{"meta":{"query_hash":"ec1f2ca963e3","filters":{"venue":"Language Testing in Asia"},"cohort_total":12,"direct_labels_cover":0,"predictions_cover":12,"exported":12,"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/ec1f2ca963e3","api":"https://metacan.xera.ac/api/v1/cohort?venue=Language+Testing+in+Asia"},"results":[{"id":"W1569132542","doi":"10.1186/s40468-015-0020-6","title":"Chinese university students’ perceptions of assessment tasks and classroom assessment environment","year":2015,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":29,"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":"Psychology; Learning environment; Context (archaeology); Perception; Mathematics education; Formative assessment; Scale (ratio); Pedagogy","score_opus":0.028109092519047394,"score_gpt":0.3653477989662329,"score_spread":0.33723870644718545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569132542","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":[0.9419419,0.00005137185,0.0002485311,0.00020581215,0.00008667508,0.00027220027,0.00000679497,0.000049805247,0.057136897],"genre_scores_gemma":[0.97824585,0.000027115608,0.020577317,0.000016425585,0.00006138612,0.000004238641,0.000008887506,0.00000886621,0.0010499203],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983996,0.00026047515,0.000193727,0.00023836593,0.0006561989,0.00025160247],"domain_scores_gemma":[0.9993121,0.00020936469,0.00012275977,0.00017017771,0.0000404026,0.00014521285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010369428,0.00012500619,0.00020326526,0.00011173711,0.0001617467,0.000052068808,0.00030226546,0.00007039295,0.00013340233],"category_scores_gemma":[0.00012812347,0.0001241186,0.00003318454,0.00032400366,0.00018474406,0.00016649706,0.00021501459,0.00018707944,0.000007998821],"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":[0.0000039356037,0.00020671145,0.97881746,0.000006567232,0.000013543161,0.000027102884,0.018329524,0.000036725978,0.00047793344,0.0006787766,0.00006474539,0.0013369817],"study_design_scores_gemma":[0.00074924243,0.00007007319,0.8975031,0.00002637691,0.000019450987,8.8467317e-7,0.10085373,0.00023987185,0.0000010310321,0.00010820738,0.0003066649,0.00012139339],"about_ca_topic_score_codex":0.002242851,"about_ca_topic_score_gemma":0.0009390415,"teacher_disagreement_score":0.08252421,"about_ca_system_score_codex":0.000412319,"about_ca_system_score_gemma":0.00016235102,"threshold_uncertainty_score":0.50614095},"labels":[],"label_agreement":null},{"id":"W1921505225","doi":"10.1186/s40468-015-0018-0","title":"Raising the bar: language testing experience and second language motivation among South Korean young adolescents","year":2015,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Multilingual Education and Policy","field":"Social Sciences","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":"Carleton University; University of British Columbia","funders":"","keywords":"Psychology; Language assessment; Test (biology); Exploratory factor analysis; Salient; Context (archaeology); Language proficiency; Language education; Developmental psychology; Mathematics education; Pedagogy; Social psychology; Psychometrics","score_opus":0.10666736387976755,"score_gpt":0.4019436657537405,"score_spread":0.29527630187397297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1921505225","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":[0.9562259,0.00025155875,0.000017014818,0.00009724402,0.00022729707,0.00029917737,0.000005636289,0.0001872283,0.042688943],"genre_scores_gemma":[0.99681675,6.188339e-7,0.0011436093,0.00026915115,0.0005653978,0.000017614266,0.000007544709,0.000024694868,0.0011546317],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99828106,0.00031057923,0.00029223497,0.0003105471,0.0003516006,0.00045397028],"domain_scores_gemma":[0.998784,0.00044895645,0.00019657152,0.00026057093,0.00009759096,0.00021227835],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011966518,0.00017272934,0.0001635759,0.00011655189,0.00037900795,0.00023367567,0.0002965634,0.0000952475,0.00007031806],"category_scores_gemma":[0.011782215,0.00014661031,0.00002505532,0.0006690885,0.00028180704,0.00027181406,0.000083474864,0.00030700333,0.000018758605],"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":[0.0000023868035,0.000015818472,0.44794965,0.000012832717,0.0000014402526,0.000016317985,0.54195756,0.0000078934045,0.0008383516,0.00004456532,0.000021388201,0.009131786],"study_design_scores_gemma":[0.0004066693,0.000015661584,0.4924166,0.00026427422,0.0000071565623,0.000010668844,0.5053908,0.0007270044,0.00043174226,0.00003614063,0.000063184314,0.00023009833],"about_ca_topic_score_codex":0.023582721,"about_ca_topic_score_gemma":0.0043446505,"teacher_disagreement_score":0.044466935,"about_ca_system_score_codex":0.00012255972,"about_ca_system_score_gemma":0.0001959123,"threshold_uncertainty_score":0.996542},"labels":[],"label_agreement":null},{"id":"W2112346409","doi":"10.1186/s40468-015-0016-2","title":"How language proficiency contributes to Chinese students’ academic success in Korean universities","year":2015,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Grit, Self-Efficacy, and Motivation","field":"Psychology","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":"Queen's University","funders":"","keywords":"Psychology; Language proficiency; Test of English as a Foreign Language; Academic achievement; Medical education; Graduate students; Mathematics education; English language; Pedagogy; Medicine","score_opus":0.03571550564783218,"score_gpt":0.36311434997557873,"score_spread":0.3273988443277466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112346409","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":[0.9902109,0.0006793257,0.00010907958,0.00070848566,0.00028172162,0.00052329875,0.000014413352,0.00018137213,0.0072914353],"genre_scores_gemma":[0.9963127,7.97734e-7,0.00039094035,0.00023156793,0.0001416545,0.00002676031,0.000040175004,0.000023554927,0.0028318488],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99853355,0.0001854125,0.00023528349,0.000353833,0.0002566888,0.00043523073],"domain_scores_gemma":[0.9991309,0.00030961013,0.0001003799,0.00027609113,0.00007182575,0.00011117865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006558978,0.00018760344,0.00024719755,0.00040712635,0.000040539646,0.00006347328,0.00048711372,0.00015315117,0.000016500238],"category_scores_gemma":[0.0011376081,0.00017304742,0.000025297197,0.00089388265,0.000046062527,0.00016736146,0.00012199712,0.00041076788,0.0000339168],"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":[0.000044063385,0.00018815912,0.91316634,0.000016118911,0.000009500326,0.00022607803,0.08126364,0.000039565773,0.0018813326,0.0003128351,0.00047342412,0.0023789608],"study_design_scores_gemma":[0.0019268449,0.00009083447,0.90623516,0.00011325341,0.000007756833,0.000011355362,0.0910452,0.00005630235,0.000190618,0.000058382,0.00007698336,0.0001873254],"about_ca_topic_score_codex":0.0032616223,"about_ca_topic_score_gemma":0.0010285449,"teacher_disagreement_score":0.009781558,"about_ca_system_score_codex":0.00021577918,"about_ca_system_score_gemma":0.000062465486,"threshold_uncertainty_score":0.7056669},"labels":[],"label_agreement":null},{"id":"W2886638441","doi":"10.1186/s40468-018-0065-4","title":"How does anxiety influence language performance? From the perspectives of foreign language classroom anxiety and cognitive test anxiety","year":2018,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":175,"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":"Anxiety; Psychology; Test anxiety; Foreign language; Test (biology); Foreign language anxiety; Cognition; Developmental psychology; Language assessment; Clinical psychology; Consistency (knowledge bases); Mathematics education; Psychiatry","score_opus":0.012529891190225325,"score_gpt":0.2365920863830132,"score_spread":0.2240621951927879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886638441","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":[0.9707579,0.001771053,0.000013989029,0.0001464094,0.00007345172,0.00026076057,0.00013995367,0.00019399717,0.02664248],"genre_scores_gemma":[0.99671924,0.000040890285,0.0008657102,0.00018063775,0.0009854918,0.00002039047,0.00003309478,0.000044443066,0.0011100936],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9983842,0.0001817979,0.00028000132,0.0004660888,0.00026686842,0.0004210918],"domain_scores_gemma":[0.9980743,0.0010804557,0.00025306878,0.0003466776,0.00017787654,0.0000676016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005953672,0.00029938732,0.00031620642,0.00008493106,0.00049402716,0.00029733567,0.0003020028,0.00009487068,0.00021611684],"category_scores_gemma":[0.0023562128,0.00019354207,0.00006983305,0.00016081882,0.0007944602,0.00040583522,0.00014507085,0.00066044537,0.000012176776],"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":[0.000020997093,0.000058068104,0.42444262,0.000049036993,0.00002942727,0.000009619511,0.54060316,0.0000025543804,0.005143813,0.00038288077,0.00004656493,0.029211253],"study_design_scores_gemma":[0.0006721328,0.00019156569,0.1680066,0.00062513317,0.00006940213,0.000022666209,0.82569396,0.00093195494,0.002693045,0.00010065568,0.0006195605,0.0003732985],"about_ca_topic_score_codex":0.0044018757,"about_ca_topic_score_gemma":0.003528976,"teacher_disagreement_score":0.28509083,"about_ca_system_score_codex":0.000039549344,"about_ca_system_score_gemma":0.000041677275,"threshold_uncertainty_score":0.7892417},"labels":[],"label_agreement":null},{"id":"W2923578044","doi":"10.1186/s40468-019-0078-7","title":"The language assessment literacy needs of Iranian EFL teachers with a focus on reformed assessment policies","year":2019,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":59,"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":"Rubric; Psychology; Literacy; Curriculum; Pedagogy; Active listening; Mathematics education; Language assessment; Alternative assessment; Perception; Focus group; Sociology","score_opus":0.016486939779852855,"score_gpt":0.3597537479867195,"score_spread":0.3432668082068666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923578044","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":[0.73854375,0.000086236636,0.000011115717,0.0008582077,0.00010694401,0.00047829407,0.0000032763596,0.00008218337,0.25983],"genre_scores_gemma":[0.9922814,0.000008688894,0.00398759,0.00010257393,0.00012386173,0.000039190592,0.0000059089452,0.00002603912,0.0034247441],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99787766,0.00027869164,0.00033678685,0.0002079076,0.0007577382,0.00054124225],"domain_scores_gemma":[0.99822253,0.00095411635,0.00026533718,0.000401505,0.00007523277,0.00008127846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012979126,0.00020248181,0.0002800356,0.00018488336,0.00027335342,0.00020277839,0.0005256163,0.00008174123,0.000090272304],"category_scores_gemma":[0.00021551726,0.00013157044,0.00006249021,0.00095696683,0.00017420146,0.00020029148,0.00008140898,0.0003746251,0.000018236964],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002767608,0.00015224538,0.7561647,0.000022006652,0.000041083946,0.000022920834,0.20572098,0.000023045031,0.0023872466,0.0082842,0.000059402446,0.027094468],"study_design_scores_gemma":[0.001109891,0.0003988157,0.66257334,0.00031725364,0.000024641091,0.000002201009,0.33428672,0.00016493916,0.00014020417,0.00011619222,0.0006004857,0.00026531573],"about_ca_topic_score_codex":0.008235031,"about_ca_topic_score_gemma":0.0026889099,"teacher_disagreement_score":0.25640526,"about_ca_system_score_codex":0.00034717194,"about_ca_system_score_gemma":0.0002686807,"threshold_uncertainty_score":0.9983692},"labels":[],"label_agreement":null},{"id":"W2967888896","doi":"10.1186/s40468-019-0089-4","title":"Critical review of validation models and practices in language testing: their limitations and future directions for validation research","year":2019,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":46,"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":"Argument (complex analysis); Empirical research; Construct (python library); Computer science; Test (biology); Construct validity; Language assessment; Management science; Psychology; Data science; Psychometrics; Statistics; Mathematics education; Mathematics; Engineering","score_opus":0.2871225134574545,"score_gpt":0.4973541369068704,"score_spread":0.21023162344941593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967888896","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":[0.950391,0.009614783,0.00003289545,0.002890097,0.00010103495,0.001037774,0.000009458484,0.000048318663,0.03587464],"genre_scores_gemma":[0.9844843,0.0015227272,0.013568017,0.000038328777,0.0001552732,0.000075397926,0.000017753071,0.000010020223,0.00012819465],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9987629,0.00036362562,0.00022249893,0.00020510083,0.00024614038,0.00019975062],"domain_scores_gemma":[0.99349976,0.005968047,0.00013593823,0.000104951585,0.00025460002,0.00003669989],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002735364,0.00006949196,0.00015020077,0.00015270262,0.00014998179,0.00008018706,0.00009263175,0.00006174558,0.000016054904],"category_scores_gemma":[0.014158816,0.00006526084,0.000014802052,0.0007933145,0.00008805448,0.000451443,0.00003817369,0.00016850777,0.0000014042854],"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":[0.000036281377,0.0004542522,0.53744376,0.004326604,0.000026933509,0.000010915036,0.2725309,0.000040472558,0.011377798,0.036784515,0.00024397805,0.13672356],"study_design_scores_gemma":[0.0019713482,0.00061807537,0.34270382,0.010848637,0.00012502685,0.0000138945525,0.61326945,0.012570039,0.0007303106,0.012769178,0.0035913961,0.0007888534],"about_ca_topic_score_codex":0.0011627866,"about_ca_topic_score_gemma":0.0006360557,"teacher_disagreement_score":0.3407385,"about_ca_system_score_codex":0.000042271826,"about_ca_system_score_gemma":0.00008187256,"threshold_uncertainty_score":0.99414533},"labels":[],"label_agreement":null},{"id":"W2984367764","doi":"10.1186/s40468-019-0094-7","title":"Assessing peer review pattern and the effect of face-to-face and mobile-mediated modes on students’ academic writing development","year":2019,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Academic writing; English for academic purposes; Peer feedback; Mathematics education; Cohesion (chemistry); Task (project management); Second language writing; Face-to-face; Pedagogy; Medical education; Second language; Linguistics","score_opus":0.032727561803754454,"score_gpt":0.399730670787874,"score_spread":0.36700310898411953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2984367764","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":[0.99303335,0.0023340744,0.000014764151,0.00044698076,0.000044238364,0.0011273244,9.702906e-7,0.000039087376,0.0029592016],"genre_scores_gemma":[0.9989048,0.0001295381,0.00032683447,0.00026416642,0.000031595413,0.000056979887,0.0000034838026,0.000011295057,0.00027125416],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99813914,0.00037688072,0.0002883372,0.00022866015,0.0007193938,0.0002475729],"domain_scores_gemma":[0.99759084,0.0020567053,0.00014607051,0.00010690558,0.000045999997,0.00005349484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038383983,0.00013309157,0.00031031328,0.00005554549,0.00013310908,0.00010719962,0.00026734453,0.00006301434,0.000016861648],"category_scores_gemma":[0.0017384096,0.000091775204,0.000019420713,0.00029218005,0.00008494952,0.00015200183,0.00016369967,0.00026788193,0.000014405986],"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":[0.000008676761,0.00000994297,0.9367851,0.00024859465,0.000011661529,0.000003662041,0.027149228,0.000014975339,0.00055784825,0.000012797935,0.000018707411,0.035178784],"study_design_scores_gemma":[0.002465648,0.00016451847,0.93659735,0.007880027,0.000053733587,0.0000022617469,0.05132966,0.00053923094,0.00032918458,0.000006138485,0.0002789835,0.00035327795],"about_ca_topic_score_codex":0.0002210361,"about_ca_topic_score_gemma":0.00003098051,"teacher_disagreement_score":0.034825508,"about_ca_system_score_codex":0.000051644503,"about_ca_system_score_gemma":0.000030024641,"threshold_uncertainty_score":0.37424842},"labels":[],"label_agreement":null},{"id":"W4309467076","doi":"10.1186/s40468-022-00201-5","title":"Lessons from the Chinese imperial examination system","year":2022,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Global Educational Reforms and Inequalities","field":"Social Sciences","cited_by":33,"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":"Imperial examination; Language assessment; Linguistics; Set (abstract data type); Psychology; Field (mathematics); History; Pedagogy; Computer science; Philosophy; Ancient history","score_opus":0.031570842347215446,"score_gpt":0.34437883217476145,"score_spread":0.312807989827546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309467076","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":[0.93500865,0.00017990396,0.0000031137401,0.0010835825,0.00052945997,0.00010483865,0.0000390982,0.000062490304,0.06298887],"genre_scores_gemma":[0.99863374,7.0206613e-7,0.00020342748,0.00011174629,0.0005432155,0.00005118388,0.000028636727,0.000004743163,0.00042257484],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99904513,0.00028744596,0.00011938036,0.0001021094,0.00030111123,0.0001447975],"domain_scores_gemma":[0.99926525,0.0005210587,0.000063434534,0.00009752299,0.000028757531,0.00002396533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000991193,0.000049227336,0.00006389169,0.00002140548,0.00057655113,0.0000580021,0.00022499367,0.00001800108,0.00023659393],"category_scores_gemma":[0.00178924,0.00003400508,0.000018652832,0.00039758027,0.00004095038,0.000077365,0.000059750557,0.00011137063,0.000008436563],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011000647,0.00010440834,0.13101809,0.000015586857,0.000011655386,0.000029758023,0.6172789,0.00026936314,0.00096696574,0.20401646,0.00095101795,0.045326803],"study_design_scores_gemma":[0.00014959539,0.000016638822,0.5286991,0.000022321456,0.0000035366172,0.0000025855063,0.46651587,0.0002990234,0.0000053084887,0.0013933661,0.0028005147,0.00009217271],"about_ca_topic_score_codex":0.07144972,"about_ca_topic_score_gemma":0.0035748938,"teacher_disagreement_score":0.397681,"about_ca_system_score_codex":0.0002781647,"about_ca_system_score_gemma":0.00014067451,"threshold_uncertainty_score":0.93473357},"labels":[],"label_agreement":null},{"id":"W4387821100","doi":"10.1186/s40468-023-00261-1","title":"Instructional practices and students’ reading performance: a comparative study of 10 top performing regions in PISA 2018","year":2023,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Enthusiasm; Psychology; Reading (process); Multilevel model; Mathematics education; China; Sample (material); Teacher education; Pedagogy; Geography; Social psychology; Political science; Chemistry","score_opus":0.1189039487434486,"score_gpt":0.4392416959406387,"score_spread":0.3203377471971901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387821100","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":[0.9801283,0.000029146879,2.665783e-7,0.000056621506,0.00009448681,0.00032880483,7.0812433e-7,0.000054479155,0.019307222],"genre_scores_gemma":[0.99840325,0.000015896532,0.00064408913,0.0000051310153,0.00007744503,0.00002700377,0.0000025615786,0.000005682444,0.00081894966],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987656,0.00013947088,0.0002451937,0.00019633671,0.00042690232,0.00022649759],"domain_scores_gemma":[0.99903995,0.000550924,0.00024366446,0.00008858718,0.000042997184,0.00003388579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011062715,0.00008586227,0.00018035315,0.0002450246,0.0002254995,0.0000631839,0.00019429532,0.000040422514,0.000041812546],"category_scores_gemma":[0.0006629465,0.00008531625,0.000011347044,0.001151276,0.000096103395,0.00034719708,0.0001140482,0.00017086469,0.00000954461],"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":[0.0000121440535,0.000116823874,0.81576747,0.000012274435,0.000008748239,0.000013494255,0.18271083,0.000027252543,0.00015912241,0.00010714851,0.000038461414,0.0010262599],"study_design_scores_gemma":[0.00045138807,0.00009097797,0.6555846,0.0000816633,0.000006686676,0.0000014344936,0.3431694,0.00047882026,0.000010644953,0.000014963482,0.00004333949,0.00006609773],"about_ca_topic_score_codex":0.003298593,"about_ca_topic_score_gemma":0.00445518,"teacher_disagreement_score":0.16045856,"about_ca_system_score_codex":0.000076135235,"about_ca_system_score_gemma":0.000058882964,"threshold_uncertainty_score":0.4986508},"labels":[],"label_agreement":null},{"id":"W4400514459","doi":"10.1186/s40468-024-00294-0","title":"Adaptation and norm determination of the Boston Naming Test for healthy Lebanese adults aged between 50 and 88 years","year":2024,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Normative; Boston Naming Test; Psychology; Norm (philosophy); Test (biology); Cognition; Clinical psychology; Developmental psychology; Gerontology; Neuropsychology; Medicine; Psychiatry","score_opus":0.040891310306870876,"score_gpt":0.30745301490376475,"score_spread":0.2665617045968939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400514459","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":[0.9987556,0.00044364898,0.000055004366,0.00016518754,0.000094723015,0.0003299053,0.000029863879,0.00005742707,0.00006867422],"genre_scores_gemma":[0.9980042,0.000006286512,0.0016961772,0.00014162764,0.00007418334,0.000011973672,0.0000044997737,0.000013652955,0.000047374924],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99923867,0.00007353339,0.00019036856,0.00026793446,0.00008017769,0.00014930096],"domain_scores_gemma":[0.9974929,0.0022843585,0.00007921534,0.00010573959,0.000013325542,0.00002443487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027235298,0.00008520471,0.00011441752,0.000086022,0.00006757446,0.000029927964,0.000089411675,0.00005520617,0.0000012342532],"category_scores_gemma":[0.003079358,0.00006662204,0.0000193448,0.0002153447,0.0000899544,0.00008575224,0.00004672453,0.00014179655,5.274068e-7],"study_design_candidate":"bench_or_experimental","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":[0.00003210846,0.000031732186,0.031099502,0.00052658556,0.0000017750551,0.00022348054,0.0323463,0.0000035996209,0.6024109,0.000029598341,0.000008499842,0.33328593],"study_design_scores_gemma":[0.0035177446,0.001956578,0.7021337,0.003408092,0.00012712655,0.0013822501,0.009717518,0.03671434,0.23871066,0.0011258193,0.00026411517,0.00094205356],"about_ca_topic_score_codex":0.00017531654,"about_ca_topic_score_gemma":0.00019335473,"teacher_disagreement_score":0.6710342,"about_ca_system_score_codex":0.000014839164,"about_ca_system_score_gemma":0.000026161513,"threshold_uncertainty_score":0.36865017},"labels":[],"label_agreement":null},{"id":"W4407613621","doi":"10.1186/s40468-025-00341-4","title":"Correction: Lessons from the Chinese imperial examination system","year":2025,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Legal Education and Practice Innovations","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Imperial examination; Linguistics; Psychology; Language education; Mathematics education; History; Philosophy; Ancient history","score_opus":0.027878936346111008,"score_gpt":0.3862787152161436,"score_spread":0.3583997788700326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407613621","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":[0.49971664,0.00011469738,0.00021460319,0.01642594,0.0045087207,0.00019172953,0.0000048214274,0.00018356425,0.4786393],"genre_scores_gemma":[0.9950226,0.0000011415195,0.00044345084,0.00030253938,0.00065103825,0.000028390863,0.000012831402,0.000003710808,0.00353428],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99914724,0.0003443221,0.00015025567,0.000117459684,0.00012983686,0.00011091203],"domain_scores_gemma":[0.9974899,0.0021808099,0.00008131265,0.00013753481,0.000093649105,0.000016771435],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009194731,0.000053033913,0.00006303699,0.000057478337,0.00045534922,0.00019353829,0.00016071659,0.000052522504,0.000111508445],"category_scores_gemma":[0.009805205,0.000041095125,0.000014323474,0.0014838338,0.00005170594,0.00020867106,0.000018982904,0.00023681113,0.00002629095],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016631178,0.00017276763,0.21013856,0.000025064339,0.000029900488,0.000017670513,0.37735063,0.000075364944,0.0019954205,0.14688675,0.022332434,0.24095881],"study_design_scores_gemma":[0.00027941493,0.000007134662,0.81645614,0.00018429219,0.000017259179,0.0000022660402,0.16221395,0.0014715565,0.00005531991,0.00054647715,0.018641213,0.0001249638],"about_ca_topic_score_codex":0.04688612,"about_ca_topic_score_gemma":0.014664221,"teacher_disagreement_score":0.6063176,"about_ca_system_score_codex":0.00016268087,"about_ca_system_score_gemma":0.00036551,"threshold_uncertainty_score":0.99853563},"labels":[],"label_agreement":null},{"id":"W4415055623","doi":"10.1186/s40468-025-00390-9","title":"Shaping written corrective feedback perspectives and practices: comparing novice and experienced instructors of English for academic purposes in Bangladesh","year":2025,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":1,"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 Manitoba; Red River College","funders":"","keywords":"Corrective feedback; Professional development; English for academic purposes; Grammar; Faculty development; Relevance (law); Focus group; Qualitative research; Higher education","score_opus":0.06050911231811046,"score_gpt":0.33303835002998666,"score_spread":0.2725292377118762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415055623","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":[0.97570217,0.0019506636,0.0000113932665,0.000037308244,0.00013128338,0.00023573595,0.0000030465003,0.00007004987,0.021858368],"genre_scores_gemma":[0.9983167,0.000009140178,0.0012754637,0.000037653965,0.00016309367,0.000029879471,0.0000029091161,0.000012639332,0.00015250564],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.999107,0.00009461372,0.00025425915,0.00027400808,0.000074057396,0.00019604621],"domain_scores_gemma":[0.9983083,0.0012340224,0.00024267843,0.00007986353,0.00011058579,0.000024547553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004441626,0.00012682911,0.0002527679,0.00023954624,0.00015178947,0.00009495523,0.000102714184,0.000057013178,0.000011284972],"category_scores_gemma":[0.007142053,0.00012548626,0.000016764434,0.00013273212,0.00018194474,0.00029579064,0.00006818872,0.00047034957,1.5165483e-7],"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":[0.00003153592,0.0000230568,0.22100359,0.00016026576,0.00001098769,0.0000034050076,0.7662357,0.00002726711,0.00066772656,0.0053528114,0.00000766528,0.006475984],"study_design_scores_gemma":[0.00080056814,0.00006386975,0.06674029,0.0011786326,0.000016713671,0.0000035607493,0.92693126,0.003379063,0.00017530889,0.00014121979,0.00039829963,0.00017121619],"about_ca_topic_score_codex":0.0019576408,"about_ca_topic_score_gemma":0.0015385897,"teacher_disagreement_score":0.16069555,"about_ca_system_score_codex":0.000048671925,"about_ca_system_score_gemma":0.00003288026,"threshold_uncertainty_score":0.8550221},"labels":[],"label_agreement":null}]}