{"id":"https://openalex.org/W7225345779","doi":"https://doi.org/10.1080/08957347.2026.2758589","title":"ALGORITHMIC RATER DRIFT IN AUTOMATED ESSAY SCORING: A MANY-FACET RASCH ANALYSIS OF SUCCESSIVE LLM VERSIONS","display_name":"ALGORITHMIC RATER DRIFT IN AUTOMATED ESSAY SCORING: A MANY-FACET RASCH ANALYSIS OF SUCCESSIVE LLM VERSIONS","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225345779","doi":"https://doi.org/10.1080/08957347.2026.2758589"},"language":"en","primary_location":{"id":"doi:10.1080/08957347.2026.2758589","doi":"https://doi.org/10.1080/08957347.2026.2758589","is_oa":false,"landing_page_url":"https://doi.org/10.1080/08957347.2026.2758589","pdf_url":null,"source":{"id":"https://openalex.org/S2940672","display_name":"Applied Measurement in Education","issn_l":"0895-7347","issn":["0895-7347","1532-4818"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","erih-plus","jufo-1","norway-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Measurement in Education","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5106757291","display_name":"Umur \u00d6\u00e7","orcid":"https://orcid.org/0000-0002-1269-1115","observed_orcids":["https://orcid.org/0000-0002-1269-1115"]},"institutions":[{"id":"https://openalex.org/I4210094226","display_name":"Mi\u0307lli\u0307 E\u011fi\u0307ti\u0307m Bakanli\u011fi","ror":"https://ror.org/00jga9g46","country_code":"TR","type":"government","lineage":["https://openalex.org/I4210094226"]},{"id":"https://openalex.org/I4210141076","display_name":"Ministere de l'Education Nationale","ror":"https://ror.org/04xp49e10","country_code":"FR","type":"government","lineage":["https://openalex.org/I2802818602","https://openalex.org/I4210141076"]}],"countries":["FR","TR"],"is_corresponding":true,"raw_author_name":"Umur \u00d6\u00e7","raw_affiliation_strings":["Ministry of National Education (MoNE)"],"raw_orcid":"https://orcid.org/0000-0002-1269-1115","affiliations":[{"raw_affiliation_string":"Ministry of National Education (MoNE)","institution_ids":["https://openalex.org/I4210094226","https://openalex.org/I4210141076"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5106757291"],"corresponding_institution_ids":["https://openalex.org/I4210094226","https://openalex.org/I4210141076"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10467","display_name":"Psychometric Methodologies and Testing","score":0.6098999977111816,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10467","display_name":"Psychometric Methodologies and Testing","score":0.6098999977111816,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14025","display_name":"Educational Technology and Assessment","score":0.1648000031709671,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14414","display_name":"Artificial Intelligence in Education","score":0.03189999982714653,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/automated-essay-scoring","display_name":"automated essay scoring","score":0.9150000214576721},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9399999976158142},{"id":"https://openalex.org/keywords/chatgpt","display_name":"ChatGPT","score":0.8259999752044678},{"id":"https://openalex.org/keywords/interobserver-agreement","display_name":"interobserver agreement","score":0.6389999985694885},{"id":"https://openalex.org/keywords/persuasive-essay","display_name":"persuasive essay","score":0.5630000233650208},{"id":"https://openalex.org/keywords/reasoning-effort","display_name":"reasoning effort","score":0.33000001311302185}],"concepts":[{"id":"https://openalex.org/C101266164","wikidata":"https://www.wikidata.org/wiki/Q2131821","display_name":"Rasch model","level":2,"score":0.9330000281333923},{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.7950999736785889},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4821999967098236},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4756999909877777},{"id":"https://openalex.org/C19875794","wikidata":"https://www.wikidata.org/wiki/Q1207340","display_name":"Item response theory","level":3,"score":0.46799999475479126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4641999900341034},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C61863361","wikidata":"https://www.wikidata.org/wiki/Q470749","display_name":"Inter-rater reliability","level":3,"score":0.44200000166893005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43639999628067017},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4059999883174896},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3822000026702881},{"id":"https://openalex.org/C171606756","wikidata":"https://www.wikidata.org/wiki/Q506132","display_name":"Psychometrics","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C181447626","wikidata":"https://www.wikidata.org/wiki/Q1224359","display_name":"Differential item functioning","level":4,"score":0.33899998664855957},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C2778263599","wikidata":"https://www.wikidata.org/wiki/Q1669245","display_name":"Item analysis","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C207968926","wikidata":"https://www.wikidata.org/wiki/Q7227107","display_name":"Polytomous Rasch model","level":4,"score":0.2791000008583069},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C2778883600","wikidata":"https://www.wikidata.org/wiki/Q2390977","display_name":"Language proficiency","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C55786151","wikidata":"https://www.wikidata.org/wiki/Q951437","display_name":"Level of measurement","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2687000036239624},{"id":"https://openalex.org/C2776818064","wikidata":"https://www.wikidata.org/wiki/Q829903","display_name":"Agreement","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C2778091340","wikidata":"https://www.wikidata.org/wiki/Q15749950","display_name":"Quality of Life Research","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C49453240","wikidata":"https://www.wikidata.org/wiki/Q1592163","display_name":"Construct validity","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C3018868096","wikidata":"https://www.wikidata.org/wiki/Q2693233","display_name":"Internal consistency","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25760000944137573},{"id":"https://openalex.org/C198999979","wikidata":"https://www.wikidata.org/wiki/Q5159115","display_name":"Concurrent validity","level":4,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/08957347.2026.2758589","doi":"https://doi.org/10.1080/08957347.2026.2758589","is_oa":false,"landing_page_url":"https://doi.org/10.1080/08957347.2026.2758589","pdf_url":null,"source":{"id":"https://openalex.org/S2940672","display_name":"Applied Measurement in Education","issn_l":"0895-7347","issn":["0895-7347","1532-4818"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","erih-plus","jufo-1","norway-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Measurement in Education","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1593930920","https://openalex.org/W1983897914","https://openalex.org/W2015795623","https://openalex.org/W2054745812","https://openalex.org/W2055923168","https://openalex.org/W2063885316","https://openalex.org/W2101412158","https://openalex.org/W2109594752","https://openalex.org/W2142266390","https://openalex.org/W2159759971","https://openalex.org/W2164777277","https://openalex.org/W2342249984","https://openalex.org/W2802461780","https://openalex.org/W2989567029","https://openalex.org/W4254687493","https://openalex.org/W4307344395","https://openalex.org/W4323655724","https://openalex.org/W4392202731","https://openalex.org/W4392681182","https://openalex.org/W4396806295","https://openalex.org/W4400608580","https://openalex.org/W4402411200","https://openalex.org/W4402860127","https://openalex.org/W4404341075","https://openalex.org/W4409780841","https://openalex.org/W4410973956","https://openalex.org/W4415797148","https://openalex.org/W7133211372","https://openalex.org/W7133239970","https://openalex.org/W7135037337"],"related_works":["https://openalex.org/W7135037337","https://openalex.org/W7204894163","https://openalex.org/W7172248012","https://openalex.org/W4406606530","https://openalex.org/W4415043371","https://openalex.org/W4400138640","https://openalex.org/W7170368551","https://openalex.org/W4411609111","https://openalex.org/W7132831666","https://openalex.org/W4396806295"],"abstract_inverted_index":{"Although":[0],"large":[1],"language":[2],"models":[3],"are":[4,145],"increasingly":[5],"used":[6],"for":[7],"automated":[8],"scoring,":[9],"the":[10,109],"psychometric":[11],"stability":[12],"of":[13,43],"their":[14],"scoring":[15],"across":[16],"version":[17,133],"updates":[18,134],"remains":[19],"underexplored.":[20],"This":[21],"study":[22],"compared":[23],"two":[24],"successive":[25],"ChatGPT":[26],"versions":[27,118],"(GPT-5.1":[28],"and":[29,38,59,66,78,121,142],"GPT-5.2)":[30],"on":[31],"persuasive":[32],"essays":[33,47],"in":[34],"agreement,":[35],"severity,":[36],"leniency,":[37],"bias.":[39],"A":[40],"stratified":[41],"sample":[42],"99":[44],"ASAP":[45],"2.0":[46],"was":[48,73,94,103],"scored":[49],"three":[50],"times":[51],"by":[52],"each":[53],"model":[54],"with":[55,130],"a":[56,86],"holistic":[57],"rubric":[58],"analyzed":[60],"using":[61],"agreement":[62,80,129],"indices,":[63],"Bland\u2013Altman":[64],"analysis,":[65],"Many-Facet":[67],"Rasch":[68],"Measurement":[69],"(MFRM).":[70],"Inter-version":[71,124],"correlation":[72],"high":[74],"(r":[75],"=":[76],".771)":[77],"adjacent":[79],"reached":[81],"99.0%,":[82],"yet":[83],"MFRM":[84],"revealed":[85],"4.26-logit":[87],"severity\u2013leniency":[88],"difference.":[89],"Against":[90],"human":[91,131],"scores,":[92],"GPT-5.1":[93],"nearly":[95],"unbiased":[96],"(\u22120.04;":[97],"60.6%":[98],"exact":[99],"agreement),":[100],"whereas":[101],"GPT-5.2":[102],"systematically":[104],"lenient":[105,120],"(+0.33;":[106],"47.5%).":[107],"Raising":[108],"reasoning-effort":[110],"setting":[111],"from":[112],"none":[113],"to":[114],"medium":[115],"made":[116],"both":[117],"more":[119],"less":[122],"stable.":[123],"consistency":[125],"does":[126],"not":[127],"guarantee":[128],"scores;":[132],"can":[135],"produce":[136],"algorithmic":[137],"rater":[138],"drift.":[139],"Version":[140],"locking":[141],"criterion-based":[143],"validation":[144],"recommended.":[146]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-11-06T00:00:00"}