{"meta":{"query_hash":"8eedc4ff3541","filters":{"venue":"Language Assessment Quarterly"},"cohort_total":22,"direct_labels_cover":0,"predictions_cover":22,"exported":22,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/8eedc4ff3541","api":"https://metacan.xera.ac/api/v1/cohort?venue=Language+Assessment+Quarterly"},"results":[{"id":"W2002561419","doi":"10.1080/15434303.2014.936603","title":"Using Lexical Profiling Tools to Investigate Children’s Written Vocabulary in Grade 3: An Exploratory Study","year":2015,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Calgary","funders":"","keywords":"Vocabulary; Rubric; Lexical diversity; Salient; Psychology; Computer science; Linguistics; Profiling (computer programming); Exploratory research; Vocabulary development; Natural language processing; Lexical density; Trait; Artificial intelligence; Mathematics education; Lexical item; Sociology","score_opus":0.12772409961458991,"score_gpt":0.43022945482507097,"score_spread":0.30250535521048105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002561419","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9970941,0.000045388584,0.00028690812,0.00055337284,0.00023075107,0.00075205864,0.0000057416764,0.00015738205,0.0008743054],"genre_scores_gemma":[0.9917354,3.7497387e-7,0.0070623797,0.00030611348,0.000696584,0.00008802666,0.0000349129,0.000022374901,0.00005383479],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9972938,0.0010504106,0.0003125855,0.00038434303,0.0005367931,0.00042207353],"domain_scores_gemma":[0.9991072,0.00006832943,0.00008037413,0.00027182256,0.00007916812,0.00039315224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026379842,0.00014798497,0.0002077686,0.00018034356,0.00023532618,0.0003643282,0.00022914854,0.00007915723,0.000011258221],"category_scores_gemma":[0.00013566358,0.00015800071,0.000030823623,0.00039142213,0.000061121966,0.0007167904,0.000022098702,0.00024361644,0.000015098191],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012586501,0.0011616822,0.43023,0.000008751249,0.000018339982,0.00007879752,0.55467576,0.00007963276,0.003168103,0.0015959174,0.00010588071,0.00886455],"study_design_scores_gemma":[0.0007641609,0.00075117627,0.116138175,0.000072104056,0.000023281029,0.0000036719782,0.8810411,0.0003250043,0.0001297832,0.00038118762,0.000032491254,0.00033787967],"about_ca_topic_score_codex":0.006299836,"about_ca_topic_score_gemma":0.0129897725,"teacher_disagreement_score":0.32636532,"about_ca_system_score_codex":0.0002959958,"about_ca_system_score_gemma":0.00056888565,"threshold_uncertainty_score":0.952351},"labels":[],"label_agreement":null},{"id":"W2015223621","doi":"10.1080/15434303.2014.981334","title":"Interpreting the Impact of the Ontario Secondary School Literacy Test on Second Language Students Within an Argument-Based Validation Framework","year":2015,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Argument (complex analysis); Literacy; Context (archaeology); Mathematics education; Test (biology); Curriculum; Reading (process); Ell; Language proficiency; Empirical research; Psychology; Pedagogy; Language assessment; Linguistics; Teaching method; Mathematics","score_opus":0.016460365348475472,"score_gpt":0.3890332495887422,"score_spread":0.37257288424026674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015223621","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9859685,0.000040822077,0.00015857891,0.00032602434,0.0005758933,0.00080301164,0.0000351297,0.0000722697,0.012019774],"genre_scores_gemma":[0.99618423,3.5618834e-7,0.0008259438,0.00048217253,0.00029143973,0.000052465384,0.00004822072,0.000027237502,0.0020879274],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99657845,0.0007991931,0.00048390598,0.00036914388,0.0013109886,0.0004583026],"domain_scores_gemma":[0.9977991,0.00056095794,0.00049451157,0.00075849897,0.00015495328,0.00023198761],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021565882,0.0002811441,0.0002830522,0.000096956406,0.00043607363,0.0007812304,0.0012597785,0.00013808391,0.0022242996],"category_scores_gemma":[0.00020229367,0.0001712414,0.00022500812,0.00037080614,0.0001524563,0.0006747794,0.00007754562,0.000809064,0.000038037633],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004974287,0.00057281245,0.5438338,0.000008453961,0.00009432029,0.0000107441465,0.4514106,0.000049905557,0.0008062328,0.00023366115,0.00060540007,0.0023243693],"study_design_scores_gemma":[0.0015062449,0.0020713834,0.7565621,0.00027438148,0.00007929908,0.0000013213473,0.23761442,0.00028561972,0.00048600757,0.0005585418,0.0001667983,0.00039389348],"about_ca_topic_score_codex":0.031859588,"about_ca_topic_score_gemma":0.03417153,"teacher_disagreement_score":0.21379615,"about_ca_system_score_codex":0.0009341819,"about_ca_system_score_gemma":0.0011939552,"threshold_uncertainty_score":0.9986878},"labels":[],"label_agreement":null},{"id":"W2028824355","doi":"10.1080/15434300801934751","title":"Comments on “Evaluation of the Usefulness of the<i>Versant for English</i>Test: A Response”: The Author Responds","year":2008,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Christian Studies","funders":"","keywords":"Test (biology); Psychology; English language; Language assessment; Mathematics education; Linguistics; Computer science; Cognitive psychology","score_opus":0.0786983967731293,"score_gpt":0.32736721141316966,"score_spread":0.24866881464004037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028824355","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917682,0.000042687778,0.00004743382,0.0015068197,0.0006475321,0.0006282856,0.00007133525,0.000029839282,0.0052579036],"genre_scores_gemma":[0.99516433,3.475844e-7,0.000040163388,0.00032800494,0.00021961717,0.00009087246,0.000008211459,0.000019507237,0.00412892],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99720395,0.0014268003,0.00031886247,0.00016551492,0.0007014611,0.00018342426],"domain_scores_gemma":[0.9974958,0.0013017133,0.00034465687,0.0006080061,0.00022886043,0.000021020962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002996123,0.00013883447,0.00017761216,0.00005501841,0.00075116183,0.0000536849,0.00044788053,0.000041488856,0.00019920766],"category_scores_gemma":[0.00045491112,0.000069236194,0.00018224209,0.00007175727,0.0002083104,0.00009493726,0.000028382805,0.0002999836,0.000002143958],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003670759,0.00037839255,0.0023879209,0.000046564754,0.00009628521,0.0000015616466,0.96114933,0.000096221265,0.002109016,0.021163382,0.0054749283,0.006729292],"study_design_scores_gemma":[0.0071722865,0.004920913,0.22146128,0.0009073002,0.00074761227,0.000012097074,0.61725986,0.006174871,0.0065080794,0.0016569182,0.13241075,0.0007680353],"about_ca_topic_score_codex":0.00018984119,"about_ca_topic_score_gemma":0.00022389773,"teacher_disagreement_score":0.3438895,"about_ca_system_score_codex":0.000070694645,"about_ca_system_score_gemma":0.0001481035,"threshold_uncertainty_score":0.57774055},"labels":[],"label_agreement":null},{"id":"W2096160735","doi":"10.1080/15434300701375832","title":"Three Generations of DIF Analyses: Considering Where It Has Been, Where It Is Now, and Where It Is Going","year":2007,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":386,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Differential item functioning; Contrast (vision); Psychology; Cognitive psychology; Item response theory; Econometrics; Computer science; Psychometrics; Artificial intelligence; Mathematics; Developmental psychology","score_opus":0.08492024923436474,"score_gpt":0.43632217501312276,"score_spread":0.351401925778758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096160735","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8150021,0.005624855,0.02692896,0.0475564,0.0011708331,0.000859707,0.00027627038,0.00014074078,0.102440126],"genre_scores_gemma":[0.97200865,0.00010370861,0.012140975,0.0066669993,0.0004935285,0.000086279004,0.00008568882,0.000054451568,0.008359737],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9969435,0.00014822744,0.000929441,0.0008176497,0.0005243055,0.0006369313],"domain_scores_gemma":[0.9979244,0.00045960903,0.00041425126,0.0007597716,0.00018678227,0.00025522424],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005792451,0.0004242767,0.0005519639,0.00019436434,0.00029841124,0.00022346096,0.00036125965,0.00028686778,0.014936084],"category_scores_gemma":[0.000010155658,0.0003789917,0.00020081022,0.0003921827,0.00018210987,0.0003079022,0.000047591442,0.00045617504,0.00024030608],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108164524,0.0017755528,0.24463987,0.0003096328,0.0014236233,0.000288283,0.06773006,0.0000059533186,0.02098111,0.004693085,0.62748015,0.030564517],"study_design_scores_gemma":[0.006072184,0.0033643518,0.53597885,0.00095244235,0.0008627624,0.00022675548,0.27813545,0.0004938076,0.00078557886,0.007092046,0.16364613,0.002389612],"about_ca_topic_score_codex":0.0010968356,"about_ca_topic_score_gemma":0.013014818,"teacher_disagreement_score":0.46383402,"about_ca_system_score_codex":0.000086950655,"about_ca_system_score_gemma":0.00011667453,"threshold_uncertainty_score":0.9998662},"labels":[],"label_agreement":null},{"id":"W2112485328","doi":"10.1080/15434303.2015.1010726","title":"Teachers’ Grading Decision Making: Multiple Influencing Factors and Methods","year":2015,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":138,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); Psychology; Mathematics education; English language; Multivariate analysis of variance; Statistics; Engineering; Mathematics","score_opus":0.04392888403571169,"score_gpt":0.44262896175885824,"score_spread":0.39870007772314653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112485328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9721803,0.00025679005,0.014739337,0.00013068932,0.00053192774,0.00031267287,0.000002428814,0.00017936283,0.011666475],"genre_scores_gemma":[0.9285433,0.000006457129,0.07078302,0.00011196886,0.00020828652,0.000016003172,0.000006128478,0.000021156378,0.00030365933],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9976478,0.0005109212,0.00029308398,0.00036638044,0.0006636434,0.0005181679],"domain_scores_gemma":[0.9984816,0.00079078367,0.00014999852,0.00023985007,0.00007483536,0.00026297013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002215324,0.00021650938,0.00028431753,0.0001521183,0.0004279438,0.00041469696,0.00030855194,0.00012700343,0.00009018436],"category_scores_gemma":[0.00025376683,0.00018725546,0.00007811721,0.0003026884,0.000115081486,0.0006288868,0.00006152047,0.00023380225,0.00001224679],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008713797,0.000048825998,0.52652055,0.000004065987,0.000034770295,0.000015180897,0.37655205,0.0000014970733,0.00092576176,0.0014289131,0.00029790003,0.094161764],"study_design_scores_gemma":[0.0009254496,0.00024675333,0.28736317,0.00006240925,0.00005070329,0.0000015854598,0.7060346,0.000321111,0.0000403012,0.0016912703,0.002886578,0.0003760849],"about_ca_topic_score_codex":0.002273368,"about_ca_topic_score_gemma":0.0018290747,"teacher_disagreement_score":0.32948256,"about_ca_system_score_codex":0.0002860255,"about_ca_system_score_gemma":0.00015201364,"threshold_uncertainty_score":0.7636056},"labels":[],"label_agreement":null},{"id":"W2955380721","doi":"10.1080/15434303.2019.1628238","title":"“Be a Machine”: International Graduate Students’ Narratives around High-Stakes English Tests","year":2019,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Test of English as a Foreign Language; Narrative; Test (biology); Agency (philosophy); Language proficiency; Mathematics education; Language assessment; Psychology; Pedagogy; Study abroad; Medical education; Sociology; Linguistics; Social science","score_opus":0.021598236431953518,"score_gpt":0.29817958750423507,"score_spread":0.27658135107228154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955380721","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92681,0.00013233842,0.00005877423,0.0004261753,0.0024795712,0.00025584293,0.00007167429,0.00030385653,0.06946173],"genre_scores_gemma":[0.9751648,0.0000017723975,0.0003771827,0.0007979156,0.0013350336,0.000034339926,0.0003271212,0.000044600787,0.021917263],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99807036,0.00019287257,0.0003211245,0.00042137605,0.0006477235,0.00034656387],"domain_scores_gemma":[0.9990793,0.00015026571,0.00018906785,0.000382428,0.0001171422,0.00008182456],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039107923,0.00028120645,0.00028837778,0.00017023804,0.00023666488,0.0010753952,0.00051706145,0.000050185627,0.009127589],"category_scores_gemma":[0.000024654644,0.00023727516,0.00012197983,0.000042138265,0.00007196659,0.00061918533,0.000040533476,0.0005262446,0.00018887609],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028323333,0.0003646926,0.01924434,0.000041938853,0.00033281714,0.000113375114,0.9229043,0.000010305706,0.0006247049,0.03789573,0.0010878168,0.017351668],"study_design_scores_gemma":[0.0018590101,0.0008046326,0.01574284,0.00009490437,0.000042059055,0.00000856458,0.9430533,0.00027989823,0.000025685462,0.0003666711,0.037115164,0.0006072807],"about_ca_topic_score_codex":0.0020528447,"about_ca_topic_score_gemma":0.0019349678,"teacher_disagreement_score":0.048354737,"about_ca_system_score_codex":0.000078403675,"about_ca_system_score_gemma":0.000032677337,"threshold_uncertainty_score":0.99996156},"labels":[],"label_agreement":null},{"id":"W2975930148","doi":"10.1080/15434303.2019.1671392","title":"Incorporating Translanguaging in Language Assessment: The Case of a Test for University Professors","year":2019,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Translanguaging; Operationalization; Active listening; Test (biology); Psychology; Task (project management); Competence (human resources); Mathematics education; Pedagogy; Computer science; Social psychology","score_opus":0.012807469388652586,"score_gpt":0.28008995809552417,"score_spread":0.2672824887068716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975930148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9737643,0.0001600327,0.00039753463,0.00027295935,0.00022565821,0.0007648789,0.00010232865,0.000091118265,0.024221165],"genre_scores_gemma":[0.99490947,4.5574996e-7,0.0011165367,0.0001370979,0.00017304042,0.00001987522,0.000074233474,0.000034258883,0.003535028],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9985888,0.00025659963,0.00034229658,0.0003160389,0.00015764628,0.00033860773],"domain_scores_gemma":[0.9984386,0.0007919899,0.00027704108,0.00039545065,0.000052417327,0.000044525055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086360617,0.00021137798,0.00032560554,0.00020004455,0.000262463,0.00012668045,0.00028571114,0.000059593884,0.00077589636],"category_scores_gemma":[0.000024384964,0.00016585753,0.00014084522,0.000117089316,0.000092201626,0.0003249333,0.000021632142,0.0004686462,0.000008716105],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003858461,0.0003515043,0.013175071,0.00045192448,0.00011059255,0.0015852621,0.83074576,0.000044189073,0.004901102,0.06497666,0.00007673892,0.08354262],"study_design_scores_gemma":[0.0018654477,0.0005292157,0.001471548,0.00015755609,0.00006228724,0.00006321251,0.9895734,0.0051733195,0.00006696027,0.00010119241,0.00063978723,0.00029606523],"about_ca_topic_score_codex":0.008453423,"about_ca_topic_score_gemma":0.018559638,"teacher_disagreement_score":0.15882766,"about_ca_system_score_codex":0.000082305014,"about_ca_system_score_gemma":0.00009434831,"threshold_uncertainty_score":0.9993491},"labels":[],"label_agreement":null},{"id":"W3111103222","doi":"10.1080/15434303.2020.1846190","title":"“Follow Your Interests Because Those Will Motivate You to Excel”: An Interview with Alister Cumming","year":2020,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; York University","funders":"","keywords":"Psychology; Library science; Computer science","score_opus":0.07021481758870055,"score_gpt":0.39532355855434204,"score_spread":0.32510874096564146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111103222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9738936,0.00007826358,0.003582457,0.014725638,0.00022792761,0.0003911186,0.00001504094,0.00028511148,0.006800854],"genre_scores_gemma":[0.9903906,0.000004129167,0.0040634964,0.0032253722,0.0008862569,0.000050516122,0.000044782657,0.00003492544,0.0012998976],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99799204,0.0004444034,0.00027277158,0.000449281,0.0004126303,0.00042888965],"domain_scores_gemma":[0.99901295,0.000063107684,0.00012182565,0.00028993413,0.000101547084,0.0004106613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063969847,0.00019628779,0.0002422146,0.000074746604,0.00028769457,0.00047060705,0.00039211518,0.0000685698,0.0003009987],"category_scores_gemma":[0.00005930223,0.00017364691,0.000065886095,0.0003112649,0.000057188186,0.00068413804,0.00002804325,0.00021109536,0.000057521454],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045085173,0.00029387733,0.009821521,0.000115527546,0.00006884174,0.000117750475,0.82655543,0.00000487225,0.003437066,0.0019152819,0.0018285427,0.15579619],"study_design_scores_gemma":[0.0014592257,0.0036205957,0.023371719,0.001162622,0.00014062006,0.000008629941,0.928805,0.00018854022,0.0004243159,0.00018511286,0.03956272,0.0010708821],"about_ca_topic_score_codex":0.0017531436,"about_ca_topic_score_gemma":0.0041236575,"teacher_disagreement_score":0.1547253,"about_ca_system_score_codex":0.000109255096,"about_ca_system_score_gemma":0.00013635578,"threshold_uncertainty_score":0.7081116},"labels":[],"label_agreement":null},{"id":"W3209416046","doi":"10.1080/15434303.2021.1992629","title":"The Relationship between Word Difficulty and Frequency: A Response to Hashimoto (2021)","year":2021,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Word lists by frequency; Correlation; Vocabulary; Rank (graph theory); Word (group theory); Linguistics; Psychology; Range (aeronautics); Mathematics; Statistics; Sentence; Philosophy","score_opus":0.01621099591469831,"score_gpt":0.3205802786497973,"score_spread":0.304369282735099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209416046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6749615,0.002377786,0.30444825,0.016908804,0.0001730063,0.00034764642,0.000013569683,0.00047091793,0.0002985394],"genre_scores_gemma":[0.7433425,0.0000016330154,0.255436,0.00024758987,0.00008125598,0.0000525474,0.000009437008,0.000012052594,0.00081697525],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979206,0.0004893631,0.0002960157,0.000521683,0.00040059708,0.0003717886],"domain_scores_gemma":[0.9969036,0.0017622225,0.00010130755,0.0009453963,0.00012047221,0.00016701242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008984907,0.00019380855,0.0001912975,0.00009390563,0.00042888432,0.00095909514,0.0007568303,0.00009353749,0.0000110308665],"category_scores_gemma":[0.00045957768,0.00014183333,0.000057214944,0.00068112224,0.00004796463,0.00046200125,0.00016929289,0.00036222686,0.000021677673],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066916626,0.00013175752,0.07032432,0.00006162352,0.0000910083,0.0010772339,0.032207377,5.6206136e-7,0.0735165,0.14572139,0.0025639597,0.6742374],"study_design_scores_gemma":[0.0009096138,0.00087102596,0.87949955,0.00028038438,0.0000504389,0.00012157482,0.004729796,0.00028665157,0.0056262156,0.10430716,0.0022882065,0.0010293693],"about_ca_topic_score_codex":0.00005300479,"about_ca_topic_score_gemma":0.00015762933,"teacher_disagreement_score":0.80917525,"about_ca_system_score_codex":0.000106883315,"about_ca_system_score_gemma":0.00019926995,"threshold_uncertainty_score":0.9248577},"labels":[],"label_agreement":null},{"id":"W4220982091","doi":"10.1080/15434303.2022.2038172","title":"Investigating the Effects of Task Type and Linguistic Background on Accuracy in Automated Speech Recognition Systems: Implications for Use in Language Assessment of Young Learners","year":2022,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Christian Studies; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Task (project management); Computer science; Natural language processing; Artificial intelligence; Meaning (existential); Task analysis; Language proficiency; Test (biology); Psychology; Speech recognition","score_opus":0.03373161378752211,"score_gpt":0.33916975486964335,"score_spread":0.30543814108212125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220982091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951417,0.000090349524,0.0030441184,0.00011552484,0.00024281653,0.00095241255,0.000050214447,0.000084512976,0.0002783866],"genre_scores_gemma":[0.9772757,0.0000055446485,0.022194156,0.00009742351,0.00002048904,0.00030248833,0.00007095152,0.000013802397,0.00001940587],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983001,0.00048524424,0.00044690174,0.0003127513,0.00025158952,0.00020342355],"domain_scores_gemma":[0.9968898,0.0022623956,0.00032458946,0.0003838889,0.000097594326,0.000041679457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079018733,0.0001376777,0.00025781782,0.00026324554,0.00009964306,0.00011978824,0.00031342683,0.00004047323,0.000007160274],"category_scores_gemma":[0.0004106816,0.00012087931,0.000041517083,0.000671074,0.00003731088,0.00021870252,0.00005566734,0.00020942511,7.998246e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007194033,0.0021771556,0.09075653,0.0023646506,0.00028932068,0.00021007737,0.07732934,0.0003813506,0.23979762,0.01711576,0.00050451874,0.56900173],"study_design_scores_gemma":[0.0038118262,0.003415609,0.5500887,0.0010225836,0.00010740898,0.00008704417,0.05579581,0.38040322,0.003116983,0.0013612872,0.00004726583,0.00074224157],"about_ca_topic_score_codex":0.0011615376,"about_ca_topic_score_gemma":0.00026694938,"teacher_disagreement_score":0.5682595,"about_ca_system_score_codex":0.00014996201,"about_ca_system_score_gemma":0.00013464934,"threshold_uncertainty_score":0.49293151},"labels":[],"label_agreement":null},{"id":"W4290958425","doi":"10.1080/15434303.2022.2073886","title":"Developing a Scenario-Based English Language Assessment in an Asian University","year":2022,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Language assessment; Linguistics; Language proficiency; Psychology; Mathematics education; Sociology; Computer science","score_opus":0.017125628697372018,"score_gpt":0.2795077938743099,"score_spread":0.2623821651769379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290958425","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9560176,0.00004801408,0.0010637884,0.00063810666,0.00050792494,0.00028124993,0.00005653458,0.0003691141,0.04101768],"genre_scores_gemma":[0.9937437,3.5535794e-7,0.0029019825,0.00045645615,0.00030926857,0.000024491059,0.0003074609,0.000039024668,0.0022172465],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9975241,0.00086232513,0.00026976623,0.00044255008,0.00045007063,0.0004512009],"domain_scores_gemma":[0.9992201,0.000088645415,0.00015433479,0.00038988062,0.00004854992,0.000098539385],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008401234,0.00023463991,0.00027340243,0.00034673736,0.00087332906,0.0003067803,0.00043073346,0.000041700074,0.0029728943],"category_scores_gemma":[0.000009299368,0.00025853977,0.00009371968,0.00014670653,0.00006157136,0.0004276185,0.000060554252,0.0009889649,0.000010061023],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042402455,0.000570468,0.010770613,0.00006672284,0.000049024122,0.0009867682,0.8673573,0.00036004215,0.00034922213,0.085664615,0.00028327352,0.03349951],"study_design_scores_gemma":[0.0014434962,0.00088007434,0.009062035,0.00005364723,0.00002917051,0.0000030680935,0.9456292,0.003114318,0.000007014879,0.00007223843,0.03919638,0.0005093745],"about_ca_topic_score_codex":0.002901461,"about_ca_topic_score_gemma":0.0091610635,"teacher_disagreement_score":0.08559238,"about_ca_system_score_codex":0.00071233045,"about_ca_system_score_gemma":0.0003705552,"threshold_uncertainty_score":0.9999867},"labels":[],"label_agreement":null},{"id":"W4323544073","doi":"10.1080/15434303.2023.2184266","title":"Aligning Language Frameworks: An Example with the CLB and CEFR","year":2023,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Rasch model; Benchmarking; Dimension (graph theory); Computer science; German; Argument (complex analysis); Linguistics; Vocabulary; Certificate; Natural language processing; Computational linguistics; Language proficiency; Artificial intelligence; Psychology; Mathematics education","score_opus":0.020053347554890008,"score_gpt":0.2752021690098073,"score_spread":0.2551488214549173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323544073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98499936,0.000317055,0.00037322933,0.0007247393,0.00016263138,0.00018426172,0.000016342996,0.0005715318,0.012650873],"genre_scores_gemma":[0.9922587,0.000002258946,0.00039048135,0.0011661125,0.0008330718,0.000046719855,0.00013170303,0.000050899613,0.0051200446],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99860454,0.00021434423,0.00016218625,0.0003529482,0.0002666618,0.0003993184],"domain_scores_gemma":[0.9990612,0.0002692427,0.00009699659,0.0004512317,0.000030969717,0.00009036184],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005484178,0.00021337993,0.00019696393,0.00011496052,0.000624606,0.0007486553,0.00022500851,0.00007595622,0.0011319135],"category_scores_gemma":[0.000008406101,0.00013238142,0.00004451845,0.000096679425,0.0001385073,0.00036502833,0.00002646692,0.0006493533,0.00006871385],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010807751,0.000039645187,0.0004961847,0.000030010231,0.00007648129,0.0002267584,0.85252565,0.000010972489,0.0005724882,0.024961041,0.0013793797,0.1196706],"study_design_scores_gemma":[0.00047856328,0.00065841695,0.002713481,0.00006172082,0.00005636114,0.000020709667,0.9796958,0.0009874803,0.000025678997,0.00013030057,0.014838349,0.00033314317],"about_ca_topic_score_codex":0.0068398723,"about_ca_topic_score_gemma":0.0074101295,"teacher_disagreement_score":0.12717016,"about_ca_system_score_codex":0.000019816887,"about_ca_system_score_gemma":0.000024700665,"threshold_uncertainty_score":0.9997812},"labels":[],"label_agreement":null},{"id":"W4385361752","doi":"10.1080/15434303.2023.2237487","title":"The Canadian English Language Proficiency Index Program (CELPIP) Test","year":2023,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Index (typography); Language proficiency; Language assessment; Test (biology); Linguistics; Test of English as a Foreign Language; Psychology; Mathematics education; Computer science; Programming language","score_opus":0.012615323848987793,"score_gpt":0.2915964155539256,"score_spread":0.27898109170493784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385361752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7016331,0.00023853443,0.000009463056,0.0013359948,0.0012245011,0.000737383,0.000054041277,0.0016291314,0.29313788],"genre_scores_gemma":[0.96853024,0.0000023460404,0.000053807158,0.00018367184,0.0011217261,0.00017599521,0.000119110045,0.00004315991,0.02976993],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9981971,0.00014577837,0.0002538466,0.00029664556,0.00038213673,0.0007244915],"domain_scores_gemma":[0.99894357,0.00026845478,0.00009821641,0.0004298486,0.00008449742,0.00017543157],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008037756,0.0002058801,0.00015940961,0.00017783919,0.0018049335,0.0013914219,0.00041221816,0.00006504244,0.00054892065],"category_scores_gemma":[0.00010668666,0.00014585479,0.000090818154,0.00016391082,0.00016095462,0.00020409591,0.00002243013,0.0005807744,0.00031857705],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033533292,0.00012892325,0.008477188,0.000037826587,0.000044992987,0.00020954717,0.71348065,0.0000057581938,0.000082322,0.026966166,0.010389412,0.24017386],"study_design_scores_gemma":[0.0004213448,0.00082571956,0.015323765,0.00005514741,0.000028852332,0.0000036005451,0.5988744,0.0022689223,0.000009045413,0.00016873321,0.38157266,0.0004478384],"about_ca_topic_score_codex":0.10127063,"about_ca_topic_score_gemma":0.60431045,"teacher_disagreement_score":0.50303984,"about_ca_system_score_codex":0.00012909702,"about_ca_system_score_gemma":0.00022128182,"threshold_uncertainty_score":0.99964523},"labels":[],"label_agreement":null},{"id":"W4389294437","doi":"10.1080/15434303.2023.2288253","title":"Validity Arguments for Automated Essay Scoring of Young Students’ Writing Traits","year":2023,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Writing assessment; Consistency (knowledge bases); Context (archaeology); Vocabulary; Psychology; Inference; Argument (complex analysis); Formative assessment; Trait; Artificial intelligence; Natural language processing; Computer science; Mathematics education; Linguistics","score_opus":0.0296680655231284,"score_gpt":0.359881211422216,"score_spread":0.3302131458990876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389294437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7880567,0.0000082329,0.21014544,0.000118065574,0.00021573852,0.00041297945,0.000019947405,0.00081962656,0.00020327186],"genre_scores_gemma":[0.9802725,9.708205e-7,0.019339617,0.000026061021,0.000052083265,0.00011176667,0.00004693149,0.000011963748,0.00013811055],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982348,0.000121939825,0.00042179416,0.00039788726,0.0004916967,0.00033186068],"domain_scores_gemma":[0.99897623,0.00022959757,0.00018459039,0.00045338183,0.0000901913,0.00006602624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011132472,0.00013931212,0.0002202543,0.0001334027,0.00013037985,0.00021621247,0.0007928991,0.000058463575,0.000006747511],"category_scores_gemma":[0.00002646708,0.0001383288,0.0000959745,0.00046959732,0.000021383024,0.00051827735,0.00006507311,0.0000880709,0.000014305362],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033116816,0.0014770799,0.15367603,0.0010317528,0.00025305885,0.00007972993,0.093690924,0.0002957399,0.19971862,0.033600073,0.0010069781,0.5151369],"study_design_scores_gemma":[0.0011157865,0.0006074037,0.8524105,0.00010034975,0.00002777803,0.0000062145377,0.0050720507,0.13514766,0.0036421674,0.00149702,0.00004980215,0.00032325735],"about_ca_topic_score_codex":0.00006737553,"about_ca_topic_score_gemma":0.000034188684,"teacher_disagreement_score":0.69873446,"about_ca_system_score_codex":0.00009068496,"about_ca_system_score_gemma":0.00007510196,"threshold_uncertainty_score":0.56408846},"labels":[],"label_agreement":null},{"id":"W4391927924","doi":"10.1080/15434303.2024.2311724","title":"The Development and Initial Validation of O-WSVLT, a Meaning-Recall Online L2 Spanish Vocabulary Levels Test","year":2024,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Psychology; Meaning (existential); Vocabulary; Linguistics; Test (biology); Language proficiency; Recall; Vocabulary development; Cognitive psychology; Mathematics education","score_opus":0.023606083092814454,"score_gpt":0.3639875715569394,"score_spread":0.3403814884641249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391927924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9802194,0.0039480245,0.0026860163,0.00039125822,0.00063822925,0.0002564985,0.000053784046,0.00017684071,0.011629909],"genre_scores_gemma":[0.99496794,0.0000022689694,0.0021626435,0.0005738481,0.00029875364,0.000036761747,0.00017247282,0.00003400696,0.0017513115],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99847263,0.00020133377,0.0004479366,0.00033689736,0.00026001615,0.00028120232],"domain_scores_gemma":[0.99884045,0.0006298001,0.000115522686,0.00029071313,0.000049469174,0.00007407299],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00058590685,0.00018323882,0.0001926645,0.000114203256,0.00015167384,0.00019016628,0.00016933946,0.0000960251,0.004454937],"category_scores_gemma":[0.0000334276,0.00014004216,0.00006041227,0.00018171233,0.00006484816,0.00014362553,0.000026279498,0.00030959694,0.000071118164],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045239696,0.0003899719,0.0011381331,0.00015868721,0.00042560566,0.00073849555,0.20166372,0.0000029736934,0.010968535,0.009408382,0.0015148867,0.7735454],"study_design_scores_gemma":[0.005472224,0.004472151,0.3194526,0.0011729818,0.0005094934,0.0008546462,0.58365446,0.002372616,0.012133285,0.001243798,0.06651432,0.0021473642],"about_ca_topic_score_codex":0.00008839235,"about_ca_topic_score_gemma":0.000095135685,"teacher_disagreement_score":0.771398,"about_ca_system_score_codex":0.00004589388,"about_ca_system_score_gemma":0.00009852782,"threshold_uncertainty_score":0.99645513},"labels":[],"label_agreement":null},{"id":"W4396694688","doi":"10.1080/15434303.2024.2346089","title":"The Academic Achievement of Undergraduate Students with Different English Language Proficiency Profiles","year":2024,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"York University","keywords":"Language proficiency; Mathematics education; Academic achievement; Psychology; Language assessment","score_opus":0.009969094360222603,"score_gpt":0.28885734732641716,"score_spread":0.27888825296619457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396694688","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98698825,0.0026339213,0.0001966714,0.000551855,0.00068083813,0.0004715573,0.000033850072,0.0003219009,0.008121135],"genre_scores_gemma":[0.9882254,0.000016386848,0.0000450051,0.00008479388,0.0005992431,0.00010832176,0.000058384558,0.000046376965,0.0108160665],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9979455,0.00020307554,0.000389423,0.0003599794,0.00068832276,0.00041371942],"domain_scores_gemma":[0.99908984,0.00026144632,0.00014737897,0.00037863172,0.00005433141,0.000068356596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005094784,0.00027347266,0.00024924666,0.00011875537,0.00038131682,0.0006480062,0.0004930673,0.000049876442,0.000258537],"category_scores_gemma":[0.000014942898,0.0001474507,0.00010735421,0.000078203295,0.00018158392,0.00024293612,0.00004465547,0.00070189836,0.000017539687],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000386411,0.00026819765,0.0060617905,0.0003299014,0.0004170667,0.00013687453,0.726674,0.000004670115,0.0012602413,0.1622972,0.0005211754,0.10199022],"study_design_scores_gemma":[0.0011283745,0.0024212364,0.0068474724,0.000861092,0.00027622396,0.000010612025,0.97542864,0.0006163207,0.0009117102,0.0005649865,0.0102271335,0.0007062203],"about_ca_topic_score_codex":0.00045177722,"about_ca_topic_score_gemma":0.00085360795,"teacher_disagreement_score":0.2487546,"about_ca_system_score_codex":0.00007014588,"about_ca_system_score_gemma":0.000057258578,"threshold_uncertainty_score":0.6248739},"labels":[],"label_agreement":null},{"id":"W4399443232","doi":"10.1080/15434303.2024.2364172","title":"Adapting to a New Normal: A Review of <i>Technology Assisted Language Assessment in Diverse Contexts</i>","year":2024,"lang":"en","type":"review","venue":"Language Assessment Quarterly","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Language assessment; Psychology; Computer science; Linguistics; Mathematics education","score_opus":0.05299991408977252,"score_gpt":0.4712575397084361,"score_spread":0.4182576256186636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399443232","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024745357,0.9700064,0.00033762792,0.0010134946,0.0017645382,0.00266862,0.00033269546,0.00023443032,0.02339474],"genre_scores_gemma":[0.0007106119,0.9723353,0.008967584,0.0021496336,0.00059424527,0.0018159028,0.000927054,0.00018852494,0.012311164],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99377877,0.000838128,0.0022736352,0.0014485429,0.0007373664,0.0009235708],"domain_scores_gemma":[0.99669176,0.00041799495,0.0009867125,0.0014292479,0.00011274276,0.00036153125],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012195767,0.0009945481,0.0031806498,0.00120721,0.000057017205,0.00008725081,0.0012653851,0.0006757113,0.005208087],"category_scores_gemma":[0.000050818544,0.0007797022,0.0008569763,0.0026279248,0.000082066224,0.00013964082,0.00019929619,0.0018577334,0.0009801629],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000101819705,0.00076590275,0.000076684315,0.026026962,0.0005116272,0.00078190386,0.003198119,5.2868206e-8,0.000012038822,0.0030319374,0.025289992,0.9402946],"study_design_scores_gemma":[0.0010045249,0.0015433242,0.0008703185,0.14115502,0.0019141703,0.00024142905,0.015845092,9.595494e-7,3.7773657e-7,0.00019565721,0.83597505,0.0012540941],"about_ca_topic_score_codex":0.0010961982,"about_ca_topic_score_gemma":0.00025575797,"teacher_disagreement_score":0.9390405,"about_ca_system_score_codex":0.00042641922,"about_ca_system_score_gemma":0.0009391439,"threshold_uncertainty_score":0.9997977},"labels":[],"label_agreement":null},{"id":"W4405148704","doi":"10.1080/15434303.2024.2438142","title":"The Academic Achievement of Undergraduate Students with Different TOEFL iBT Score Profiles: A Replication Study","year":2024,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"York University","keywords":"Test of English as a Foreign Language; Replication (statistics); Psychology; Mathematics education; Academic achievement; Language assessment; Statistics; Mathematics","score_opus":0.012464814340156248,"score_gpt":0.349279442253663,"score_spread":0.33681462791350675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405148704","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94913685,0.00024218275,0.0436085,0.0060203727,0.00013820987,0.00057412084,0.0000035157939,0.000195934,0.00008030186],"genre_scores_gemma":[0.9977668,0.000016608965,0.0009135941,0.00004804061,0.00007220569,0.00008784634,0.000011541217,0.000015802667,0.0010675646],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978987,0.00019157851,0.00035017869,0.0005156952,0.0007971546,0.00024671864],"domain_scores_gemma":[0.9985532,0.00014719572,0.00014897446,0.0010264011,0.0000648014,0.000059415317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060873746,0.00017958687,0.00018437201,0.0000829928,0.00013842437,0.00038191667,0.0010243072,0.000038488834,0.0000015992972],"category_scores_gemma":[0.000008750815,0.00010056378,0.00005236595,0.00043119842,0.0000371502,0.00020625647,0.00010012786,0.00042612213,0.000007986389],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055843702,0.0031235146,0.351705,0.0003883801,0.0013089428,0.00026471444,0.060447086,0.00018421185,0.005221935,0.08809556,0.000703849,0.48850095],"study_design_scores_gemma":[0.0031731636,0.019345336,0.7479639,0.0014369416,0.0005008889,0.00003749141,0.0498673,0.16515972,0.0011355012,0.00935493,0.0007807754,0.0012440672],"about_ca_topic_score_codex":0.00005202865,"about_ca_topic_score_gemma":0.000058354413,"teacher_disagreement_score":0.48725688,"about_ca_system_score_codex":0.00007472916,"about_ca_system_score_gemma":0.00009430547,"threshold_uncertainty_score":0.4100872},"labels":[],"label_agreement":null},{"id":"W4406605978","doi":"10.1080/15434303.2024.2448963","title":"Test Takers’ Attitudes Toward Varieties of Accents in Listening Tasks of the Duolingo English Test (2021 test version)","year":2025,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Linguistics, Language Diversity, and Identity","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Test (biology); Active listening; Psychology; Communication","score_opus":0.010048740647190942,"score_gpt":0.2588661768107817,"score_spread":0.24881743616359078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406605978","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9665318,0.00035975687,0.000034634377,0.0000760426,0.005715716,0.00036764468,0.00046786727,0.0000544208,0.026392091],"genre_scores_gemma":[0.9956277,0.000013117397,0.0001515512,0.00012282559,0.0011049458,0.00000719656,0.00004360715,0.000013254144,0.0029157754],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998526,0.000069777896,0.0004679498,0.00028061788,0.00037697697,0.000278703],"domain_scores_gemma":[0.9977451,0.0006314099,0.00027265763,0.0004438197,0.00086552015,0.00004149758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003020353,0.00020554216,0.0003669812,0.00018617114,0.00019199176,0.0001939405,0.00055826415,0.00007767183,0.0008006198],"category_scores_gemma":[0.002744091,0.00016972098,0.00016309894,0.00015414512,0.00027455462,0.00024300945,0.00015419081,0.00026720812,0.000009213869],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013088586,0.00094912306,0.7698497,0.00043294556,0.0000952595,0.000027442577,0.22034661,0.0000035761184,0.00031054212,0.0038170826,0.0031640225,0.0009905933],"study_design_scores_gemma":[0.0022279383,0.00061802834,0.50721765,0.00086964975,0.0003499447,3.6639005e-7,0.4821713,0.00018526711,0.0009926008,0.00064782676,0.0042114896,0.00050798233],"about_ca_topic_score_codex":0.0048520383,"about_ca_topic_score_gemma":0.004575317,"teacher_disagreement_score":0.2626321,"about_ca_system_score_codex":0.00009768789,"about_ca_system_score_gemma":0.00013647754,"threshold_uncertainty_score":0.8766225},"labels":[],"label_agreement":null},{"id":"W4406929912","doi":"10.1080/15434303.2025.2458599","title":"From Global Dependence to Local Expertise: An Interview with Rama Mathew","year":2025,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Education and Islamic Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Regional science; Economic geography; Sociology; Geography","score_opus":0.015369465846946137,"score_gpt":0.3964436286729267,"score_spread":0.38107416282598056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406929912","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80272025,0.00078196655,0.10900621,0.013840962,0.00075426034,0.0004702231,0.000025826728,0.00020742386,0.072192855],"genre_scores_gemma":[0.9912912,0.000010786776,0.0034835115,0.0028265656,0.00016190836,0.00007356388,0.000010292581,0.000005379371,0.002136775],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9987579,0.00023534293,0.00016136402,0.00029539687,0.0002887861,0.00026120315],"domain_scores_gemma":[0.99945354,0.000053220585,0.000042527277,0.00027491341,0.00006750633,0.0001082739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025607453,0.000120031174,0.0001694081,0.000035932924,0.00020189333,0.00017004421,0.00033384212,0.00004786521,0.00055579294],"category_scores_gemma":[0.000013845339,0.00009907395,0.00003449775,0.0003177922,0.00010140863,0.00021150672,0.000022932585,0.00007492613,0.00006289251],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017955601,0.00028252613,0.005664908,0.00001437997,0.00008029569,0.000027428814,0.26261654,0.0000013256125,0.00011458232,0.027891524,0.0050824275,0.6982061],"study_design_scores_gemma":[0.0004671528,0.0004263719,0.05648994,0.00022856353,0.000044036562,9.056248e-7,0.92198694,0.000062440915,0.00004190131,0.0021591051,0.017811406,0.00028125153],"about_ca_topic_score_codex":0.013289421,"about_ca_topic_score_gemma":0.027379991,"teacher_disagreement_score":0.69792485,"about_ca_system_score_codex":0.00027629067,"about_ca_system_score_gemma":0.00026168613,"threshold_uncertainty_score":0.9932812},"labels":[],"label_agreement":null},{"id":"W4407098810","doi":"10.1080/15434303.2025.2455196","title":"Differential Item Functioning Due to Cultural Familiarity on a Large-Scale Reading Test: Does the Length of Residence Matter?","year":2025,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Differential item functioning; Psychology; Reading (process); Scale (ratio); Test (biology); Residence; Item response theory; Psychometrics; Developmental psychology; Linguistics; Geography; Sociology; Demography","score_opus":0.07156230965493464,"score_gpt":0.4314743672554329,"score_spread":0.35991205760049827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407098810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9002083,0.0000388525,0.08772122,0.00143408,0.0008612484,0.00027546682,0.000029869521,0.000059552323,0.009371401],"genre_scores_gemma":[0.9884573,0.0000016838775,0.007358666,0.00057042844,0.00011802593,0.000033598317,0.0000037220857,0.000007793355,0.003448737],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967728,0.00060523255,0.0007084486,0.00059009343,0.0009425812,0.00038080904],"domain_scores_gemma":[0.9796287,0.01891887,0.00030373118,0.0008863478,0.00019035429,0.00007202741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026358694,0.00019760913,0.00041614965,0.00038167898,0.00034887152,0.0004043621,0.00089542015,0.000076025804,0.0004235713],"category_scores_gemma":[0.006917705,0.00009908403,0.00014641254,0.0017856214,0.000058051897,0.00022424984,0.00012690744,0.00031463918,0.000043804983],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009287456,0.00029886523,0.71061397,0.00004427918,0.00006531377,0.000036284157,0.01502431,0.000031768654,0.024955917,0.0020645247,0.011521459,0.23525043],"study_design_scores_gemma":[0.0003476424,0.00044014264,0.934936,0.00016739138,0.000026726811,0.0000055333385,0.05745522,0.002297265,0.0011440403,0.002765784,0.0002525607,0.00016169458],"about_ca_topic_score_codex":0.0003421109,"about_ca_topic_score_gemma":0.0001998626,"teacher_disagreement_score":0.23508874,"about_ca_system_score_codex":0.000062662126,"about_ca_system_score_gemma":0.00003928794,"threshold_uncertainty_score":0.82816386},"labels":[],"label_agreement":null},{"id":"W4410015948","doi":"10.1080/15434303.2025.2497818","title":"On the Interplay Between Conceptions of Assessment and Assessment Agency: Perspectives of Iranian EFL Preservice Teachers","year":2025,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Mathematics education; Pedagogy; Agency (philosophy); Psychology; Alternative assessment; Semi-structured interview; Qualitative research; Sociology; Social science","score_opus":0.017476476578897192,"score_gpt":0.4119940254646767,"score_spread":0.39451754888577956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410015948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8479688,0.00022318623,0.0020148205,0.0038874864,0.00021555899,0.00094161415,0.000051983712,0.00006195569,0.1446346],"genre_scores_gemma":[0.9957344,0.00006212567,0.0021840308,0.00014146756,0.00011399222,0.00009997735,0.00002124134,0.00001787504,0.0016248949],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9966862,0.00090709626,0.000596832,0.00046377914,0.0008885299,0.0004575244],"domain_scores_gemma":[0.9974739,0.0012755727,0.00039100883,0.00056113536,0.00019313155,0.000105253974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017433671,0.00028250107,0.000517161,0.00023046279,0.0004996376,0.0001572197,0.0007528146,0.00014336954,0.0006956308],"category_scores_gemma":[0.00004457453,0.0002212195,0.00018469631,0.000578091,0.0005743835,0.00029499936,0.00011437288,0.0004928942,0.0000034877862],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024332732,0.0007222304,0.22937746,0.00009805688,0.0007415653,0.0000065674963,0.3489155,0.000004347066,0.0035698793,0.39210847,0.0012569814,0.023174599],"study_design_scores_gemma":[0.0007276802,0.00052838074,0.56086797,0.00017533246,0.00017187085,1.4438429e-7,0.43417472,0.00007823697,0.00004469846,0.002535828,0.00050051307,0.00019466419],"about_ca_topic_score_codex":0.0022795077,"about_ca_topic_score_gemma":0.0009944428,"teacher_disagreement_score":0.38957265,"about_ca_system_score_codex":0.000330875,"about_ca_system_score_gemma":0.0005849473,"threshold_uncertainty_score":0.9021069},"labels":[],"label_agreement":null}]}