyunghyun","raw_affiliation_strings":["New York University"],"raw_orcid":"https://orcid.org/0000-0003-1669-3211","affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.8798999786376953},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.67330002784729},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5771999955177307},{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.4927000105381012},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.47350001335144043}],"concepts":[{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.8798999786376953},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.67330002784729},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5771999955177307},{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.4927000105381012},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4724000096321106},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4348999857902527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4171999990940094},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3019999861717224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.299699991941452},{"id":"https://openalex.org/C125832229","wikidata":"https://www.wikidata.org/wiki/Q6503924","display_name":"Chemical nomenclature","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C2993739289","wikidata":"https://www.wikidata.org/wiki/Q10494269","display_name":"Real property","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26579999923706055},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14430369","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14430369","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14430369","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14430369","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Dataset"},"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":{"This":[0],"dataset":[1,19,31],"was":[2],"curated":[3],"based":[4],"on":[5],"the":[6,17,42,45],"LlaSMol":[7],"dataset,":[8],"reaction":[9,57,68],"prediction,":[10],"and":[11,37],"property":[12],"prediction":[13,58,69],"subsets.":[14],"We":[15],"augmented":[16],"original":[18],"by":[20],"translating":[21],"SMILES":[22,36],"string":[23],"representation":[24],"into":[25],"IUPAC":[26,38],"name":[27],"representation.":[28],"The":[29],"resulting":[30],"consists":[32],"of":[33,44],"one-to-one":[34],"mapped":[35],"representations.":[39],"Below":[40],"is":[41],"statistics":[43],"dataset:":[46],"|":[47,49,51,53,60,62,64,71,73,75,80,82,84,89,91,93,99,101,103,109,111,113,119,121,123,129,131,133,139,141,143,149,151,153,155],"Task":[48],"#Train":[50],"#Valid":[52],"#Test":[54],"||--------------------------------------|----------|--------|-------||":[55],"Forward":[56,67],"(full)":[59,79],"963,567":[61],"1,956":[63,74],"300":[65,76,85,94,124,134,154],"||":[66,77,86,95,105,115,125,135,145],"(subset)":[70,88],"76,379":[72],"Retrosynthesis":[78,87],"932,616":[81],"2,004":[83,92],"76,471":[90],"Property":[96,106,116,126,136,146],"-":[97,107,117,127,137,147],"BBBP":[98],"1,521":[100],"188":[102],"189":[104],"ClinTox":[108],"1,063":[110],"127":[112],"131":[114],"HIV":[118],"32,864":[120],"4,104":[122],"SIDER":[128],"21,800":[130],"2,540":[132],"ESOL":[138],"888":[140],"111":[142],"112":[144],"LIPO":[148],"3,358":[150],"385":[152]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
