{"id":"https://openalex.org/W4388452573","doi":"https://doi.org/10.1021/acs.jcim.3c01281","title":"Snowball 2.0: Generic Material Data Parser for ChemDataExtractor","display_name":"Snowball 2.0: Generic Material Data Parser for ChemDataExtractor","publication_year":2023,"publication_date":"2023-11-07","ids":{"openalex":"https://openalex.org/W4388452573","doi":"https://doi.org/10.1021/acs.jcim.3c01281","pmid":"https://pubmed.ncbi.nlm.nih.gov/37934697"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c01281","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c01281","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.3c01281","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021467511","display_name":"Qingyang Dong","orcid":"https://orcid.org/0000-0002-8782-7638"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Qingyang Dong","raw_affiliation_strings":["Cavendish Laboratory, Department of Physics, University of Cambridge, Cambridge CB3 0HE, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8782-7638","affiliations":[{"raw_affiliation_string":"Cavendish Laboratory, Department of Physics, University of Cambridge, Cambridge CB3 0HE, U.K","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068607578","display_name":"Jacqueline M. Cole","orcid":"https://orcid.org/0000-0002-1552-8743"},"institutions":[{"id":"https://openalex.org/I1286704778","display_name":"Rutherford Appleton Laboratory","ror":"https://ror.org/03gq8fr08","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1286704778","https://openalex.org/I162524378","https://openalex.org/I4210087105"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":true,"raw_author_name":"Jacqueline M. Cole","raw_affiliation_strings":["Cavendish Laboratory, Department of Physics, University of Cambridge, Cambridge CB3 0HE, U.K","ISIS Neutron and Muon Source, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K"],"raw_orcid":"https://orcid.org/0000-0002-1552-8743","affiliations":[{"raw_affiliation_string":"Cavendish Laboratory, Department of Physics, University of Cambridge, Cambridge CB3 0HE, U.K","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]},{"raw_affiliation_string":"ISIS Neutron and Muon Source, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K","institution_ids":["https://openalex.org/I1286704778"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068607578"],"corresponding_institution_ids":["https://openalex.org/I1286704778","https://openalex.org/I241749","https://openalex.org/I4210096386"],"apc_list":null,"apc_paid":null,"fwci":0.4572,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.55508308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"63","issue":"22","first_page":"7045","last_page":"7055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998999834060669,"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":0.9998999834060669,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9958000183105469,"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/T10028","display_name":"Topic Modeling","score":0.9496999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8256122469902039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7847012877464294},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7392380237579346},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6181793808937073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5706762075424194},{"id":"https://openalex.org/keywords/snowball-sampling","display_name":"Snowball sampling","score":0.5619614720344543},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5428909659385681},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5403931140899658},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5313513875007629},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4991128444671631},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4861859679222107},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4214492738246918},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.41969045996665955},{"id":"https://openalex.org/keywords/snowball-earth","display_name":"Snowball Earth","score":0.41704681515693665},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3754436671733856},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11289846897125244}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8256122469902039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7847012877464294},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7392380237579346},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6181793808937073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5706762075424194},{"id":"https://openalex.org/C106399304","wikidata":"https://www.wikidata.org/wiki/Q868123","display_name":"Snowball sampling","level":2,"score":0.5619614720344543},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5428909659385681},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5403931140899658},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5313513875007629},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4991128444671631},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4861859679222107},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4214492738246918},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.41969045996665955},{"id":"https://openalex.org/C168816792","wikidata":"https://www.wikidata.org/wiki/Q214689","display_name":"Snowball Earth","level":3,"score":0.41704681515693665},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3754436671733856},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11289846897125244},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C15739521","wikidata":"https://www.wikidata.org/wiki/Q602963","display_name":"Glacial period","level":2,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1021/acs.jcim.3c01281","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c01281","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:37934697","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37934697","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:pubmedcentral.nih.gov:10685441","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10685441","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10685441/pdf/ci3c01281.pdf","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:oai:www.repository.cam.ac.uk:1810/361755","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/361755","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/59dcbb7b-f598-4885-8019-e1377a568981/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":"Article"},{"id":"pmh:oai:purl.org/net/epubs:work/56345892","is_oa":true,"landing_page_url":"https://epubs.stfc.ac.uk/work/56345892","pdf_url":null,"source":{"id":"https://openalex.org/S4306400600","display_name":"ePubs (Science and Technology Facilities Council, Research Councils UK)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162524378","host_organization_name":"Science and Technology Facilities Council","host_organization_lineage":["https://openalex.org/I162524378"],"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":"","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.3c01281","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c01281","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G1531024995","display_name":null,"funder_award_id":"RCSRF1819\\7\\10","funder_id":"https://openalex.org/F4320320005","funder_display_name":"Royal Academy of Engineering"}],"funders":[{"id":"https://openalex.org/F4320307790","display_name":"BASF","ror":"https://ror.org/01q8f6705"},{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"},{"id":"https://openalex.org/F4320334632","display_name":"Science and Technology Facilities Council","ror":"https://ror.org/057g20z61"},{"id":"https://openalex.org/F4320338254","display_name":"ISIS Neutron and Muon Source","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W617139115","https://openalex.org/W1985697096","https://openalex.org/W1992985800","https://openalex.org/W1997841190","https://openalex.org/W2111044246","https://openalex.org/W2117363206","https://openalex.org/W2134329894","https://openalex.org/W2136794542","https://openalex.org/W2161344493","https://openalex.org/W2165671627","https://openalex.org/W2523785361","https://openalex.org/W2755202310","https://openalex.org/W2766362701","https://openalex.org/W2808304511","https://openalex.org/W2992302948","https://openalex.org/W3006937107","https://openalex.org/W3047398431","https://openalex.org/W3118795178","https://openalex.org/W3200122731","https://openalex.org/W4214535912","https://openalex.org/W4225378608","https://openalex.org/W4225409008","https://openalex.org/W4281617541","https://openalex.org/W4283074682","https://openalex.org/W4307139584"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2004087619","https://openalex.org/W2469016277","https://openalex.org/W2757101400","https://openalex.org/W1982302668","https://openalex.org/W2362196274","https://openalex.org/W2557094866","https://openalex.org/W1990527953","https://openalex.org/W2240384024","https://openalex.org/W2766839647"],"abstract_inverted_index":{"The":[0,20],"ever-growing":[1],"amount":[2],"of":[3,16,40,102,121,171],"chemical":[4,29,82],"data":[5,47,173],"found":[6],"in":[7,23,128,150,168],"the":[8,14,24,38,135,169],"scientific":[9],"literature":[10],"has":[11,34,139],"led":[12],"to":[13,26,79],"emergence":[15],"data-driven":[17],"materials":[18],"discovery.":[19],"first":[21],"step":[22],"pipeline,":[25],"automatically":[27],"extract":[28,80],"information":[30,106],"from":[31,108],"plain":[32],"text,":[33],"been":[35,140],"driven":[36],"by":[37,94],"development":[39],"software":[41],"toolkits":[42],"such":[43],"as":[44],"ChemDataExtractor.":[45],"Such":[46],"extraction":[48],"processes":[49],"have":[50],"created":[51],"a":[52,66,71,98,125],"demand":[53],"for":[54,161],"parsers":[55],"that":[56],"efficiently":[57],"enable":[58],"text":[59],"mining.":[60],"Here,":[61],"we":[62],"present":[63],"Snowball":[64,111,118,122,146,153,175],"2.0,":[65,144],"sentence":[67],"parser":[68],"based":[69],"on":[70,114],"semisupervised":[72],"machine-learning":[73],"algorithm.":[74],"It":[75],"can":[76],"be":[77],"used":[78],"any":[81],"property":[83],"without":[84],"additional":[85],"training.":[86],"We":[87],"validate":[88],"its":[89],"precision,":[90],"recall,":[91],"and":[92,96,157,163,184],"F-score":[93],"training":[95],"testing":[97],"model":[99],"with":[100,130],"sentences":[101],"semiconductor":[103],"band":[104],"gap":[105],"curated":[107],"journal":[109],"articles.":[110],"2.0":[112,123,147,154,176],"builds":[113],"two":[115],"previously":[116],"developed":[117],"algorithms.":[119],"Evaluation":[120],"shows":[124],"15\u201320%":[126],"increase":[127],"recall":[129],"marginally":[131],"reduced":[132],"precision":[133],"over":[134],"previous":[136],"version":[137],"which":[138],"incorporated":[141],"into":[142],"ChemDataExtractor":[143],"giving":[145],"better":[148,158,179],"performance":[149],"most":[151],"configurations.":[152],"offers":[155],"more":[156,166],"parsing":[159],"options":[160],"ChemDataExtractor,":[162],"it":[164],"is":[165],"capable":[167],"pipeline":[170],"automated":[172],"extraction.":[174],"also":[177],"features":[178],"generalizability,":[180],"performance,":[181],"learning":[182],"efficiencies,":[183],"user-friendliness.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}