{"id":"https://openalex.org/W7223086249","doi":"https://doi.org/10.26434/chemrxiv.15010913/v1","title":"Benchmarking thermoelectric property extraction from scientific text","display_name":"Benchmarking thermoelectric property extraction from scientific text","publication_year":2026,"publication_date":"2026-10-22","ids":{"openalex":"https://openalex.org/W7223086249","doi":"https://doi.org/10.26434/chemrxiv.15010913/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15010913/v1","doi":"https://doi.org/10.26434/chemrxiv.15010913/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010913/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010913/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010913/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159164286","display_name":"Berna Uyan\u0131k","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Berna Uyan\u0131k","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5159164286"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.399399995803833,"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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.399399995803833,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.21719999611377716,"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/T10440","display_name":"Advanced Thermoelectric Materials and Devices","score":0.15360000729560852,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/thermoelectric-properties","display_name":"thermoelectric properties","score":0.9800000190734863},{"id":"https://openalex.org/keywords/property-extraction","display_name":"property extraction","score":0.7609999775886536},{"id":"https://openalex.org/keywords/scientific-texts","display_name":"scientific texts","score":0.9169999957084656},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.593999981880188},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.6100000143051147},{"id":"https://openalex.org/keywords/thermoelectric-materials","display_name":"thermoelectric materials","score":0.6940000057220459},{"id":"https://openalex.org/keywords/gold-standard-annotation","display_name":"gold standard annotation","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C63024428","wikidata":"https://www.wikidata.org/wiki/Q552456","display_name":"Thermoelectric effect","level":2,"score":0.5863999724388123},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5647000074386597},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.47769999504089355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4147000014781952},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.35370001196861267},{"id":"https://openalex.org/C117127486","wikidata":"https://www.wikidata.org/wiki/Q11569191","display_name":"Thermoelectric generator","level":3,"score":0.35199999809265137},{"id":"https://openalex.org/C128458982","wikidata":"https://www.wikidata.org/wiki/Q18891486","display_name":"Thermoelectric cooling","level":3,"score":0.35190001130104065},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C207365445","wikidata":"https://www.wikidata.org/wiki/Q15020929","display_name":"Thermoelectric materials","level":3,"score":0.2565999925136566}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.26434/chemrxiv.15010913/v1","doi":"https://doi.org/10.26434/chemrxiv.15010913/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010913/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010913/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"doi:10.26434/chemrxiv.15010913/v2","doi":"https://doi.org/10.26434/chemrxiv.15010913/v2","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010913/v2","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010913/v2","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"doi:10.5281/zenodo.23522990","doi":"https://doi.org/10.5281/zenodo.23522990","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23522990","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,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},{"id":"doi:10.5281/zenodo.23522991","doi":"https://doi.org/10.5281/zenodo.23522991","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23522991","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,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15010913/v1","doi":"https://doi.org/10.26434/chemrxiv.15010913/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15010913/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010913/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223086249.pdf","grobid_xml":"https://content.openalex.org/works/W7223086249.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2065832194","https://openalex.org/W2523785361","https://openalex.org/W2953641512","https://openalex.org/W2964864162","https://openalex.org/W3200122731","https://openalex.org/W4307139584","https://openalex.org/W4392002118","https://openalex.org/W4405616956","https://openalex.org/W4414814630","https://openalex.org/W4417187428","https://openalex.org/W7153313481","https://openalex.org/W7164015949","https://openalex.org/W7220714616"],"related_works":["https://openalex.org/W4414814630","https://openalex.org/W4307139584","https://openalex.org/W7080509683","https://openalex.org/W7214106069","https://openalex.org/W4410819665","https://openalex.org/W2968928243","https://openalex.org/W4408973355","https://openalex.org/W2746747154","https://openalex.org/W4303648596","https://openalex.org/W4411567682"],"abstract_inverted_index":{"Databases":[0],"of":[1,16,76,180,191,204],"thermoelectric":[2,46],"properties":[3],"are":[4,23,28],"built":[5],"largely":[6],"by":[7,94],"extracting":[8],"values":[9],"from":[10,97,185,208,215],"the":[11,14,35,43,77,82,108,125,129,137,149,156,162,186,198,209,216,226],"literature,":[12],"and":[13,25,61,86,121,148,159,164,173,231],"choice":[15],"extraction":[17],"method":[18,233],"determines":[19],"how":[20,26],"many":[21,27],"records":[22],"recovered":[24],"wrong.":[29],"We":[30,200,224],"compare":[31],"five":[32],"methods":[33,66,169],"on":[34,69,81,88],"same":[36],"paragraph-level":[37],"task:":[38],"a":[39,48,55,70,89,104,236],"corpus-informed":[40],"regular-expression":[41,78,157],"baseline,":[42],"published":[44],"ChemDataExtractor":[45,163],"parsers,":[47],"MaterialsBERT-based":[49],"named-entity":[50],"model":[51,59],"with":[52,103,175],"rule-based":[53],"linking,":[54],"single-prompt":[56,138],"large":[57],"language":[58],"(LLM)":[60],"an":[62,205],"LLM":[63,139,168],"agent.":[64],"The":[65],"were":[67],"developed":[68],"100-paragraph":[71],"development":[72],"sample":[73,92],"(the":[74],"rules":[75],"baseline":[79,158],"earlier,":[80],"whole":[83],"corpus),":[84],"frozen,":[85],"run":[87],"200-paragraph":[90],"test":[91,132],"drawn":[93],"stratified":[95],"sampling":[96],"311":[98],"papers":[99],"(mostly":[100],"arXiv":[101],"preprints),":[102],"paper-level":[105],"split":[106],"between":[107],"two":[109],"samples.":[110],"A":[111],"record":[112],"counts":[113],"as":[114],"correct":[115],"only":[116],"if":[117],"property,":[118,171],"value,":[119],"temperature":[120,174],"material":[122,187,195],"all":[123,232],"match":[124],"gold":[126,229],"standard.":[127],"On":[128],"160":[130],"in-scope":[131],"paragraphs":[133],"(241":[134],"core":[135],"records),":[136],"reached":[140],"F1":[141,176],"=":[142],"0.79":[143],"(95":[144],"%":[145],"CI":[146],"0.71\u20130.87)":[147],"agent":[150,211],"0.73":[151],"(0.64\u20130.83),":[152],"against":[153],"0.22":[154],"for":[155,161],"0.06":[160],"NER":[165],"pipelines.":[166],"Both":[167],"recover":[170],"value":[172],"above":[177],"0.94;":[178],"most":[179,190],"their":[181],"remaining":[182],"losses":[183],"arise":[184],"criterion;":[188],"in":[189,219,235],"these":[192],"cases":[193],"one":[194],"name":[196],"contains":[197],"other.":[199],"found":[201],"no":[202],"evidence":[203],"accuracy":[206],"improvement":[207],"tested":[210],"configuration,":[212],"which":[213],"differs":[214],"single":[217],"prompt":[218],"several":[220],"components":[221],"at":[222],"once.":[223],"release":[225],"protocol,":[227],"code,":[228],"standard":[230],"outputs":[234],"public":[237],"repository.":[238]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-22T00:00:00"}
