{"meta":{"query_hash":"6e475cc8b99a","filters":{"venue":"Language Testing"},"cohort_total":57,"direct_labels_cover":0,"predictions_cover":57,"exported":57,"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/6e475cc8b99a","api":"https://metacan.xera.ac/api/v1/cohort?venue=Language+Testing"},"results":[{"id":"W1979398480","doi":"10.1177/0265532214560799","title":"A prototype of a receptive lexical test for a polysynthetic heritage language: The case of Inuttitut in Labrador","year":2014,"lang":"en","type":"article","venue":"Language Testing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"The Scarborough Hospital; University of Toronto; Carleton University","funders":"","keywords":"Heritage language; Linguistics; Vocabulary; Psychology; Test (biology); Comprehension; Noun; Language proficiency; First language; Natural language processing; Computer science; Mathematics education","score_opus":0.016575572520713226,"score_gpt":0.2924684211711534,"score_spread":0.27589284865044017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979398480","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":[0.8981039,0.0023390572,0.09549961,0.0005780943,0.00006966079,0.0020174591,0.00002387462,0.00074746925,0.00062087894],"genre_scores_gemma":[0.6692018,2.3211405e-7,0.33055526,0.000069018824,0.000033687862,0.000097339704,6.4715164e-7,0.000014219417,0.000027784065],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988532,0.00011577208,0.0003498149,0.00028577726,0.00013321113,0.00026222746],"domain_scores_gemma":[0.9971865,0.0018874475,0.00024884954,0.00051620236,0.00012274979,0.000038243645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008631768,0.00014797536,0.00026476444,0.0001220079,0.00006213992,0.000040622526,0.0006869013,0.0000767355,0.0000058105757],"category_scores_gemma":[0.0064302483,0.0001034157,0.000058264483,0.00070904236,0.00012241642,0.0001761099,0.00020882324,0.0002196644,0.0000015928532],"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":[0.00013197945,0.0004387789,0.0022182234,0.001145561,0.000024784928,0.0009872088,0.071593344,0.000014717454,0.29602683,0.023662962,0.000072698225,0.60368294],"study_design_scores_gemma":[0.0030505236,0.005163533,0.0011785008,0.0032949946,0.000091210175,0.003038223,0.013660617,0.19686697,0.74830455,0.02382121,0.00009509802,0.001434582],"about_ca_topic_score_codex":0.0019112661,"about_ca_topic_score_gemma":0.0005231013,"teacher_disagreement_score":0.6022483,"about_ca_system_score_codex":0.000028395198,"about_ca_system_score_gemma":0.000063067404,"threshold_uncertainty_score":0.7698072},"labels":[],"label_agreement":null},{"id":"W2005408543","doi":"10.1191/0265532204lt292oa","title":"Test decisions over time: tracking validity","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":69,"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":"Test (biology); Psychology; Sample (material); Active listening; Test validity; Applied psychology; Social psychology; Mathematics education; Psychometrics; Developmental psychology","score_opus":0.10042040920656546,"score_gpt":0.29390229656668887,"score_spread":0.1934818873601234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005408543","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":[0.89928323,0.00015309502,0.00019511399,0.00009807546,0.000161516,0.00006820215,0.000011404881,0.0005819982,0.099447355],"genre_scores_gemma":[0.99155074,5.549055e-7,0.0024728975,0.00028690507,0.0008213656,0.0000035263558,0.000013121376,0.000033433833,0.0048174285],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99909234,0.000043959168,0.00019126567,0.00020748196,0.00018216691,0.000282794],"domain_scores_gemma":[0.9982728,0.0013213984,0.000089575384,0.00019976679,0.000050061026,0.00006644046],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00040038629,0.00013717817,0.00014253701,0.000066790286,0.00068159774,0.00027952594,0.00014964992,0.000035761852,0.0015911215],"category_scores_gemma":[0.0045773597,0.00011988529,0.00006053765,0.00006109421,0.00006603329,0.00019960248,0.000047554706,0.00036342282,0.0005117817],"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":[0.000013557282,0.0006795053,0.032778762,0.0000868864,0.00006419853,0.000793916,0.6610945,0.0020743005,0.039068315,0.024917476,0.003123549,0.23530504],"study_design_scores_gemma":[0.019432819,0.0035686505,0.23409186,0.015328458,0.0012502352,0.0012302492,0.20570815,0.033423863,0.012552097,0.046924893,0.41314915,0.013339578],"about_ca_topic_score_codex":0.0011158178,"about_ca_topic_score_gemma":0.00022568855,"teacher_disagreement_score":0.45538634,"about_ca_system_score_codex":0.00004464213,"about_ca_system_score_gemma":0.000030143405,"threshold_uncertainty_score":0.9993216},"labels":[],"label_agreement":null},{"id":"W2008716813","doi":"10.1177/02655322100270020902","title":"Book Review: Chapelle, C. A., Enright, M. K. and Jamieson, J. M. (Eds) Building a validity argument for the Test of English as a Foreign LanguageTM. New York and London: Routledge, Taylor &amp; Francis Group, 2008. 370 + xiii pp. ISBN 0-8058-5456-8 (paperback)","year":2010,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","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":"University of Toronto","funders":"","keywords":"Argument (complex analysis); Psychology; Media studies; Sociology; Chemistry","score_opus":0.02347074940022355,"score_gpt":0.2445379187758677,"score_spread":0.22106716937564413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008716813","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13113604,0.84878325,0.00036724372,0.00043151423,0.00080854975,0.0015191786,0.00011080989,0.0004269607,0.01641643],"genre_scores_gemma":[0.824583,0.0081154145,0.03460341,0.03495795,0.024501557,0.00065937993,0.00034697616,0.00068307423,0.07154923],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978285,0.00010577576,0.00058983325,0.00057793,0.00030490448,0.0005930815],"domain_scores_gemma":[0.9947553,0.0038062194,0.00044040463,0.0005851861,0.00021329171,0.00019955925],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001151292,0.0004436734,0.0006064206,0.00007394607,0.0008023667,0.00030954907,0.00035519458,0.00012939828,0.0029572842],"category_scores_gemma":[0.008583907,0.0003212995,0.00015890028,0.00012480757,0.00026668518,0.00028184368,0.00015928053,0.0008021006,0.000017129552],"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":[0.000114681476,0.00039086968,0.0042058327,0.0041101384,0.00036650256,0.000099260484,0.30579573,0.000009684885,0.0100645,0.009356162,0.32010895,0.3453777],"study_design_scores_gemma":[0.001272591,0.00026235447,0.00016388144,0.00085825275,0.00030283668,0.000069588095,0.00824815,0.00056940573,0.00041619636,0.00018629836,0.98705256,0.00059787126],"about_ca_topic_score_codex":0.0036396503,"about_ca_topic_score_gemma":0.0016930971,"teacher_disagreement_score":0.84066784,"about_ca_system_score_codex":0.000021421243,"about_ca_system_score_gemma":0.000033396194,"threshold_uncertainty_score":0.9999239},"labels":[],"label_agreement":null},{"id":"W2027399021","doi":"10.1177/0265532207076363","title":"The challenges of the Ontario Secondary School Literacy Test for second language students","year":2007,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":57,"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":"Literacy; Test (biology); Psychology; Mathematics education; Vocabulary; Context (archaeology); Reading (process); English as a second language; Language proficiency; Language assessment; Pedagogy; Linguistics","score_opus":0.02266960080524535,"score_gpt":0.3419876094318603,"score_spread":0.31931800862661497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027399021","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":[0.92490053,0.019034114,0.00004053805,0.00014934815,0.00053671375,0.00046820633,0.000023313647,0.00009866417,0.054748584],"genre_scores_gemma":[0.9743323,8.785945e-7,0.00079068565,0.002058849,0.0004704866,0.000040684175,0.000009012924,0.00004261497,0.022254525],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9983564,0.00011470184,0.00045159343,0.00031854305,0.0002505334,0.0005082351],"domain_scores_gemma":[0.99565506,0.0031236084,0.00032735438,0.0006830052,0.00011263056,0.00009833123],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015276659,0.00019725143,0.00020894308,0.00007172694,0.00036965,0.000089992645,0.0006713927,0.00010990333,0.00968408],"category_scores_gemma":[0.0017113447,0.00012702476,0.00013674948,0.00019980768,0.00008539326,0.00010194995,0.00013737587,0.00060594606,0.000064985696],"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":[0.00016744598,0.00040941508,0.13684724,0.00019304975,0.00029002156,0.00030292472,0.4866394,0.000003225331,0.025983032,0.0014577156,0.0023752374,0.34533128],"study_design_scores_gemma":[0.0017560776,0.00019743413,0.8851979,0.00016788745,0.000049552695,0.00010451109,0.09748836,0.000009586689,0.0029342344,0.00009413287,0.01169293,0.00030744402],"about_ca_topic_score_codex":0.0019724737,"about_ca_topic_score_gemma":0.010491096,"teacher_disagreement_score":0.7483506,"about_ca_system_score_codex":0.00008002898,"about_ca_system_score_gemma":0.00007224191,"threshold_uncertainty_score":0.9912212},"labels":[],"label_agreement":null},{"id":"W2042225150","doi":"10.1191/0265532204lt273oa","title":"Evaluation of an in-depth vocabulary knowledge measure for assessing reading performance","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":237,"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":"Test of English as a Foreign Language; Vocabulary; Reading comprehension; Reading (process); Context (archaeology); Measure (data warehouse); Test (biology); Psychology; Language proficiency; Sample (material); Vocabulary development; Mathematics education; Language assessment; Computer science; Linguistics; Teaching method","score_opus":0.09731813955004215,"score_gpt":0.40605952944771595,"score_spread":0.3087413898976738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042225150","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":[0.961946,0.0030437643,0.0008335939,0.0000104177,0.00017588335,0.0002867959,0.0000015839153,0.000095607196,0.03360632],"genre_scores_gemma":[0.9922594,1.2958222e-7,0.007199365,0.0001514823,0.00022229426,0.00005180746,0.000027970695,0.00003035981,0.00005718436],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99871606,0.00024561698,0.00028191527,0.00025900736,0.00023655454,0.00026084826],"domain_scores_gemma":[0.99909663,0.00019571192,0.00016095045,0.00024376462,0.0002571928,0.000045767043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031304883,0.00011592316,0.00017011215,0.0001833873,0.000091869704,0.000028619705,0.0001204321,0.00008907282,0.000684517],"category_scores_gemma":[0.0011807752,0.00011910448,0.00003596853,0.0003366669,0.000024305022,0.0002627604,0.000015923812,0.00018125119,0.000018503284],"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":[0.0000292533,0.00023031764,0.013572693,0.00010562261,0.0000321651,0.00003624922,0.0734766,0.0035799947,0.04331007,0.00023064399,0.000007649212,0.86538875],"study_design_scores_gemma":[0.011453127,0.00058337534,0.7942628,0.0019056608,0.00034840472,0.00021220041,0.10177416,0.070695706,0.017345265,0.0004423854,0.000055845314,0.0009210572],"about_ca_topic_score_codex":0.0001404246,"about_ca_topic_score_gemma":0.00006481753,"teacher_disagreement_score":0.8644677,"about_ca_system_score_codex":0.000118902484,"about_ca_system_score_gemma":0.000116560695,"threshold_uncertainty_score":0.7494982},"labels":[],"label_agreement":null},{"id":"W2078562183","doi":"10.1177/0265532210384253","title":"Impact and consequences of school-based assessment (SBA): Students’ and parents’ views of SBA in Hong Kong","year":2011,"lang":"en","type":"article","venue":"Language Testing","topic":"Parental Involvement in Education","field":"Social Sciences","cited_by":92,"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":"Perception; Psychology; Competence (human resources); Certificate; Context (archaeology); Medical education; Developmental psychology; Mathematics education; Pedagogy; Social psychology; Medicine","score_opus":0.2119144028794248,"score_gpt":0.4574731512778527,"score_spread":0.2455587483984279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078562183","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":[0.9955471,0.00061716593,0.000013083051,0.000016059286,0.000068173504,0.00023355235,0.0000074980694,0.000017495444,0.0034798665],"genre_scores_gemma":[0.99630946,0.000025533554,0.003579307,0.000024100744,0.000025890879,0.000010779523,0.0000047475964,0.0000051271636,0.000015048584],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99896556,0.00017675258,0.00027195772,0.00014960837,0.00026173514,0.00017440693],"domain_scores_gemma":[0.9992792,0.0002501778,0.00023907395,0.00009998431,0.000051035768,0.000080520855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088581676,0.00008307703,0.00016907702,0.00009191225,0.00007375069,0.00002735764,0.00015026196,0.00003621225,0.000071563336],"category_scores_gemma":[0.00061976636,0.00007525065,0.000019023422,0.00025321144,0.00029235752,0.00017171673,0.00004503408,0.00007789077,6.0954096e-7],"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":[0.0000037247737,0.0001567186,0.9646982,0.000040625648,0.0000076186543,0.000003175888,0.021097427,0.0000021793956,0.0126213785,0.000055269396,0.0000037925633,0.001309866],"study_design_scores_gemma":[0.00023015575,0.00007428443,0.9656995,0.00023430867,0.000012290384,4.2702894e-7,0.030938888,0.000035940975,0.0025165123,0.00018092235,0.0000014221218,0.00007535989],"about_ca_topic_score_codex":0.033196077,"about_ca_topic_score_gemma":0.004081465,"teacher_disagreement_score":0.029114613,"about_ca_system_score_codex":0.00008274943,"about_ca_system_score_gemma":0.00017346005,"threshold_uncertainty_score":0.9732419},"labels":[],"label_agreement":null},{"id":"W2082767250","doi":"10.1177/0265532208101010","title":"An investigation into native and non-native teachers' judgments of oral English performance: A mixed methods approach","year":2009,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":137,"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":"Psychology; Pronunciation; Rasch model; Consistency (knowledge bases); Grammar; Mathematics education; First language; Internal consistency; Multimethodology; Linguistics; Psychometrics; Developmental psychology; Computer science; Artificial intelligence","score_opus":0.04154220340015909,"score_gpt":0.3200407438186342,"score_spread":0.2784985404184751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082767250","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":[0.9757374,0.00011478098,0.0005273069,0.000013927353,0.00007283677,0.00012092675,0.0000019131887,0.0001330943,0.023277828],"genre_scores_gemma":[0.9013217,6.7118293e-7,0.09794325,0.000095900425,0.00020862363,0.000006673522,0.000024772804,0.000013389149,0.00038503998],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9989463,0.00031778956,0.0002082213,0.00021800448,0.00013907018,0.00017061968],"domain_scores_gemma":[0.99931353,0.00019825286,0.00017661465,0.000121834586,0.0001271684,0.00006257673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011553871,0.00014204752,0.0001992127,0.00010994084,0.00032257475,0.0000983085,0.00010677282,0.00004438387,0.000023964081],"category_scores_gemma":[0.0007698403,0.00012390992,0.000022882741,0.00007973056,0.00014239296,0.00040917334,0.000025024303,0.00034151273,7.06702e-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":[0.000005036533,0.00004507543,0.0049866643,0.000041497722,0.000016032689,0.0000010391869,0.84223187,0.000077754434,0.003015193,0.0007998537,0.000020828877,0.14875916],"study_design_scores_gemma":[0.0015669517,0.0015633903,0.050608303,0.00053292094,0.0001354867,0.000006502383,0.82713366,0.10633303,0.009431276,0.0014836979,0.0003798519,0.00082493795],"about_ca_topic_score_codex":0.00077469414,"about_ca_topic_score_gemma":0.000039191393,"teacher_disagreement_score":0.14793421,"about_ca_system_score_codex":0.000029508457,"about_ca_system_score_gemma":0.000022067548,"threshold_uncertainty_score":0.50529},"labels":[],"label_agreement":null},{"id":"W2096343999","doi":"10.1191/0265532203lt248oa","title":"Does item-level DIF manifest itself in scale-level analyses? Implications for translating language tests","year":2003,"lang":"en","type":"article","venue":"Language Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":92,"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; Equivalence (formal languages); Psychology; Scale (ratio); Measurement invariance; Item response theory; Item analysis; Statistics; Test (biology); Psychometrics; Developmental psychology; Linguistics; Structural equation modeling; Mathematics; Confirmatory factor analysis","score_opus":0.6773012489253456,"score_gpt":0.5390986227521983,"score_spread":0.13820262617314727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096343999","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":[0.9085241,0.000791975,0.07255301,0.00050009455,0.0003716465,0.0006680805,0.00022360127,0.00027219008,0.016095296],"genre_scores_gemma":[0.67267895,0.0000014885725,0.3261494,0.00017053753,0.0001277178,0.00006777591,0.000010476823,0.00003100654,0.0007626727],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958195,0.0005375626,0.001269155,0.00097087893,0.00059234165,0.00081057823],"domain_scores_gemma":[0.9392038,0.05879252,0.00057977653,0.0009333737,0.00030845153,0.00018210015],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0067473818,0.00032961855,0.00060644554,0.0008460847,0.00038192733,0.00031472635,0.0008995,0.0001509855,0.00012601065],"category_scores_gemma":[0.25759593,0.00020998971,0.00019117874,0.004788593,0.00007689429,0.00032620228,0.00008801077,0.00032671777,0.000022061904],"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":[0.000007264762,0.00009430339,0.68711156,0.00003705266,0.000016420128,0.000028158827,0.004096707,0.00019680226,0.052141923,0.00043189642,0.00011171434,0.2557262],"study_design_scores_gemma":[0.0011228053,0.000077574325,0.96406627,0.00015316941,0.00004474372,0.000088666464,0.015527273,0.0037632782,0.0028780722,0.011484906,0.00018875708,0.0006045162],"about_ca_topic_score_codex":0.0004920563,"about_ca_topic_score_gemma":0.0011195227,"teacher_disagreement_score":0.27695468,"about_ca_system_score_codex":0.00006955244,"about_ca_system_score_gemma":0.000095446296,"threshold_uncertainty_score":0.85631317},"labels":[],"label_agreement":null},{"id":"W2097625210","doi":"10.1177/0265532211404195","title":"Test review: ACCESS for ELLs <sup>®</sup>","year":2011,"lang":"en","type":"article","venue":"Language Testing","topic":"Digital Accessibility for Disabilities","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Ell; Psychology; Test (biology); Language proficiency; Mathematics education; Teaching method; Geology","score_opus":0.13373330771807518,"score_gpt":0.3811891609412508,"score_spread":0.24745585322317565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097625210","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29124472,0.003688116,0.000072617615,0.0003570868,0.000115410665,0.0013349586,0.00007815366,0.00064278324,0.7024662],"genre_scores_gemma":[0.98629946,0.00005961528,0.0061459853,0.001249018,0.0004111899,0.00015003192,0.000015874879,0.00003567201,0.0056331307],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99856174,0.000058899448,0.00032282027,0.00031986032,0.00026482454,0.0004718684],"domain_scores_gemma":[0.99783504,0.0014005968,0.00013162152,0.0003184953,0.00018327868,0.00013095014],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010374349,0.00014157001,0.00022747053,0.000038394355,0.00030292288,0.00020276435,0.00075288553,0.000058735855,0.00052089],"category_scores_gemma":[0.022432927,0.00012966567,0.000105132494,0.00043512456,0.0002944165,0.0010504713,0.00014602247,0.000091007496,0.00007847642],"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":[0.000023097838,0.0008700556,0.4358202,0.0045298184,0.000050050126,0.000033628054,0.18751748,0.000008624997,0.00016293129,0.013520069,0.016772553,0.3406915],"study_design_scores_gemma":[0.0042939885,0.0018848459,0.060810067,0.020677788,0.0010443333,0.0000512759,0.41711122,0.0030218556,0.0064481376,0.27463707,0.2019059,0.008113514],"about_ca_topic_score_codex":0.0031775574,"about_ca_topic_score_gemma":0.00057119766,"teacher_disagreement_score":0.696833,"about_ca_system_score_codex":0.00007245631,"about_ca_system_score_gemma":0.00011497951,"threshold_uncertainty_score":0.9858015},"labels":[],"label_agreement":null},{"id":"W2100317885","doi":"10.1177/0265532215570924","title":"How do young students with different profiles of reading skill mastery, perceived ability, and goal orientation respond to holistic diagnostic feedback?","year":2015,"lang":"en","type":"article","venue":"Language Testing","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":61,"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; Reading (process); Goal orientation; Cognition; Developmental psychology; Orientation (vector space); Mathematics education; Cognitive psychology; Social psychology","score_opus":0.06663303109817183,"score_gpt":0.3901718268217531,"score_spread":0.3235387957235813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100317885","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":[0.9963343,0.00008910333,0.00021658016,0.0002015094,0.00032027584,0.00047066616,0.000028336168,0.00004549558,0.0022936994],"genre_scores_gemma":[0.9956874,5.5319657e-7,0.0026306566,0.00009449535,0.00014877034,0.00010252483,0.0000314683,0.000018195526,0.0012859377],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99857837,0.00018073591,0.00021800603,0.00040295997,0.00034926724,0.00027064988],"domain_scores_gemma":[0.99813306,0.001153575,0.0001382516,0.00023621264,0.00015256567,0.00018631872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032486214,0.00016911175,0.00021563163,0.0000863722,0.00006201849,0.00010504723,0.00017784732,0.000055250846,0.000071288625],"category_scores_gemma":[0.001692213,0.00012098302,0.000017703287,0.00023458849,0.00007103882,0.00008921753,0.00009234608,0.00012888505,0.00001317494],"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":[0.0001257889,0.00031715215,0.95953417,0.000037253103,0.000028680499,0.000034973138,0.03374704,0.000003293566,0.0023027272,0.00018178315,0.00007500747,0.0036121279],"study_design_scores_gemma":[0.0007882874,0.00056301476,0.9668079,0.00017104158,0.000034319197,0.00004307867,0.031072529,0.000004826328,0.000045117467,0.00031484696,0.000006313504,0.00014874143],"about_ca_topic_score_codex":0.0002013405,"about_ca_topic_score_gemma":0.000028454648,"teacher_disagreement_score":0.007273709,"about_ca_system_score_codex":0.000057102014,"about_ca_system_score_gemma":0.000018479848,"threshold_uncertainty_score":0.49335444},"labels":[],"label_agreement":null},{"id":"W2104209819","doi":"10.1177/0265532212436659","title":"Topical knowledge and ESL writing","year":2012,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":77,"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","funders":"","keywords":"Impromptu; Cohesion (chemistry); Language proficiency; Psychology; Test (biology); Mathematics education; Language assessment; Second language writing; Test of English as a Foreign Language; English for academic purposes; Task (project management); Pedagogy; Second language; Linguistics; Computer science","score_opus":0.061547222700138966,"score_gpt":0.29217058559962256,"score_spread":0.2306233628994836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104209819","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":[0.7490291,0.0026797955,0.000020124715,0.00004477178,0.00014233729,0.00002650454,7.261738e-7,0.00018878643,0.24786788],"genre_scores_gemma":[0.9911574,6.853463e-7,0.0013804146,0.0001336435,0.0024570315,0.0000028075297,0.0000025070265,0.000014442349,0.0048510684],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99944353,0.000054571294,0.000107232125,0.000092622446,0.000051940904,0.0002500801],"domain_scores_gemma":[0.99945885,0.00034706766,0.000034331464,0.00007512679,0.000018328517,0.00006630452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033363458,0.00007742867,0.0000874784,0.00003109875,0.0003456884,0.00010234936,0.00004706771,0.000022141541,0.00037626675],"category_scores_gemma":[0.000451741,0.00006679497,0.000017903845,0.000018904777,0.000050676605,0.00014638214,0.00004903193,0.00021915261,0.00006799751],"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":[0.0000019007679,0.00006159063,0.11437961,0.000103624836,0.000013316394,0.000012484457,0.52481055,0.0000010558484,0.00095715583,0.07670829,0.00054740254,0.28240302],"study_design_scores_gemma":[0.0016686239,0.00032947023,0.09240823,0.0012790629,0.00017009163,0.00029347933,0.26956883,0.005051067,0.00059364375,0.00086623075,0.62576175,0.0020095292],"about_ca_topic_score_codex":0.0001990142,"about_ca_topic_score_gemma":0.000045902663,"teacher_disagreement_score":0.62521434,"about_ca_system_score_codex":0.000009313579,"about_ca_system_score_gemma":0.000005039362,"threshold_uncertainty_score":0.4119857},"labels":[],"label_agreement":null},{"id":"W2105451781","doi":"10.1191/0265532204lt287oa","title":"Teacher formative assessment and talk in classroom contexts: assessment as discourse and assessment of discourse","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":159,"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":"Formative assessment; Psychology; Pedagogy; Discourse analysis; Applied linguistics; Mathematics education; Assessment for learning; Systemic functional linguistics; Linguistics","score_opus":0.030320027060730614,"score_gpt":0.42869087904920095,"score_spread":0.39837085198847033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105451781","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":[0.9221969,0.00030183233,0.00057308405,0.0011381911,0.00011379764,0.0005960678,0.000010919142,0.000066355846,0.075002834],"genre_scores_gemma":[0.98106205,0.000060021543,0.018208724,0.000108061984,0.00012889708,0.00005495936,0.000012758697,0.000022235365,0.0003422976],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977274,0.00023866889,0.00047453053,0.0003772012,0.0006771764,0.0005050161],"domain_scores_gemma":[0.9987569,0.00046860028,0.00032813483,0.00019963493,0.000080045334,0.00016666968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013958275,0.0002527186,0.00041968605,0.000153969,0.00032671483,0.0001746399,0.0002231136,0.00010743899,0.00010040917],"category_scores_gemma":[0.00022201492,0.00022633294,0.000051283874,0.00037445204,0.00048026603,0.0006579131,0.00020288426,0.00043380132,0.0000016211736],"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":[0.000009927094,0.0005870681,0.8351541,0.00007148167,0.00007616492,0.00010911301,0.09371276,0.000041948082,0.0020737022,0.03619533,0.000028225313,0.031940132],"study_design_scores_gemma":[0.002046388,0.00023670151,0.6623685,0.00033874577,0.00006070044,0.000006857245,0.33211297,0.00051017106,0.000039597577,0.0018874267,0.0000566251,0.00033531393],"about_ca_topic_score_codex":0.0071682576,"about_ca_topic_score_gemma":0.003914115,"teacher_disagreement_score":0.2384002,"about_ca_system_score_codex":0.00041643163,"about_ca_system_score_gemma":0.0005470617,"threshold_uncertainty_score":0.9994431},"labels":[],"label_agreement":null},{"id":"W2109863812","doi":"10.1191/0265532204lt278oa","title":"A teacher-verification study of speaking and writing prototype tasks for a new TOEFL","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":93,"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":"Test of English as a Foreign Language; Active listening; Psychology; Formative assessment; Mathematics education; Test (biology); CLARITY; Reading (process); Second language writing; Language proficiency; Presentation (obstetrics); Language assessment; Pedagogy; Computer science; Second language; Linguistics; Communication","score_opus":0.08046825576428888,"score_gpt":0.31140587081200116,"score_spread":0.23093761504771226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109863812","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":[0.9929972,0.00019942754,0.00042051318,0.00004932929,0.000033594482,0.000639434,0.0000020007662,0.00014310585,0.005515357],"genre_scores_gemma":[0.9936404,1.6252027e-7,0.0053057913,0.000030407542,0.00056717487,0.00003456566,0.000005429826,0.000021725606,0.0003943319],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99935067,0.000035150104,0.00020448698,0.00017138307,0.000088172485,0.00015015982],"domain_scores_gemma":[0.9994986,0.00015945277,0.00014718059,0.00011631528,0.000046109155,0.00003231229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003661521,0.000091927584,0.00013687415,0.0000523529,0.0003030353,0.00010144935,0.000067731446,0.000020084704,0.000033619428],"category_scores_gemma":[0.00062133564,0.00008420099,0.000020389522,0.00003605224,0.00002575096,0.00010854834,0.000022594082,0.00015232587,0.0000018782594],"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":[0.000025017254,0.00019391495,0.008487372,0.00017222141,0.000026466067,0.0000070150904,0.8562801,0.00017952124,0.0035256208,0.004053048,0.000016799191,0.12703289],"study_design_scores_gemma":[0.005402894,0.0031650276,0.010771409,0.001543824,0.00019635895,0.000030307161,0.96809363,0.002798713,0.00065034727,0.0016768728,0.004861932,0.0008086776],"about_ca_topic_score_codex":0.0053481823,"about_ca_topic_score_gemma":0.0010106774,"teacher_disagreement_score":0.12622422,"about_ca_system_score_codex":0.000017416429,"about_ca_system_score_gemma":0.00002548229,"threshold_uncertainty_score":0.8084887},"labels":[],"label_agreement":null},{"id":"W2116070328","doi":"10.1177/0265532210376379","title":"Think-aloud protocols in research on essay rating: An empirical study of their veridicality and reactivity","year":2010,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":121,"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":"Think aloud protocol; Psychology; Protocol analysis; Perception; Empirical research; Sample (material); Qualitative research; Rating scale; Social psychology; Nomothetic and idiographic; Cognitive psychology; Applied psychology; Developmental psychology; Epistemology; Cognitive science","score_opus":0.29237641940546794,"score_gpt":0.5510859877479262,"score_spread":0.25870956834245823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116070328","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":[0.9803934,0.0000029005978,7.588783e-7,0.000104596,0.000032703712,0.0041118907,0.0000011829575,0.000054597032,0.015297958],"genre_scores_gemma":[0.99917233,1.4342383e-7,0.00039210333,0.000019696705,0.00017805593,0.00017378917,6.9458065e-7,0.00000772996,0.000055460285],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99759936,0.0010201227,0.00019654748,0.0002779067,0.00061586197,0.0002901692],"domain_scores_gemma":[0.9976435,0.0018473857,0.000081942424,0.0002457829,0.00009258107,0.00008882382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064406837,0.000083672,0.0001775743,0.000079156285,0.00033934735,0.00009831074,0.00026024543,0.00008569542,0.00003783099],"category_scores_gemma":[0.0033811054,0.000066861474,0.000013694083,0.0005312032,0.00021824538,0.00016640998,0.00011733514,0.000689057,0.0000017927908],"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":[0.000024346178,0.00091238716,0.6528844,0.0000097482725,0.0000028384216,0.000014729201,0.32728985,3.7396333e-7,0.011734171,0.00017972151,0.000008902451,0.006938535],"study_design_scores_gemma":[0.0005041019,0.0004316432,0.7267394,0.000042664353,0.0000019459414,3.4257332e-7,0.27134317,0.00013408,0.00036479346,0.00032419982,0.000025817146,0.00008783205],"about_ca_topic_score_codex":0.006873621,"about_ca_topic_score_gemma":0.013844201,"teacher_disagreement_score":0.07385501,"about_ca_system_score_codex":0.000039878472,"about_ca_system_score_gemma":0.00014670374,"threshold_uncertainty_score":0.9997397},"labels":[],"label_agreement":null},{"id":"W2122362059","doi":"10.1191/0265532206lt322oa","title":"Aiming for positive washback: a case study of international teaching assistants","year":2005,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Test (biology); Psychology; Language proficiency; Process (computing); Mathematics education; Empirical research; Computer science","score_opus":0.05418180584152639,"score_gpt":0.417552964658704,"score_spread":0.36337115881717763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122362059","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":[0.9689544,0.00003273317,0.00022978257,0.00013603277,0.00014077856,0.00032807465,0.000006541906,0.000057977148,0.0301137],"genre_scores_gemma":[0.9845323,3.072115e-7,0.014273591,0.000042437918,0.00051425013,0.0000145600125,0.0000025941904,0.0000086275695,0.0006113448],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9991629,0.000079863785,0.00017863174,0.00014301934,0.00025687835,0.00017870813],"domain_scores_gemma":[0.99909174,0.0005825684,0.00012776362,0.000068469,0.000092719354,0.000036742043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071059656,0.000067600544,0.00010429358,0.00005648265,0.00040023978,0.00006266831,0.00016041397,0.000026445796,0.000039045153],"category_scores_gemma":[0.0009049757,0.00006699014,0.000031722353,0.00010132597,0.000034636047,0.00018615926,0.000052138734,0.00009001935,0.0000020921632],"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":[0.000018425306,0.00059266924,0.26160422,0.000008992158,0.00009007394,0.000386716,0.62515134,0.000033143355,0.0023640492,0.00091553485,0.00010748886,0.108727336],"study_design_scores_gemma":[0.0012065955,0.00015765922,0.018088596,0.000074744436,0.00005805515,0.000037658545,0.97810715,0.0016855712,0.00010752756,0.00002420987,0.00026923593,0.00018299378],"about_ca_topic_score_codex":0.0051838662,"about_ca_topic_score_gemma":0.005065913,"teacher_disagreement_score":0.3529558,"about_ca_system_score_codex":0.00008201926,"about_ca_system_score_gemma":0.00003300066,"threshold_uncertainty_score":0.78364897},"labels":[],"label_agreement":null},{"id":"W2123012719","doi":"10.1177/026553220101800302","title":"Examining dialogue: another approach to content specification and to validating inferences drawn from test scores","year":2001,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":162,"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":"Construct (python library); Psychology; Test (biology); Sociocultural evolution; Point (geometry); Cognition; Cognitive psychology; Content (measure theory); Mathematics education; Inference; Construct validity; Linguistics; Natural language processing; Social psychology; Computer science; Artificial intelligence; Psychometrics; Developmental psychology","score_opus":0.24408084356114834,"score_gpt":0.27518337385510755,"score_spread":0.031102530293959207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123012719","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":[0.9266044,0.0001622523,0.0013014188,0.00009141493,0.00008273293,0.00015557438,0.000011158175,0.0002283933,0.07136269],"genre_scores_gemma":[0.98398954,8.609571e-7,0.012645732,0.00049610995,0.0009940148,0.000022272849,0.000031009928,0.00002753582,0.0017929263],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99900526,0.00007466658,0.00022115308,0.00031569865,0.00014309026,0.00024014534],"domain_scores_gemma":[0.99873096,0.00086910796,0.00009656652,0.00017095354,0.00005267454,0.00007975198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035628304,0.00014734812,0.00016754342,0.00009360186,0.00052681257,0.00068011304,0.00013303821,0.000027689426,0.0001709287],"category_scores_gemma":[0.0021978137,0.00012728816,0.000015564527,0.00007850124,0.00005963792,0.00013977868,0.00007019342,0.00018133706,0.00005379833],"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":[0.000009034814,0.000081752616,0.32870877,0.000024624529,0.000018383613,0.0000151389295,0.5310782,0.00015368662,0.0258181,0.0022280428,0.00021681005,0.11164745],"study_design_scores_gemma":[0.001411497,0.0009103002,0.44665372,0.001995737,0.0001279567,0.00004309851,0.5033068,0.007240548,0.0020412807,0.0005905167,0.033464774,0.0022137763],"about_ca_topic_score_codex":0.0063684206,"about_ca_topic_score_gemma":0.0006014605,"teacher_disagreement_score":0.11794497,"about_ca_system_score_codex":0.000019534908,"about_ca_system_score_gemma":0.000012800188,"threshold_uncertainty_score":0.9627189},"labels":[],"label_agreement":null},{"id":"W2129988987","doi":"10.1177/0265532208092433","title":"Test review: College English Test (CET) in China","year":2008,"lang":"en","type":"article","venue":"Language Testing","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":192,"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":"Test (biology); College English; China; Psychology; Language assessment; Test of English as a Foreign Language; Mathematics education; Political science","score_opus":0.017274515028303867,"score_gpt":0.2757766721564041,"score_spread":0.25850215712810026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129988987","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":[0.87624043,0.020240659,0.0024853558,0.008441632,0.00072102575,0.0009573118,0.000029543253,0.002326088,0.08855796],"genre_scores_gemma":[0.9365644,0.000121200464,0.061741397,0.0008107263,0.00011732317,0.0000390768,0.0000038761755,0.000007766623,0.00059423165],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991082,0.000026526664,0.00021592452,0.0002697317,0.00014679045,0.00023282378],"domain_scores_gemma":[0.9985433,0.0008735562,0.000083974024,0.00039116165,0.0000654395,0.000042552976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028310154,0.00010621195,0.00014889018,0.00008491719,0.00012545203,0.000012650796,0.00057651324,0.000047479847,0.000022645136],"category_scores_gemma":[0.005635848,0.00010096123,0.000022910142,0.00092799263,0.000044143333,0.00020505054,0.00015714832,0.0002469618,0.000032661148],"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":[4.736991e-7,0.0007546929,0.9472071,0.00025323205,0.000006408845,0.001056227,0.0049565355,0.000014364612,0.0021569252,0.009492432,0.016718734,0.017382892],"study_design_scores_gemma":[0.0007210357,0.00023745571,0.9806531,0.002421604,0.000010575393,0.0007350305,0.0006214603,0.005557359,0.002512983,0.001761639,0.0040421747,0.0007256031],"about_ca_topic_score_codex":0.00005520729,"about_ca_topic_score_gemma":0.000016492713,"teacher_disagreement_score":0.08796372,"about_ca_system_score_codex":0.00005216243,"about_ca_system_score_gemma":0.00013080741,"threshold_uncertainty_score":0.6747043},"labels":[],"label_agreement":null},{"id":"W2131222006","doi":"10.1177/0265532210364380","title":"Use of tree-based regression in the analyses of L2 reading test items","year":2010,"lang":"en","type":"article","venue":"Language Testing","topic":"Educational Technology and Assessment","field":"Computer Science","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":"University of Alberta","funders":"","keywords":"Reading (process); Cognition; Psychology; Interpretation (philosophy); Cognitive psychology; Test (biology); Tree (set theory); Regression; Regression analysis; Natural language processing; Artificial intelligence; Computer science; Machine learning; Linguistics; Mathematics","score_opus":0.10655832357545793,"score_gpt":0.3862878005927542,"score_spread":0.2797294770172963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131222006","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":[0.99612087,0.00003536544,0.0027653088,0.0004215768,0.000047878053,0.000052650557,0.0000011554006,0.00004014962,0.0005150454],"genre_scores_gemma":[0.8886801,2.169788e-7,0.11121881,0.000057490808,0.000016868074,0.0000046528253,0.0000015298319,0.0000020873224,0.000018235018],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99946815,0.00003758151,0.00016675274,0.000114981565,0.00012352347,0.00008900646],"domain_scores_gemma":[0.9972418,0.0021896425,0.00015433946,0.00035704626,0.000046357953,0.000010844056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003532011,0.000052693522,0.00008678131,0.00011346299,0.000035354067,0.000017512597,0.0004178238,0.000039285405,0.0000034456482],"category_scores_gemma":[0.0019317215,0.000033625016,0.000020204521,0.00058381545,0.00004787209,0.00011842917,0.00004634073,0.00017215141,6.0564406e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.703237e-7,0.00013080485,0.2848825,0.00001644372,0.0000024136416,0.00001200938,0.0012446474,0.00006304986,0.6914383,0.0028929,0.00003269767,0.019283554],"study_design_scores_gemma":[0.00022313769,0.00010332207,0.40952292,0.00037977894,0.00001237367,0.000016636159,0.0012532596,0.060378548,0.52694595,0.0009841033,0.000031350617,0.00014863239],"about_ca_topic_score_codex":0.00032748515,"about_ca_topic_score_gemma":0.00007328141,"teacher_disagreement_score":0.16449241,"about_ca_system_score_codex":0.0000054602037,"about_ca_system_score_gemma":0.000051826115,"threshold_uncertainty_score":0.23125905},"labels":[],"label_agreement":null},{"id":"W2134278381","doi":"10.1177/0265532207083743","title":"The key to success: English language testing in China","year":2008,"lang":"en","type":"article","venue":"Language Testing","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":242,"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":"Ministry of Education, India; Ministry of Earth Sciences","keywords":"Language assessment; China; Context (archaeology); Psychology; English language; Test (biology); Linguistics; Test of English as a Foreign Language; Language proficiency; Chinese language; Mathematics education; History","score_opus":0.0648421376261999,"score_gpt":0.4101903691881555,"score_spread":0.3453482315619556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134278381","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":[0.80107546,0.0002265084,0.0000029332432,0.0005168193,0.00026805277,0.00018374484,0.0000023744346,0.00020813846,0.19751595],"genre_scores_gemma":[0.99033916,0.000005412271,0.0030701533,0.0005809875,0.0013778899,0.000021799364,0.0000022440718,0.000016776807,0.0045855893],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9986054,0.00018989321,0.00023459886,0.00020514781,0.00026788836,0.0004971278],"domain_scores_gemma":[0.99786735,0.0015510223,0.00008655296,0.00021980118,0.000106766,0.0001684935],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00096553774,0.000111047295,0.00011883234,0.0000888387,0.0009532226,0.00011153926,0.00038428942,0.00005532264,0.00007885817],"category_scores_gemma":[0.03555979,0.00009147055,0.000027045733,0.001128732,0.00011815539,0.00012229623,0.000062776206,0.00023385102,0.00005939662],"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":[0.0000024799845,0.000027640659,0.08376308,0.000006508226,0.0000019476256,0.000045721736,0.8534475,0.000034533736,0.00048682766,0.00042179646,0.00028658356,0.061475385],"study_design_scores_gemma":[0.0008019304,0.00008541813,0.48062363,0.0003289129,0.000013459244,0.000029050234,0.46470946,0.0011376055,0.0009347451,0.00014930399,0.05025275,0.0009337381],"about_ca_topic_score_codex":0.061056104,"about_ca_topic_score_gemma":0.013532281,"teacher_disagreement_score":0.39686057,"about_ca_system_score_codex":0.00009257929,"about_ca_system_score_gemma":0.00029779685,"threshold_uncertainty_score":0.9725641},"labels":[],"label_agreement":null},{"id":"W2135663628","doi":"10.1177/0265532208097336","title":"Cognitive diagnostic assessment of L2 reading comprehension ability: Validity arguments for Fusion Model application to <i>LanguEdge</i> assessment","year":2008,"lang":"en","type":"article","venue":"Language Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Reading comprehension; Psychology; Cognition; Test (biology); Profiling (computer programming); Dependability; Comprehension; Reading (process); Cognitive psychology; Computer science; Linguistics","score_opus":0.48241198306348876,"score_gpt":0.5159648486704076,"score_spread":0.033552865606918836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135663628","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":[0.53282154,0.00002596287,0.4643598,0.00004385342,0.00011908979,0.00073168735,0.000042698666,0.00007494368,0.0017804038],"genre_scores_gemma":[0.65655917,0.000003071366,0.34297705,0.00016932332,0.0000724407,0.00012644133,0.000022874297,0.000015533375,0.000054077384],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615526,0.00041592028,0.0010049554,0.00082364917,0.0011815485,0.0004186427],"domain_scores_gemma":[0.9124872,0.0851215,0.00071015797,0.0006375588,0.0008672672,0.0001762872],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0056074806,0.00023332296,0.00056621403,0.00035971837,0.0004046212,0.000060828457,0.00050980196,0.00009164836,0.000020187248],"category_scores_gemma":[0.13390343,0.00019093376,0.00012710292,0.0016911458,0.000076053315,0.00017613792,0.0003434014,0.00019873977,0.000007722714],"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":[0.000037648875,0.00037824857,0.6663653,0.000087881446,0.000023498758,0.000017019802,0.0021402892,0.011272374,0.10087872,0.00018096002,0.00061853585,0.21799952],"study_design_scores_gemma":[0.0009548515,0.00039295235,0.48630923,0.00024255402,0.000052464566,0.000025155636,0.0022547827,0.50187296,0.0033400976,0.0041631595,0.00004141528,0.00035041242],"about_ca_topic_score_codex":0.00012941996,"about_ca_topic_score_gemma":0.0000062281733,"teacher_disagreement_score":0.49060056,"about_ca_system_score_codex":0.00012656604,"about_ca_system_score_gemma":0.00012643693,"threshold_uncertainty_score":0.87339205},"labels":[],"label_agreement":null},{"id":"W2136852860","doi":"10.1177/026553220101800303","title":"Native- and nonnative-speaking EFL teachers’ evaluation of Chinese students’ English writing","year":2001,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":117,"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":"Psychology; Multivariate analysis of variance; First language; Foreign language; English as a foreign language; Point (geometry); Language assessment; Language proficiency; Linguistics; Mathematics education","score_opus":0.06659189121337757,"score_gpt":0.33968104876054345,"score_spread":0.2730891575471659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136852860","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":[0.8948968,0.0007365703,0.000023440432,0.000014768234,0.00010129727,0.00013278962,0.000004095264,0.00015194257,0.10393829],"genre_scores_gemma":[0.9979767,0.0000018831042,0.0005953821,0.00004456181,0.00085652125,0.000009658792,0.000011835904,0.000024815547,0.00047862905],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.998524,0.00029308806,0.0002647721,0.00021500903,0.0004980306,0.00020508697],"domain_scores_gemma":[0.9986761,0.00059030764,0.00021977746,0.00012158848,0.0003531381,0.000039044302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024756333,0.00014696067,0.00018735179,0.0001134496,0.0003803516,0.00017377175,0.00013585495,0.00003119895,0.000311388],"category_scores_gemma":[0.004877461,0.00012714425,0.000034814806,0.000073383286,0.00009510405,0.0002701373,0.00007807865,0.00031789514,0.000002910089],"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":[0.000003157266,0.00004313478,0.23105228,0.000023902705,0.000027449287,0.000008723066,0.6878537,0.00008320155,0.0005194504,0.00041706953,0.0000072686776,0.07996068],"study_design_scores_gemma":[0.0034737135,0.00029275575,0.30365664,0.0013958085,0.00025245687,0.000036065176,0.657928,0.028060086,0.0001336779,0.00082874205,0.002993396,0.0009486682],"about_ca_topic_score_codex":0.0010262446,"about_ca_topic_score_gemma":0.00047890452,"teacher_disagreement_score":0.10345966,"about_ca_system_score_codex":0.000041964457,"about_ca_system_score_gemma":0.00001839471,"threshold_uncertainty_score":0.5839129},"labels":[],"label_agreement":null},{"id":"W2137984677","doi":"10.1177/0265532207071510","title":"A confirmatory approach to differential item functioning on an ESL reading assessment","year":2006,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Advanced Education","funders":"","keywords":"Differential item functioning; Psychology; Reading (process); Test (biology); Language proficiency; Item response theory; Flagging; Cognitive psychology; Psychometrics; Developmental psychology; Linguistics; Mathematics education","score_opus":0.04018946173988295,"score_gpt":0.27198873090135683,"score_spread":0.2317992691614739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137984677","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":[0.6617964,0.000018961307,0.0015210151,0.000018659646,0.00020644105,0.00009409395,0.0000032591593,0.00043042962,0.33591077],"genre_scores_gemma":[0.9885792,3.62004e-8,0.0036052754,0.00026529477,0.0019688662,0.000022381697,0.00005916184,0.000040072187,0.0054597124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99882674,0.00013350404,0.00021733834,0.00029794942,0.00021785883,0.00030661406],"domain_scores_gemma":[0.99934316,0.00023982859,0.00009873646,0.00020193594,0.000040800194,0.00007556553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003283558,0.00017126872,0.00016798142,0.00012698493,0.00075695163,0.00043068652,0.00011873872,0.00003516833,0.00030423794],"category_scores_gemma":[0.00014290733,0.00015440336,0.000042876585,0.000049567974,0.00003298739,0.00014796016,0.0000345337,0.00037895274,0.000045151985],"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":[0.00006704642,0.0013303366,0.036560316,0.00033919036,0.000110817986,0.0001342017,0.3439125,0.011645701,0.031618755,0.4849252,0.0042940956,0.0850618],"study_design_scores_gemma":[0.005339117,0.003028467,0.16351925,0.0029370289,0.00046754873,0.00019709802,0.38039407,0.3092317,0.0016035476,0.0012516737,0.1260356,0.0059948987],"about_ca_topic_score_codex":0.0020718805,"about_ca_topic_score_gemma":0.00010099637,"teacher_disagreement_score":0.48367354,"about_ca_system_score_codex":0.00006243904,"about_ca_system_score_gemma":0.000017979004,"threshold_uncertainty_score":0.6296386},"labels":[],"label_agreement":null},{"id":"W2145055698","doi":"10.1177/0265532210368717","title":"Explaining ESL essay holistic scores: A multilevel modeling approach","year":2010,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":64,"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":"Educational Testing Service","keywords":"Psychology; Argumentation theory; Context (archaeology); Multilevel model; Set (abstract data type); Multilevel modelling; Social psychology; Epistemology; Statistics; Computer science","score_opus":0.11955947065560128,"score_gpt":0.29601648065408587,"score_spread":0.17645700999848457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145055698","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":[0.85147613,0.00014173804,0.008339768,0.000017593993,0.0004266923,0.00010997154,0.000007719938,0.00068146724,0.13879892],"genre_scores_gemma":[0.9679496,2.1614493e-7,0.027342094,0.00015504351,0.001756844,0.000022802773,0.000027153765,0.0000608441,0.0026853804],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866694,0.00007160731,0.00027182678,0.00034427835,0.00021133995,0.00043400016],"domain_scores_gemma":[0.99896485,0.00044740597,0.00011484945,0.00029645092,0.00007893623,0.000097491815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006918146,0.00021514935,0.00021372958,0.00011989843,0.00084080134,0.00038021652,0.00024929512,0.000066219734,0.0003535916],"category_scores_gemma":[0.002272333,0.0001906683,0.00006203242,0.000048951322,0.00009599784,0.00022410683,0.000080607926,0.0010381031,0.000067122375],"study_design_candidate":"simulation_or_modeling","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":[0.000012728871,0.0001495046,0.0025856467,0.00021767989,0.00004208168,0.000093985625,0.84715366,0.013007728,0.0089111775,0.053696293,0.000110688896,0.074018836],"study_design_scores_gemma":[0.00037220184,0.000029098343,0.00006990362,0.00018306183,0.000030599294,0.000035217185,0.04492009,0.9527322,0.000034404227,0.00032729257,0.00085393933,0.00041199356],"about_ca_topic_score_codex":0.0019008702,"about_ca_topic_score_gemma":0.00024905885,"teacher_disagreement_score":0.93972445,"about_ca_system_score_codex":0.000020227784,"about_ca_system_score_gemma":0.000047693895,"threshold_uncertainty_score":0.7775228},"labels":[],"label_agreement":null},{"id":"W2145523583","doi":"10.1177/026553220101800206","title":"ESL/EFL instructors' practices for writing assessment: specific purposes or general purposes?","year":2001,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":57,"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":"Interview; Psychology; Mathematics education; English for academic purposes; Pedagogy; Writing assessment; Language assessment; Process (computing); Sociology; Computer science","score_opus":0.14286572258107863,"score_gpt":0.3633483596418732,"score_spread":0.22048263706079455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145523583","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":[0.8652254,0.0006813967,0.00028363915,0.00019145873,0.00053524796,0.00033917266,0.000016214977,0.000580724,0.13214678],"genre_scores_gemma":[0.9288244,0.000017368438,0.041919816,0.0003419911,0.0060732006,0.00006382285,0.00006567508,0.0000873225,0.02260636],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99823445,0.00014381242,0.00041923093,0.00040611922,0.00025130183,0.0005450682],"domain_scores_gemma":[0.9975294,0.0013603166,0.0006192697,0.00026446735,0.00013309615,0.000093442344],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00075610337,0.00026046435,0.00028069213,0.00013270255,0.001178777,0.00094520295,0.00026155694,0.000062464285,0.0013998081],"category_scores_gemma":[0.0018652576,0.00021457505,0.000090428286,0.000087396096,0.00009756287,0.00062971615,0.00007227982,0.00047942725,0.00003341283],"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":[0.00014464601,0.00033862816,0.04630851,0.0005085911,0.00018885147,0.0007174264,0.15279113,0.00023302967,0.015716976,0.07772937,0.0030804493,0.7022424],"study_design_scores_gemma":[0.0018784379,0.0006267045,0.0030099854,0.0006728903,0.00014506553,0.00039981533,0.09129248,0.0080851335,0.00038586766,0.00063377025,0.8916006,0.001269243],"about_ca_topic_score_codex":0.0013587625,"about_ca_topic_score_gemma":0.000695334,"teacher_disagreement_score":0.8885202,"about_ca_system_score_codex":0.00006109334,"about_ca_system_score_gemma":0.00006700716,"threshold_uncertainty_score":0.99951303},"labels":[],"label_agreement":null},{"id":"W2155682078","doi":"10.1191/0265532206lt337oa","title":"How assessing reading comprehension with multiple-choice questions shapes the construct: a cognitive processing perspective","year":2006,"lang":"en","type":"article","venue":"Language Testing","topic":"Reading and Literacy Development","field":"Psychology","cited_by":243,"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":"Construct (python library); Reading comprehension; Psychology; Variety (cybernetics); Comprehension; Cognitive psychology; Cognition; Multiple choice; Perspective (graphical); Test (biology); Reading (process); Selection (genetic algorithm); Task (project management); Computer science; Linguistics; Artificial intelligence","score_opus":0.02646085463337262,"score_gpt":0.3216621472035859,"score_spread":0.29520129257021327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155682078","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":[0.9665036,0.00098653,0.0047480413,0.00049938913,0.000106297084,0.00035231884,0.000009116025,0.00040976348,0.026384953],"genre_scores_gemma":[0.983562,1.6857334e-7,0.014541077,0.00020991988,0.000345125,0.000057914644,0.000017826209,0.0000418845,0.0012240671],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984963,0.00017971953,0.000218231,0.0004625499,0.00022174108,0.0004214444],"domain_scores_gemma":[0.9963829,0.0027918303,0.0002582659,0.00015523282,0.0003582245,0.000053550055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022837611,0.00024340738,0.00021563077,0.000110819215,0.0007084723,0.00054854597,0.00013763344,0.00006991483,0.000023862496],"category_scores_gemma":[0.0013161798,0.00016355711,0.000034978042,0.0004912741,0.00020898647,0.00031275288,0.00004413012,0.00037854913,0.000011021923],"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":[0.00007025608,0.00023643588,0.6751266,0.0000966199,0.00014972249,0.0006212133,0.10686393,0.00009739653,0.014039426,0.0038326806,0.00018406822,0.19868165],"study_design_scores_gemma":[0.0014877483,0.000102309285,0.8128787,0.0022147405,0.00014684106,0.0010634376,0.17577992,0.0047879256,0.00035592593,0.00029487157,0.00032236314,0.0005651739],"about_ca_topic_score_codex":0.0031255656,"about_ca_topic_score_gemma":0.00024436123,"teacher_disagreement_score":0.19811648,"about_ca_system_score_codex":0.00010575735,"about_ca_system_score_gemma":0.00007505581,"threshold_uncertainty_score":0.66696656},"labels":[],"label_agreement":null},{"id":"W2156770411","doi":"10.1177/0265532209104666","title":"Interacting in pairs in a test of oral proficiency: Co-constructing a better performance","year":2009,"lang":"en","type":"article","venue":"Language Testing","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":163,"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 (biology); Psychology; Meaning (existential); Context (archaeology); Negotiation; Social psychology; Mathematics education","score_opus":0.06423787690980926,"score_gpt":0.44141249514360664,"score_spread":0.3771746182337974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156770411","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":[0.9365197,0.00002648729,0.0000016583723,0.00030179287,0.000059186466,0.00012889445,7.8186287e-7,0.00004161773,0.062919885],"genre_scores_gemma":[0.99403745,8.091318e-7,0.0054835347,0.0002789349,0.00009623174,0.0000036492277,0.0000010735175,0.0000045192396,0.00009381247],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990702,0.00007881753,0.0002915865,0.00013391502,0.00013696199,0.0002885158],"domain_scores_gemma":[0.9990865,0.00061141385,0.00014188293,0.000081596736,0.000038450034,0.000040186038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008745365,0.00007059228,0.00012845383,0.00016864295,0.000090905785,0.00002749879,0.00013347964,0.000041450745,0.000057346493],"category_scores_gemma":[0.006404143,0.00007187673,0.000017200518,0.0006446068,0.000071855684,0.00017822167,0.000011464877,0.00020350429,0.000005524333],"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":[0.000001628253,0.000041211773,0.6462628,0.00001222895,2.9762356e-7,0.000004617653,0.13308917,0.000010916097,0.0028752417,0.000056825942,0.0000025695465,0.21764246],"study_design_scores_gemma":[0.0007903318,0.00012709934,0.7268726,0.0010499323,0.000005274872,0.000014633791,0.25549656,0.008204082,0.006666456,0.00010197318,0.00026911026,0.0004019037],"about_ca_topic_score_codex":0.0072768833,"about_ca_topic_score_gemma":0.0015657432,"teacher_disagreement_score":0.21724056,"about_ca_system_score_codex":0.000072016526,"about_ca_system_score_gemma":0.00018422483,"threshold_uncertainty_score":0.99933374},"labels":[],"label_agreement":null},{"id":"W2159609851","doi":"10.1191/0265532204lt288oa","title":"ESL/EFL instructors’ classroom assessment practices: purposes, methods, and procedures","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":184,"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 Alberta; Queen's University","funders":"","keywords":"Psychology; English as a foreign language; Mathematics education; Tertiary level; Pedagogy; Second language; Language assessment; Linguistics","score_opus":0.06401151606627827,"score_gpt":0.4566933338742858,"score_spread":0.39268181780800754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159609851","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":[0.88996714,0.0010865754,0.00091468275,0.0011419782,0.0003414859,0.0005238556,0.000003373891,0.00038530212,0.105635606],"genre_scores_gemma":[0.66833675,0.000045215726,0.3304719,0.00020610109,0.00041520045,0.000023970428,0.000004750965,0.000017263876,0.00047885528],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983709,0.00023232849,0.00023016303,0.00033622226,0.00042266166,0.0004077303],"domain_scores_gemma":[0.9984898,0.00073267025,0.00038974822,0.0001591591,0.00008756423,0.00014104483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012594918,0.00016029156,0.00019261414,0.00007346245,0.0006034473,0.00033342637,0.00025224616,0.00009594835,0.00007815419],"category_scores_gemma":[0.0042768843,0.00014758801,0.00003457235,0.00035829487,0.00015921147,0.00049749925,0.000119671015,0.00025058602,0.000009544773],"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":[0.000017907454,0.00031890383,0.571827,0.00022070242,0.00014528548,0.00016533208,0.16596346,0.00002255949,0.03583076,0.04561178,0.00037620644,0.17950013],"study_design_scores_gemma":[0.004627989,0.00053177046,0.5233849,0.00087021524,0.00042780183,0.00009897222,0.417603,0.00026029817,0.0024667666,0.022054665,0.025515001,0.0021586095],"about_ca_topic_score_codex":0.005643806,"about_ca_topic_score_gemma":0.0027572415,"teacher_disagreement_score":0.32955724,"about_ca_system_score_codex":0.00015519245,"about_ca_system_score_gemma":0.00047157542,"threshold_uncertainty_score":0.8531784},"labels":[],"label_agreement":null},{"id":"W2162394022","doi":"10.1177/0265532212469178","title":"Differential importance of language components in determining secondary school students’ Chinese reading literacy performance","year":2013,"lang":"en","type":"article","venue":"Language Testing","topic":"Reading and Literacy Development","field":"Psychology","cited_by":6,"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 Saskatchewan","funders":"","keywords":"Dictation; Psychology; Reading (process); Copying; Reading comprehension; Literacy; Mathematics education; Chinese characters; Linguistics; Pedagogy; Computer science; Artificial intelligence","score_opus":0.018120185307201827,"score_gpt":0.3170660889351399,"score_spread":0.29894590362793805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162394022","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":[0.9909829,0.00026635037,0.000020659725,0.000008354644,0.00032153385,0.0003004298,0.0000063107855,0.00010983631,0.007983626],"genre_scores_gemma":[0.9945767,0.0000013829406,0.0033255192,0.00013231408,0.00015120918,0.000079786034,0.000044661585,0.000038662114,0.0016497755],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99807805,0.0000987646,0.0006920455,0.00038782615,0.00026956294,0.00047374805],"domain_scores_gemma":[0.9987798,0.00033131498,0.000307218,0.00040713217,0.000057770827,0.000116811774],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00026623835,0.00025021093,0.00037316536,0.00024420046,0.00007254863,0.000099275814,0.00040033544,0.00007972239,0.0020666614],"category_scores_gemma":[0.00030563975,0.00021850422,0.000050233233,0.00037389767,0.000034625595,0.00037045477,0.00015525674,0.0003978766,0.00017582993],"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":[0.000013930261,0.00009916065,0.888968,0.00008557476,0.000025074696,0.00012088416,0.03972847,0.000002881238,0.024612505,0.0000029872795,0.000030188663,0.04631038],"study_design_scores_gemma":[0.0009429338,0.000048353508,0.9947724,0.00046884833,0.0000069461917,0.00005335868,0.002020498,0.0010001191,0.0004340401,0.000007810401,0.0000071722875,0.00023752809],"about_ca_topic_score_codex":0.0010442764,"about_ca_topic_score_gemma":0.000014676053,"teacher_disagreement_score":0.10580443,"about_ca_system_score_codex":0.00006587046,"about_ca_system_score_gemma":0.000024089286,"threshold_uncertainty_score":0.9988456},"labels":[],"label_agreement":null},{"id":"W2168715918","doi":"10.1177/02655322090260020602","title":"Test review: The Versant Spanish <sup>TM</sup> Test","year":2009,"lang":"en","type":"article","venue":"Language Testing","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Test (biology); Psychology; Geology","score_opus":0.03386165576883628,"score_gpt":0.2910663115460739,"score_spread":0.2572046557772376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168715918","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":[0.95112294,0.011087005,0.0000110086985,0.0069765183,0.00019951374,0.00092145026,0.00007281004,0.0010276118,0.028581118],"genre_scores_gemma":[0.94584936,0.0003100868,0.00048136502,0.051716927,0.0005264709,0.0000117904465,0.000008989965,0.000029790825,0.0010652423],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99798656,0.00016044629,0.00038084,0.0006023324,0.00027379347,0.00059605285],"domain_scores_gemma":[0.99450094,0.0044465982,0.00019189941,0.0007069816,0.00005035773,0.00010320313],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00048470544,0.00028472723,0.00029892143,0.000050554867,0.00038482284,0.00008257599,0.00074254134,0.000078867815,0.0001843066],"category_scores_gemma":[0.029490003,0.00018741393,0.00010706393,0.00061654113,0.00016814604,0.00014023032,0.00012300498,0.0004982287,0.00029760294],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057543025,0.00023202952,0.0012910963,0.00011276802,0.0000032689395,0.0065671727,0.0028107446,0.000018345192,0.93765354,0.00003729121,0.011389119,0.03987885],"study_design_scores_gemma":[0.004172631,0.004306541,0.008966379,0.0071696686,0.0006270901,0.035216056,0.0057064504,0.0067928564,0.83427554,0.0013955913,0.08682118,0.0045499913],"about_ca_topic_score_codex":0.000069928894,"about_ca_topic_score_gemma":0.0000068978393,"teacher_disagreement_score":0.103378005,"about_ca_system_score_codex":0.000027416723,"about_ca_system_score_gemma":0.00004636549,"threshold_uncertainty_score":0.978685},"labels":[],"label_agreement":null},{"id":"W2318200755","doi":"10.1177/0265532213509810","title":"Examining the impact of L2 proficiency and keyboarding skills on scores on TOEFL-iBT writing tasks","year":2013,"lang":"en","type":"article","venue":"Language Testing","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":45,"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":"Test of English as a Foreign Language; Psychology; Test (biology); Language proficiency; Task (project management); Context (archaeology); English language; Mathematics education","score_opus":0.04433657734822507,"score_gpt":0.3557343872788868,"score_spread":0.31139780993066174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2318200755","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":[0.94112355,0.00011604401,0.0000083628365,0.00016186312,0.000060947237,0.00025013267,0.0000024375072,0.000108198445,0.05816849],"genre_scores_gemma":[0.9984141,0.0000034140153,0.000697928,0.000087032255,0.00048926397,0.00002248504,0.0000020152197,0.000015084695,0.00026870635],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987514,0.00017989325,0.00022147347,0.00021930056,0.00027169829,0.00035623554],"domain_scores_gemma":[0.997257,0.0022129791,0.00018715703,0.00016553783,0.000105407154,0.000071908034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001226496,0.00011699738,0.0001442264,0.00008196316,0.0007270469,0.00019783137,0.00016868804,0.0000533656,0.00005256522],"category_scores_gemma":[0.005429271,0.00008267799,0.00003961862,0.000318105,0.00016212945,0.00014053333,0.000034857396,0.00019878878,0.000013984215],"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":[0.0000067161563,0.00017367785,0.4198041,0.00008381053,0.00002802822,0.000008499903,0.21221998,0.0003940443,0.025049184,0.002970464,0.00053799973,0.3387235],"study_design_scores_gemma":[0.00036130424,0.000528318,0.77323806,0.0020104311,0.000024240468,0.000009936045,0.21863447,0.0019309773,0.0021914148,0.00066028745,0.000009711766,0.00040084653],"about_ca_topic_score_codex":0.010379515,"about_ca_topic_score_gemma":0.000051128784,"teacher_disagreement_score":0.35343397,"about_ca_system_score_codex":0.00008147863,"about_ca_system_score_gemma":0.00010001522,"threshold_uncertainty_score":0.99621046},"labels":[],"label_agreement":null},{"id":"W2337150116","doi":"10.1177/0265532214559115","title":"Design in four diagnostic language assessments","year":2015,"lang":"en","type":"article","venue":"Language Testing","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":9,"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":"Language assessment; Language proficiency; Psychology; Educational assessment; Process (computing); Intervention (counseling); Educational research; Mathematics education; Management science; Computer science; Pedagogy","score_opus":0.2169898390405153,"score_gpt":0.45664737825958907,"score_spread":0.23965753921907376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337150116","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":[0.9064298,0.0006309916,0.0022691009,0.00018529393,0.00068104063,0.00027220912,0.0000052341315,0.00014386776,0.089382455],"genre_scores_gemma":[0.9737221,5.469306e-7,0.022110252,0.0007883082,0.0002640341,0.00012028886,0.000016678268,0.000021363285,0.0029564074],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985015,0.0003299797,0.00025123823,0.0003275388,0.00021416294,0.00037562035],"domain_scores_gemma":[0.9971808,0.0022648973,0.00009315529,0.00026198273,0.0000477164,0.00015143258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007257408,0.00014949957,0.00016479417,0.000093588314,0.00003452504,0.0000345979,0.00023773896,0.00008543235,0.0007884694],"category_scores_gemma":[0.0017033676,0.0001292658,0.000023960367,0.00042095972,0.000026483867,0.000083819876,0.000046065375,0.00024568726,0.0007392911],"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":[0.00006337519,0.0009274896,0.8644369,0.00001936628,0.000050996463,0.0025073169,0.028069131,0.0002056492,0.0017335158,0.00091752387,0.006765139,0.0943036],"study_design_scores_gemma":[0.002171991,0.0004366001,0.9734071,0.00012430527,0.000023880824,0.0001648063,0.019679053,0.00032691177,0.00008796591,0.0027604282,0.0003349666,0.00048197535],"about_ca_topic_score_codex":0.00074181386,"about_ca_topic_score_gemma":0.000023825734,"teacher_disagreement_score":0.10897022,"about_ca_system_score_codex":0.00007258174,"about_ca_system_score_gemma":0.00005724497,"threshold_uncertainty_score":0.95023376},"labels":[],"label_agreement":null},{"id":"W2599956837","doi":"10.1177/0265532216684576","title":"Book Review: Focus on Assessment","year":2016,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","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":"University of Ottawa","funders":"","keywords":"Focus (optics); Psychology; Linguistics; Philosophy; Optics","score_opus":0.032919987551438844,"score_gpt":0.3820371374063785,"score_spread":0.3491171498549397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2599956837","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063560978,0.049841147,0.00031162592,0.019971998,0.00035572206,0.00056498474,0.0000044667613,0.0004652489,0.92212874],"genre_scores_gemma":[0.74898744,0.011241683,0.008742928,0.053436033,0.0033476981,0.00017588933,0.0000060360226,0.00008353755,0.17397878],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988451,0.00014989104,0.00014152589,0.00017956948,0.0003998061,0.0002841098],"domain_scores_gemma":[0.9990121,0.00061920885,0.000084784544,0.00016497685,0.00004506898,0.000073854666],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007457504,0.00008741454,0.00012604444,0.00002854758,0.00023416654,0.00003564494,0.000208229,0.0000322609,0.0027160947],"category_scores_gemma":[0.0007724354,0.000057213198,0.0000431595,0.00018121215,0.000058264603,0.00013711031,0.000042467265,0.000069687645,0.00027905605],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003486994,0.00011815684,0.04055792,0.000075834934,0.000029923309,0.00009783427,0.0050381594,1.5776098e-7,0.004292534,0.0073035294,0.49328735,0.4491951],"study_design_scores_gemma":[0.0011973215,0.00026540563,0.05647068,0.005692355,0.0000871443,0.000003092869,0.003840892,0.000010299217,0.000522372,0.00070564065,0.93042296,0.00078182144],"about_ca_topic_score_codex":0.00024996576,"about_ca_topic_score_gemma":0.00005375852,"teacher_disagreement_score":0.74814993,"about_ca_system_score_codex":0.00011009288,"about_ca_system_score_gemma":0.00006975269,"threshold_uncertainty_score":0.9981955},"labels":[],"label_agreement":null},{"id":"W2611914815","doi":"10.1177/0265532217703433","title":"Developing a user-oriented second language comprehensibility scale for English-medium universities","year":2017,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":59,"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 Alberta; Concordia University","funders":"","keywords":"Operationalization; Formative assessment; Psychology; Construct (python library); English for academic purposes; Scale (ratio); Language proficiency; Point (geometry); Task (project management); Focus (optics); Rating scale; Mathematics education; Linguistics; Computer science","score_opus":0.04907756014366304,"score_gpt":0.29045579136247907,"score_spread":0.24137823121881602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611914815","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":[0.93787754,0.00012431169,0.00058020715,0.000098446086,0.00062958134,0.00018870523,0.00005883514,0.00043013625,0.06001224],"genre_scores_gemma":[0.97072804,2.5341495e-7,0.008520718,0.00018625116,0.0013724217,0.000009180869,0.000046032976,0.000032793185,0.019104317],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9989377,0.00006617502,0.00019769737,0.00029964955,0.00013616183,0.0003626014],"domain_scores_gemma":[0.99850625,0.00055470946,0.00022251086,0.00044071206,0.00020973707,0.000066088236],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00045040753,0.00017743034,0.00023182073,0.00006704454,0.002093313,0.00043155823,0.0003136562,0.00005273215,0.000496938],"category_scores_gemma":[0.0010649825,0.0001705791,0.00007504365,0.00002058194,0.00022030527,0.00038923384,0.0001489197,0.00029642016,0.000013632239],"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":[0.000037272417,0.00004886645,0.016086375,0.00044668769,0.00005523515,0.000060383816,0.95750254,0.000018155439,0.0016190053,0.016632354,0.0010057343,0.006487359],"study_design_scores_gemma":[0.0018108615,0.00013277115,0.010415663,0.000644811,0.000082752435,0.000010102482,0.8136135,0.0020834294,0.0016960334,0.00022031293,0.16840948,0.00088031415],"about_ca_topic_score_codex":0.0015573589,"about_ca_topic_score_gemma":0.003623045,"teacher_disagreement_score":0.16740376,"about_ca_system_score_codex":0.000088134955,"about_ca_system_score_gemma":0.00009195081,"threshold_uncertainty_score":0.9992058},"labels":[],"label_agreement":null},{"id":"W2751665091","doi":"10.1177/0265532217725776","title":"Developing and evaluating a computerized adaptive testing version of the Word Part Levels Test","year":2017,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Affix; Test (biology); Vocabulary; Computerized adaptive testing; Natural language processing; Computer science; Strengths and weaknesses; Word (group theory); Vocabulary development; Psychology; Artificial intelligence; Linguistics; Psychometrics; Social psychology","score_opus":0.1617082178408199,"score_gpt":0.3865890369439115,"score_spread":0.2248808191030916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751665091","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":[0.985706,0.00064651325,0.0005732497,0.00011133463,0.00033082074,0.00021031452,0.000011569135,0.00010196245,0.012308283],"genre_scores_gemma":[0.95322484,1.4356395e-7,0.04534487,0.00070496043,0.00024240733,0.000010272709,0.0000025019444,0.000024307712,0.00044569353],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987025,0.00019300623,0.00030424196,0.00031629478,0.00018610424,0.0002978563],"domain_scores_gemma":[0.99691653,0.0017586288,0.0005989927,0.00053820264,0.00013618877,0.000051464613],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00079064304,0.00016231202,0.00022783039,0.000051199542,0.0008287188,0.000102123384,0.00036492368,0.00007422241,0.0009806536],"category_scores_gemma":[0.006763358,0.00012922297,0.00004254717,0.00016166893,0.00014060913,0.0001251,0.00033293382,0.0002690206,0.000023114342],"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":[0.00005352444,0.0000640029,0.16652374,0.000104035345,0.00009121967,0.00018218522,0.030091329,0.00004992958,0.086508535,0.00052744476,0.00014357732,0.71566045],"study_design_scores_gemma":[0.0019195821,0.0001703422,0.97003293,0.0012931329,0.000059816703,0.00013886073,0.014790735,0.009332729,0.001687327,0.00010350563,0.00010326191,0.00036776724],"about_ca_topic_score_codex":0.00044657642,"about_ca_topic_score_gemma":0.000009796505,"teacher_disagreement_score":0.8035092,"about_ca_system_score_codex":0.000034656634,"about_ca_system_score_gemma":0.000058824182,"threshold_uncertainty_score":0.9999326},"labels":[],"label_agreement":null},{"id":"W2776964473","doi":"10.1177/0265532217716732","title":"The development of EFL examinations in Haiti: Collaboration and language assessment literacy development","year":2017,"lang":"en","type":"article","venue":"Language Testing","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Christian ministry; Psychology; Literacy; Medical education; Professional development; English language; Pedagogy; Faculty development; Mathematics education; Language assessment; Language development; Political science; Medicine","score_opus":0.07883816509620944,"score_gpt":0.5035994185271453,"score_spread":0.42476125343093585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2776964473","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":[0.95795035,0.00015558471,0.000042161548,0.00042308558,0.000102032245,0.00017538785,0.0000015228171,0.000022084414,0.0411278],"genre_scores_gemma":[0.964879,0.000004001315,0.033300173,0.00003844248,0.000075085205,0.000027159125,0.000005382847,0.0000047676285,0.0016660056],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99921685,0.00009095631,0.00024370162,0.00010674282,0.00018022563,0.00016153365],"domain_scores_gemma":[0.99901617,0.00045659597,0.00020149775,0.00015210982,0.00012396231,0.00004969623],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0011145512,0.000060117032,0.000074607844,0.000054081833,0.001381724,0.00026593634,0.00017863559,0.00003110625,0.000019100784],"category_scores_gemma":[0.0028032442,0.000050220886,0.000006474209,0.00013301377,0.00009920088,0.00017433595,0.00005289077,0.000071669434,0.0000028228023],"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":[7.507459e-7,0.000023737002,0.028403595,0.00001234199,0.000002892629,0.000001364498,0.5091015,8.358121e-7,0.0009286687,0.0013007561,0.000008670154,0.46021485],"study_design_scores_gemma":[0.0002613286,0.000006579311,0.84312564,0.0001261786,0.0000034539735,4.801729e-7,0.14374685,0.0002833077,0.0020997117,0.00004665881,0.010168785,0.00013104336],"about_ca_topic_score_codex":0.002074819,"about_ca_topic_score_gemma":0.020138813,"teacher_disagreement_score":0.814722,"about_ca_system_score_codex":0.00010373937,"about_ca_system_score_gemma":0.00083928305,"threshold_uncertainty_score":0.99991834},"labels":[],"label_agreement":null},{"id":"W2782384206","doi":"10.1177/0265532217750692","title":"Examining sources of variability in repeaters’ L2 writing scores: The case of the PTE Academic writing section","year":2018,"lang":"en","type":"article","venue":"Language Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":11,"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":"Test (biology); Psychology; Context (archaeology); Boston Naming Test; Language assessment; Language proficiency; Mathematics education; Cognition","score_opus":0.3740090240133829,"score_gpt":0.4424069973241175,"score_spread":0.0683979733107346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782384206","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":[0.9916693,0.00021102178,0.0027101394,0.00006900854,0.0003475023,0.00020038287,0.000004981368,0.000054004988,0.004733643],"genre_scores_gemma":[0.984133,0.000001063758,0.015330731,0.000072022165,0.00040918696,0.0000061222877,2.0222414e-7,0.000012224996,0.00003543585],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9947868,0.0023896098,0.0014007796,0.00050588616,0.00054803735,0.00036889093],"domain_scores_gemma":[0.8812267,0.115811735,0.0014950268,0.0010132339,0.00040486336,0.000048406004],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043951046,0.00015094098,0.00035407374,0.0002827357,0.00038389812,0.00007337797,0.0009004445,0.0001184916,0.00003911367],"category_scores_gemma":[0.42799452,0.000083968676,0.00007881052,0.003934137,0.0004176251,0.00018757799,0.00050096004,0.0005721146,0.0000015653378],"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":[0.000006502964,0.000009143778,0.77992404,0.000023682047,0.000004543639,0.000037589292,0.008377585,0.00011393139,0.012902584,0.000048908325,0.000008312566,0.19854316],"study_design_scores_gemma":[0.00047771228,0.00015430538,0.8202249,0.0009758305,0.000033075605,0.0014294875,0.121755175,0.032621305,0.01640105,0.0056412965,0.00001124032,0.00027466007],"about_ca_topic_score_codex":0.0018823608,"about_ca_topic_score_gemma":0.00012432784,"teacher_disagreement_score":0.38404348,"about_ca_system_score_codex":0.0000366806,"about_ca_system_score_gemma":0.000048936563,"threshold_uncertainty_score":0.98445356},"labels":[],"label_agreement":null},{"id":"W2917835789","doi":"10.1177/0265532219828252","title":"The Test of English for International Communication (TOEIC <sup>®</sup> )","year":2019,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":22,"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":"American Psychological Association; Educational Testing Service","keywords":"TOEIC; Psychology; Test (biology); Linguistics; International communication; Language proficiency; Language assessment; Mathematics education; Communication; Philosophy; Reading (process)","score_opus":0.02662448091769125,"score_gpt":0.2592560255326446,"score_spread":0.23263154461495333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2917835789","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":[0.7852494,0.00045726803,0.000024417264,0.00016806203,0.00038466652,0.0001964909,0.00002004363,0.00016014744,0.21333946],"genre_scores_gemma":[0.9891253,0.0000020022992,0.0013045719,0.00007407359,0.00071866234,0.000011606202,0.000024651137,0.000014401297,0.008724702],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995065,0.000041969717,0.00016254118,0.000082461476,0.00009406458,0.000112461144],"domain_scores_gemma":[0.99632853,0.0030112846,0.00012552878,0.00021669867,0.00030506164,0.000012913915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005150306,0.000060163355,0.0000752822,0.00002708993,0.00029960537,0.00011757398,0.00026559984,0.000017401057,0.00019687512],"category_scores_gemma":[0.007995432,0.000044111657,0.00003730037,0.000019415915,0.00005772751,0.00009304401,0.000050344006,0.00015870223,0.000019523528],"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":[0.000020430212,0.000110353256,0.04517521,0.00012459878,0.000072327544,9.093382e-7,0.7968059,0.0013165489,0.0008581142,0.06969133,0.003490851,0.0823334],"study_design_scores_gemma":[0.0014504433,0.000313038,0.0022931667,0.00065495074,0.000055912995,0.0000030436156,0.29291472,0.09292159,0.00038627267,0.0017539843,0.606787,0.0004658419],"about_ca_topic_score_codex":0.00023720162,"about_ca_topic_score_gemma":0.000069371716,"teacher_disagreement_score":0.60329616,"about_ca_system_score_codex":0.000013804316,"about_ca_system_score_gemma":0.000011546271,"threshold_uncertainty_score":0.9571856},"labels":[],"label_agreement":null},{"id":"W2950885273","doi":"10.1177/0265532219854982","title":"Book Review: Assessment in the Language Classroom: Teachers Supporting Student Learning","year":2019,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","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":"Carleton University","funders":"","keywords":"Psychology; Mathematics education; Language assessment; Pedagogy","score_opus":0.018881440790615857,"score_gpt":0.31109286189690133,"score_spread":0.29221142110628545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950885273","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":[0.7667114,0.06447087,0.0000073539513,0.0006534277,0.0001986447,0.0004960411,0.0000021608178,0.00028527828,0.16717482],"genre_scores_gemma":[0.9449114,0.00006612099,0.00026900522,0.018999804,0.0005848108,0.000049652415,0.000054416992,0.00005618984,0.035008606],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9976869,0.0005313844,0.0004745255,0.0003603195,0.00041668658,0.0005301838],"domain_scores_gemma":[0.9984253,0.0008082243,0.00030706756,0.00037773943,0.000034272587,0.000047420293],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002316885,0.0002400825,0.00032998328,0.00010717142,0.00031497588,0.00029374068,0.00042198919,0.000044378543,0.008924027],"category_scores_gemma":[0.0007171384,0.00017086913,0.000103636296,0.00011620224,0.0000469035,0.00025553352,0.00009459664,0.0014547388,0.00024042472],"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":[0.000002967667,0.00013100603,0.076621026,0.0005544994,0.00004954537,0.00047628567,0.834135,0.0001675473,0.0008902212,0.00092859165,0.012915298,0.07312802],"study_design_scores_gemma":[0.00074605405,0.00019192965,0.0066460553,0.0020426267,0.00007779018,0.00005745385,0.7436022,0.0010147549,0.000019154642,0.0000057180478,0.24502389,0.00057232287],"about_ca_topic_score_codex":0.0016491994,"about_ca_topic_score_gemma":0.00033855843,"teacher_disagreement_score":0.2321086,"about_ca_system_score_codex":0.00008005259,"about_ca_system_score_gemma":0.000043317774,"threshold_uncertainty_score":0.9919819},"labels":[],"label_agreement":null},{"id":"W3039959558","doi":"10.1177/0265532220930348","title":"Change in home language environment and English literacy achievement over time: A multi-group latent growth curve modeling investigation","year":2020,"lang":"en","type":"article","venue":"Language Testing","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":10,"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":"Latent growth modeling; Literacy; Psychology; Longitudinal study; Home language; Competence (human resources); Population; Academic achievement; Mathematics education; Immigration; Developmental psychology; Pedagogy; Social psychology; Demography; Sociology; Geography; Medicine","score_opus":0.08900675997372587,"score_gpt":0.3676722898153619,"score_spread":0.278665529841636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039959558","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":[0.9973543,0.0006442155,0.00006875468,0.0009083477,0.000064817425,0.00037446053,0.000011740892,0.00013336008,0.00043996613],"genre_scores_gemma":[0.991568,0.000032302178,0.005209423,0.002271262,0.000718851,0.00004030769,0.000036066038,0.000018928831,0.00010483654],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876887,0.00018220046,0.00023933031,0.00028784698,0.00022425666,0.00029749126],"domain_scores_gemma":[0.99940246,0.00014935905,0.00009099339,0.00009458257,0.00003226719,0.00023031354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046719922,0.00013525224,0.00014552854,0.0000763698,0.00014770485,0.00010264386,0.00011950781,0.000067843124,0.00013593411],"category_scores_gemma":[0.0011674123,0.00014054606,0.000025188152,0.00026850213,0.00005500153,0.0003104684,0.000078510406,0.00018587944,0.000026367554],"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":[0.000005001341,0.00005340033,0.10644872,0.000043878234,0.0000047013377,0.000013067053,0.87470734,0.00007086137,0.0025289515,0.00016792619,0.0000074541895,0.01594871],"study_design_scores_gemma":[0.0027246529,0.0001521907,0.16234109,0.00042566255,0.000045890734,0.0000017532825,0.05355741,0.7783238,0.00035106047,0.00012129123,0.0008601656,0.0010950264],"about_ca_topic_score_codex":0.016609764,"about_ca_topic_score_gemma":0.00037971913,"teacher_disagreement_score":0.82114995,"about_ca_system_score_codex":0.000096758544,"about_ca_system_score_gemma":0.000038449165,"threshold_uncertainty_score":0.98993874},"labels":[],"label_agreement":null},{"id":"W3040446934","doi":"10.1177/0265532220937830","title":"More efficient processes for creating automated essay scoring frameworks: A demonstration of two algorithms","year":2020,"lang":"en","type":"article","venue":"Language Testing","topic":"Topic Modeling","field":"Computer Science","cited_by":51,"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 Alberta","funders":"","keywords":"Rubric; Artificial intelligence; Machine learning; Computer science; Support vector machine; Convolutional neural network; Feature engineering; Deep learning; Artificial neural network; Natural language processing; Meaning (existential); Feature (linguistics); Strengths and weaknesses; F1 score; Algorithm; Mathematics; Mathematics education; Linguistics; Psychology","score_opus":0.0348837319221498,"score_gpt":0.30971148316334696,"score_spread":0.2748277512411972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040446934","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2182092,0.0001881094,0.7799336,0.00028836972,0.000049233946,0.00020911175,0.0000024428443,0.0008561254,0.00026381074],"genre_scores_gemma":[0.54450893,1.0994344e-7,0.45523322,0.00013533254,0.000096614516,0.000014530818,0.0000016200776,0.000007476328,0.0000021467538],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891776,0.000022290971,0.00030657055,0.0003387753,0.00018015476,0.0002344434],"domain_scores_gemma":[0.9987445,0.00059219555,0.00019895984,0.0002060337,0.00018957985,0.00006876143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023099816,0.00011754832,0.00016893321,0.000042320862,0.000116919815,0.000097455835,0.00036803866,0.000060022856,0.0000011624523],"category_scores_gemma":[0.0026018152,0.00011357874,0.00003051833,0.0005957231,0.00001890998,0.00017008865,0.00012259015,0.00015669136,9.1661866e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007934903,0.00009054314,0.008498736,0.0015348309,0.000035310797,0.000044173335,0.07838282,0.6210707,0.061894447,0.005106845,0.000011367171,0.2233223],"study_design_scores_gemma":[0.00023428553,0.000040076637,0.00015098127,0.0003069196,0.000008587147,0.00000740604,0.00059788,0.9859968,0.012452692,0.0000868758,8.432411e-7,0.00011669176],"about_ca_topic_score_codex":0.00006518512,"about_ca_topic_score_gemma":0.0000026109778,"teacher_disagreement_score":0.36492607,"about_ca_system_score_codex":0.00002445424,"about_ca_system_score_gemma":0.00014175991,"threshold_uncertainty_score":0.46316063},"labels":[],"label_agreement":null},{"id":"W3087153552","doi":"10.1177/0265532220957298","title":"Hanyu Shuiping Kaoshi (HSK): A multi-level, multi-purpose proficiency test","year":2020,"lang":"en","type":"article","venue":"Language Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":50,"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":"Language proficiency; Test (biology); Psychology; Argument (complex analysis); Language assessment; Scale (ratio); Mathematics education; Linguistics; Geography","score_opus":0.8227491867455936,"score_gpt":0.5099737195301289,"score_spread":0.3127754672154647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087153552","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":[0.6171786,0.0030291248,0.36631793,0.0012476112,0.0008284577,0.00097530236,0.00008678201,0.0014841938,0.008851971],"genre_scores_gemma":[0.55950004,0.0000022654522,0.4384884,0.0010543712,0.000295155,0.000020140556,0.0000030020208,0.000034220993,0.0006024119],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9948754,0.0004547962,0.0012147677,0.0012781551,0.0012733941,0.00090349314],"domain_scores_gemma":[0.9553905,0.041881032,0.0008040175,0.0009346224,0.0004909616,0.0004988471],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0050352854,0.00038864595,0.0006416252,0.00042248293,0.0005002351,0.0005397485,0.0017285668,0.00015021299,0.00032279262],"category_scores_gemma":[0.58667415,0.00029838667,0.0001700977,0.0061946306,0.00014165154,0.00041478517,0.00067698554,0.0005704049,0.00047430748],"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":[0.000012024313,0.00020564096,0.36005777,0.000054807497,0.000012762554,0.00034692872,0.0077433777,0.00023384902,0.059637427,0.000036578098,0.00071235024,0.5709465],"study_design_scores_gemma":[0.0034309558,0.0007012363,0.4814237,0.00038517584,0.000060250317,0.00021360845,0.023980051,0.47916046,0.006773615,0.00045781696,0.001710408,0.0017027049],"about_ca_topic_score_codex":0.00018105634,"about_ca_topic_score_gemma":0.000021959377,"teacher_disagreement_score":0.5816389,"about_ca_system_score_codex":0.000050778563,"about_ca_system_score_gemma":0.00011980023,"threshold_uncertainty_score":0.99994683},"labels":[],"label_agreement":null},{"id":"W3214027731","doi":"10.1177/02655322211052680","title":"Investigating and optimizing score dependability of a local ITA speaking test across language groups: A generalizability theory approach","year":2021,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"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":"Generalizability theory; Dependability; Language proficiency; Psychology; Variance (accounting); Test (biology); Construct (python library); Formative assessment; Computer science; Mathematics education; Developmental psychology; Accounting","score_opus":0.050868985531210546,"score_gpt":0.3497865942429446,"score_spread":0.29891760871173406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214027731","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":[0.98038435,0.0011528842,0.0047810245,0.000044148735,0.00006582489,0.00023256343,0.00001666114,0.00015781727,0.01316473],"genre_scores_gemma":[0.93098235,0.0000042540373,0.06854533,0.00010991435,0.00022123879,0.00001201781,0.000015683407,0.000021010947,0.00008821429],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99761295,0.00050648104,0.00039708952,0.0005083492,0.00044740277,0.00052771973],"domain_scores_gemma":[0.9972788,0.0018545347,0.00022308495,0.00032554808,0.00016898093,0.00014902363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029051993,0.00019110511,0.00033547494,0.000031750697,0.0005742435,0.0001790089,0.00026772174,0.00011366411,0.00006458023],"category_scores_gemma":[0.0068359906,0.00018702577,0.000076177195,0.0006511075,0.0007264764,0.00027953964,0.00038376372,0.00026989277,0.0000015083446],"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":[0.000004317801,0.00015638063,0.6197887,0.00023000389,0.000026692574,0.000048284066,0.32065213,0.000079439444,0.027888648,0.0017110135,0.000004185023,0.02941021],"study_design_scores_gemma":[0.0006748703,0.000045657373,0.09744235,0.00025980826,0.000060857717,0.000024148412,0.8915778,0.003956292,0.004598945,0.00089438155,0.000008816892,0.00045611832],"about_ca_topic_score_codex":0.0031399147,"about_ca_topic_score_gemma":0.0015628922,"teacher_disagreement_score":0.57092565,"about_ca_system_score_codex":0.00010112506,"about_ca_system_score_gemma":0.00016792513,"threshold_uncertainty_score":0.8183813},"labels":[],"label_agreement":null},{"id":"W4251721468","doi":"10.1177/0265532220925448","title":"Understanding writing quality change: A longitudinal study of repeaters of a high-stakes standardized English proficiency test","year":2020,"lang":"en","type":"article","venue":"Language Testing","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":7,"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":"Language proficiency; Psychology; Test (biology); Sophistication; Linguistics; Mathematics education","score_opus":0.4041793967710166,"score_gpt":0.4111835522633015,"score_spread":0.007004155492284891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251721468","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":[0.9934057,0.00009116431,0.000314361,0.00027571103,0.00009609381,0.00048077822,0.000026200622,0.00022943689,0.005080551],"genre_scores_gemma":[0.997425,0.0000016506959,0.00186095,0.00003498076,0.00061961217,0.000020845699,0.0000046631003,0.00001642345,0.0000158506],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99789363,0.00033018188,0.00055309245,0.00032045247,0.0005815259,0.0003211011],"domain_scores_gemma":[0.9974143,0.0014634046,0.00049425033,0.0001634391,0.00035736855,0.0001072413],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022412878,0.00012244761,0.00034218968,0.00008010985,0.000408273,0.00007068421,0.00020681204,0.00005387907,0.000028398748],"category_scores_gemma":[0.018707767,0.00012796363,0.000048337453,0.00082544336,0.00015454748,0.00019312817,0.000052279767,0.0001639019,5.4505745e-7],"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":[0.000019706862,0.00021700545,0.51278347,0.00020175999,0.000013980785,0.000009674598,0.4819844,0.0000072156354,0.002245616,0.0011252656,0.00001413296,0.0013777819],"study_design_scores_gemma":[0.0008441821,0.00040196974,0.06764398,0.0003562781,0.000049232865,6.725659e-7,0.92963296,0.00007016296,0.0007148705,0.00009175786,0.000003507175,0.00019044752],"about_ca_topic_score_codex":0.010348266,"about_ca_topic_score_gemma":0.00083589106,"teacher_disagreement_score":0.44764856,"about_ca_system_score_codex":0.00011977019,"about_ca_system_score_gemma":0.00014136509,"threshold_uncertainty_score":0.9962419},"labels":[],"label_agreement":null},{"id":"W4251941390","doi":"10.1177/0265532220929918","title":"Automated scoring of junior and senior high essays using Coh-Metrix features: Implications for large-scale language testing","year":2020,"lang":"en","type":"article","venue":"Language Testing","topic":"Software Engineering Research","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; University of Alberta","funders":"","keywords":"Natural language processing; Artificial intelligence; Rating scale; Computer science; Scale (ratio); Quality (philosophy); Construct (python library); Psychology; Computational linguistics; Disadvantaged; Machine learning; Developmental psychology","score_opus":0.0384669575825602,"score_gpt":0.314934657209404,"score_spread":0.2764676996268438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251941390","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":[0.7929544,0.00044364805,0.20430955,0.00016516946,0.00006152351,0.00032973225,0.00005130433,0.0016434584,0.000041233707],"genre_scores_gemma":[0.6143281,3.8070345e-7,0.38544387,0.0000633857,0.0000993271,0.000023442026,0.000005428649,0.000026251724,0.00000985091],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984274,0.0000440952,0.00028749226,0.0004702182,0.0002178771,0.0005529008],"domain_scores_gemma":[0.99559134,0.0034210896,0.00014530416,0.00042654775,0.00021282712,0.00020285932],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00050997426,0.00018341948,0.0002773508,0.00017264928,0.00020698,0.0001450411,0.00055239134,0.00007625024,0.0000024065112],"category_scores_gemma":[0.0128062265,0.00018765165,0.00003671898,0.0017116492,0.000031806114,0.00025655155,0.0004246361,0.00022983085,0.0000016655974],"study_design_candidate":"simulation_or_modeling","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":[0.000010995404,0.000081927305,0.11395604,0.0011042666,0.000060087703,0.000071702714,0.031062406,0.0050172703,0.8071012,0.0009538756,0.0001414415,0.040438812],"study_design_scores_gemma":[0.0010255192,0.00017069154,0.10061292,0.00032041917,0.000027180511,0.00010530819,0.0017062154,0.87770486,0.017786121,0.00008529035,0.000010387262,0.00044508177],"about_ca_topic_score_codex":0.00025217608,"about_ca_topic_score_gemma":0.0000074000313,"teacher_disagreement_score":0.8726876,"about_ca_system_score_codex":0.000066992914,"about_ca_system_score_gemma":0.00009463333,"threshold_uncertainty_score":0.9955093},"labels":[],"label_agreement":null},{"id":"W4291825485","doi":"10.1177/02655322221114895","title":"Book Review: <i>Multilingual Testing and Assessment</i>","year":2022,"lang":"en","type":"article","venue":"Language Testing","topic":"Multilingual Education and Policy","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":"University of Ottawa","funders":"","keywords":"Psychology; Linguistics; Language assessment; Mathematics education; Philosophy","score_opus":0.0868325680279467,"score_gpt":0.47609491008186594,"score_spread":0.38926234205391924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291825485","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16190241,0.26779482,0.000010129852,0.0065880534,0.00073034613,0.000966389,0.000031888096,0.0008230794,0.5611529],"genre_scores_gemma":[0.5140581,0.003218228,0.0752665,0.31135204,0.004009844,0.00043631988,0.000060764425,0.00014654124,0.091451645],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99863267,0.00031182988,0.00021013244,0.00021992647,0.00032070934,0.0003047446],"domain_scores_gemma":[0.9982999,0.0012037298,0.00013987412,0.0001454923,0.00007968374,0.00013134345],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012205563,0.00009499902,0.00013817368,0.000051218674,0.0012912577,0.0000563676,0.0001815789,0.000021291795,0.0018067601],"category_scores_gemma":[0.0070047043,0.0001043693,0.000024452333,0.00049535785,0.00008317587,0.000101664526,0.00013468,0.00032065052,0.00000910903],"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":[0.000003277423,0.00014722181,0.023396952,0.00038641097,0.000015750687,0.00007779303,0.100123,0.000029659852,0.0019289121,0.00064571225,0.0976748,0.7755705],"study_design_scores_gemma":[0.00020110887,0.000037390502,0.0018462348,0.00018906544,0.000023229974,0.000024807066,0.014967394,0.00064394745,0.000031072508,0.00003702471,0.9817635,0.00023523941],"about_ca_topic_score_codex":0.005841106,"about_ca_topic_score_gemma":0.00007474955,"teacher_disagreement_score":0.8840887,"about_ca_system_score_codex":0.000091185095,"about_ca_system_score_gemma":0.00046352827,"threshold_uncertainty_score":0.99910575},"labels":[],"label_agreement":null},{"id":"W4324373876","doi":"10.1177/02655322231156819","title":"Ukrainian language proficiency test review","year":2023,"lang":"en","type":"article","venue":"Language Testing","topic":"Linguistics, Language Diversity, and Identity","field":"Arts and Humanities","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":"Western University","funders":"","keywords":"Ukrainian; Language proficiency; Psychology; Language assessment; Test (biology); Linguistics; Mathematics education","score_opus":0.06068389481600776,"score_gpt":0.28133156771583895,"score_spread":0.2206476728998312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324373876","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":[0.78690565,0.013335967,0.0000043857685,0.00021295014,0.006860224,0.00071857363,0.00030894205,0.0026745996,0.1889787],"genre_scores_gemma":[0.95189315,0.00018821574,0.00036972127,0.0025050885,0.015915733,0.000024789191,0.00019174945,0.00006282284,0.028848734],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9986379,0.000041728665,0.00027141688,0.0003068622,0.00029571346,0.00044635226],"domain_scores_gemma":[0.9985328,0.00036740588,0.00012890383,0.00034907463,0.00052545016,0.00009639909],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00049945235,0.00018599973,0.00024771751,0.00013543216,0.0004257252,0.00017744755,0.00033633318,0.00003466518,0.0016835298],"category_scores_gemma":[0.038726684,0.0001673343,0.0000906508,0.0002803795,0.00013361324,0.00015042533,0.00018027314,0.0001863292,0.0021087218],"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":[0.000003646528,0.00020680424,0.025220517,0.0037901257,0.00004958835,0.0015782174,0.84257287,0.0000023263597,0.00049618643,0.0017524011,0.10261391,0.021713423],"study_design_scores_gemma":[0.0025616903,0.0006904238,0.017821234,0.012157458,0.0009754196,0.00003381589,0.7358624,0.0027091606,0.0010805957,0.00078503473,0.22080228,0.0045205266],"about_ca_topic_score_codex":0.0018534668,"about_ca_topic_score_gemma":0.0007287238,"teacher_disagreement_score":0.16498749,"about_ca_system_score_codex":0.000032545802,"about_ca_system_score_gemma":0.000037714068,"threshold_uncertainty_score":0.9992291},"labels":[],"label_agreement":null},{"id":"W4375945263","doi":"10.1177/02655322231164565","title":"Book review: Learning-Oriented Language Assessment: Putting Theory into Practice","year":2023,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","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":"Carleton University","funders":"","keywords":"Psychology; Linguistics; Language assessment; Mathematics education; Philosophy","score_opus":0.019022381633885147,"score_gpt":0.40005753558139345,"score_spread":0.3810351539475083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375945263","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051553193,0.2413124,0.0008275859,0.016126383,0.0012845857,0.0019518003,0.000006141919,0.006044856,0.68089306],"genre_scores_gemma":[0.3674266,0.03261786,0.09934947,0.08418486,0.008543271,0.00064058416,0.00058315153,0.0005103832,0.4061438],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970041,0.00096218893,0.00032351783,0.00036723103,0.00075189903,0.00059106416],"domain_scores_gemma":[0.9959097,0.0032442336,0.00030764696,0.00023962246,0.00017126993,0.00012753968],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0048042713,0.00018106427,0.00024749327,0.00009444316,0.0009959888,0.00014685236,0.00035248772,0.000079316975,0.0011448989],"category_scores_gemma":[0.016365716,0.00017749239,0.00008156287,0.0015448191,0.00011369696,0.00058392785,0.00021346073,0.00047489116,0.00046661234],"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":[0.000023457997,0.0002356266,0.03500423,0.0009644448,0.00022621853,0.0014340692,0.39756688,0.00004937011,0.0055034324,0.010286421,0.26342678,0.28527904],"study_design_scores_gemma":[0.0005266538,0.0001001418,0.0035646013,0.0014802852,0.00019283296,0.000009004284,0.26195997,0.000806368,0.000053815933,0.00016316737,0.73059696,0.0005461754],"about_ca_topic_score_codex":0.0011308017,"about_ca_topic_score_gemma":0.000042888387,"teacher_disagreement_score":0.46717018,"about_ca_system_score_codex":0.00014270454,"about_ca_system_score_gemma":0.00015993239,"threshold_uncertainty_score":0.9997682},"labels":[],"label_agreement":null},{"id":"W4381740816","doi":"10.1177/02655322231179128","title":"Rethinking student placement to enhance efficiency and student agency","year":2023,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Carleton University; University of Ottawa","funders":"University of Ottawa","keywords":"Agency (philosophy); Context (archaeology); Psychology; Process (computing); Test (biology); Mathematics education; Language proficiency; Pedagogy; Computer science; Sociology","score_opus":0.0478632348052326,"score_gpt":0.4160427232575863,"score_spread":0.3681794884523537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381740816","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":[0.94971275,0.00021792894,0.00010595553,0.0004611493,0.0003495526,0.00048172873,0.0000013241671,0.0004371943,0.048232384],"genre_scores_gemma":[0.99389774,0.000028631172,0.002103886,0.00026293355,0.00040765005,0.0000448326,0.0000024962098,0.000015715079,0.0032360952],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9979709,0.000112308124,0.0002277678,0.00036147915,0.00081005733,0.00051751395],"domain_scores_gemma":[0.9990919,0.00045106406,0.00007926141,0.000170709,0.000058859332,0.00014820482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001602769,0.00013370036,0.00015397898,0.00011753751,0.0007081409,0.00021468925,0.00036510933,0.000045539004,0.00010700741],"category_scores_gemma":[0.00063152873,0.00013091648,0.000028559472,0.0009903419,0.000059706337,0.00010308915,0.00035580684,0.00013261393,0.00018500326],"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":[0.0000039875254,0.00008559251,0.19629578,0.000019415485,0.00002164129,0.000102335456,0.77647007,0.00007105194,0.0052997563,0.001007949,0.0004322748,0.020190174],"study_design_scores_gemma":[0.00052160694,0.00029734726,0.68828404,0.00033124315,0.00005710832,0.0000018609,0.30677745,0.0002314834,0.0004572754,0.00059230387,0.0016879351,0.00076034863],"about_ca_topic_score_codex":0.0005803019,"about_ca_topic_score_gemma":0.00046971353,"teacher_disagreement_score":0.49198827,"about_ca_system_score_codex":0.00010541179,"about_ca_system_score_gemma":0.00005064946,"threshold_uncertainty_score":0.54465187},"labels":[],"label_agreement":null},{"id":"W4383069305","doi":"10.1177/02655322231179134","title":"Fairness of using different English accents: The effect of shared L1s in listening tasks of the Duolingo English test","year":2023,"lang":"en","type":"article","venue":"Language Testing","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":15,"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":"Active listening; Psychology; Stress (linguistics); Test (biology); Interlanguage; Vocabulary; Dictation; Linguistics; Task (project management); Hindi; Communication","score_opus":0.038221913593031565,"score_gpt":0.34834213137898773,"score_spread":0.31012021778595616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383069305","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":[0.997453,0.0002652556,0.0000035780322,0.000013671238,0.00038689616,0.00037324775,0.000064838096,0.000046143006,0.0013933996],"genre_scores_gemma":[0.9997041,0.0000014493274,0.00003500965,0.000011270645,0.00011885824,0.000025145955,0.000009581993,0.000026034342,0.000068498994],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99833536,0.0004021143,0.00043498527,0.00022198756,0.00023153615,0.00037403472],"domain_scores_gemma":[0.9947923,0.004171662,0.0002871632,0.0005583448,0.00015976484,0.000030755313],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00087863236,0.00014587273,0.00038159342,0.0001429863,0.000069706526,0.000014571658,0.00063343864,0.00011375183,0.00007897416],"category_scores_gemma":[0.009390903,0.000088040375,0.000092710136,0.0010262294,0.00015718456,0.000031723386,0.00038558594,0.00042505757,0.0000018414306],"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":[0.00004835302,0.00007894072,0.82462835,0.00046632875,0.000054428474,0.000024096593,0.0846558,0.00021442375,0.08812476,0.000016810292,0.000035690387,0.0016520035],"study_design_scores_gemma":[0.0013505784,0.00022774783,0.9487026,0.0010343734,0.0000666193,0.000006415669,0.0068448163,0.003722264,0.037846714,0.000045362252,0.000004057939,0.00014847258],"about_ca_topic_score_codex":0.0016116196,"about_ca_topic_score_gemma":0.00014569353,"teacher_disagreement_score":0.124074206,"about_ca_system_score_codex":0.000023916846,"about_ca_system_score_gemma":0.000024399229,"threshold_uncertainty_score":0.9989534},"labels":[],"label_agreement":null},{"id":"W4387429753","doi":"10.1177/02655322231202947","title":"Our validity looks like justice. Does yours?","year":2023,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":27,"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 Lethbridge","funders":"","keywords":"Economic Justice; Oppression; Psychology; Licensure; Set (abstract data type); Social psychology; Mathematics education; Pedagogy; Law; Political science; Computer science","score_opus":0.13450710571791363,"score_gpt":0.4132933080995925,"score_spread":0.2787862023816789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387429753","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":[0.89666235,0.000042534888,0.00002493187,0.00083892414,0.0013660688,0.00015779288,0.000005546059,0.000987027,0.09991485],"genre_scores_gemma":[0.97990924,0.0000090632675,0.0012383129,0.00018962126,0.0016122058,0.000010182652,0.0000083954965,0.000015319325,0.017007655],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99865353,0.00010982661,0.00013187181,0.00020619419,0.00045963709,0.00043895125],"domain_scores_gemma":[0.99924207,0.00037487902,0.00007408189,0.00014682808,0.000066049484,0.0000960645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009659495,0.00009823933,0.00011867457,0.000067729314,0.0006002703,0.00015313464,0.00027854677,0.000071526,0.00011683192],"category_scores_gemma":[0.0013526478,0.00007979859,0.000047180947,0.00061866327,0.000041474017,0.00013664062,0.000107228334,0.0001505593,0.00048063803],"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":[0.000008392523,0.000090939306,0.74093914,0.000106600615,0.000044307424,0.00045663145,0.19791172,0.000022100432,0.005274525,0.0026375633,0.025422718,0.027085343],"study_design_scores_gemma":[0.000614701,0.00006505467,0.22554983,0.0001364411,0.00020208077,0.000002362614,0.7611564,0.0006111523,0.00024903382,0.0013688776,0.009372399,0.0006716757],"about_ca_topic_score_codex":0.002054527,"about_ca_topic_score_gemma":0.0009748512,"teacher_disagreement_score":0.56324464,"about_ca_system_score_codex":0.00004373112,"about_ca_system_score_gemma":0.000070377115,"threshold_uncertainty_score":0.61777896},"labels":[],"label_agreement":null},{"id":"W4399235559","doi":"10.1177/02655322241249754","title":"A scoping review of research on second language test preparation","year":2024,"lang":"en","type":"review","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","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":false,"ca_institutions":"Université de Sherbrooke; Western University","funders":"","keywords":"Psychology; Test (biology); Language assessment; Language proficiency; Linguistics; Mathematics education","score_opus":0.2975427459650408,"score_gpt":0.5064660563792833,"score_spread":0.2089233104142425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399235559","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":[0.000028991473,0.85395956,4.0195044e-7,0.000010983452,0.00018584593,0.00087323465,0.00005461525,0.000259941,0.14462641],"genre_scores_gemma":[0.00011006985,0.9759648,0.00015573898,0.0000969822,0.0017508495,0.00014523664,0.00015094569,0.00011240378,0.021512987],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.997327,0.00058512046,0.0007761786,0.00048179127,0.00045691925,0.00037295112],"domain_scores_gemma":[0.99540204,0.0035181358,0.00038998862,0.0004972785,0.00013466332,0.000057910023],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028574434,0.00033167124,0.00113086,0.0004036841,0.00029797526,0.00024115731,0.000313806,0.00010928198,0.0019237327],"category_scores_gemma":[0.0052365074,0.00024623921,0.00026252933,0.00029877794,0.00012146311,0.000090541515,0.00013374261,0.0015388677,0.0006245426],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.9848657e-7,0.000028895303,3.6201797e-7,0.654337,0.000033543354,0.000084069135,0.020938562,2.0463473e-7,0.0000018835809,0.0009199551,0.0021246772,0.32153022],"study_design_scores_gemma":[0.000026123833,0.00011904959,3.3451965e-8,0.7317721,0.00020256155,0.000018313436,0.0015421575,0.000009102262,0.0000014028079,0.000007601841,0.26611152,0.00018999744],"about_ca_topic_score_codex":0.0002095975,"about_ca_topic_score_gemma":0.00025654762,"teacher_disagreement_score":0.32134023,"about_ca_system_score_codex":0.00008695065,"about_ca_system_score_gemma":0.00027209317,"threshold_uncertainty_score":0.999999},"labels":[],"label_agreement":null},{"id":"W4404521715","doi":"10.1177/02655322241291764","title":"Review of the Canadian English Language Proficiency Index Program (CELPIP)","year":2024,"lang":"en","type":"article","venue":"Language Testing","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":3,"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":"Psychology; Language proficiency; Index (typography); Language assessment; Linguistics; Mathematics education; Computer science; Philosophy","score_opus":0.06094631709999317,"score_gpt":0.45701666441974953,"score_spread":0.3960703473197564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404521715","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21107273,0.06271833,0.0000013861846,0.0028940616,0.0014022886,0.0012854872,0.000024722323,0.00056519,0.7200358],"genre_scores_gemma":[0.9939931,0.0000995364,0.00036420624,0.001491181,0.0006807329,0.000034485594,0.0000043968657,0.000012382927,0.0033199817],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990414,0.000130754,0.0001757909,0.00014095573,0.00022454864,0.00028656496],"domain_scores_gemma":[0.999315,0.00017398207,0.000056885143,0.00019587124,0.00012459056,0.00013363516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080190995,0.00007301444,0.000094606796,0.00006603318,0.00029047253,0.00009248687,0.00029930146,0.000052463976,0.00036934932],"category_scores_gemma":[0.006670138,0.000053010226,0.000055435004,0.0010212993,0.0001315451,0.00006578924,0.000026849724,0.00019383743,0.000021295578],"study_design_candidate":"not_applicable","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":[3.003819e-7,0.00003652089,0.0064641503,0.002309049,0.000007950159,0.000012979972,0.46240622,0.000001014016,0.00009973927,0.004638097,0.00342061,0.52060336],"study_design_scores_gemma":[0.00015400899,0.00004967563,0.009794569,0.019485211,0.000080432204,0.0000095223195,0.11073383,0.00092947757,0.00046575672,0.00013357114,0.8576055,0.0005584374],"about_ca_topic_score_codex":0.52345,"about_ca_topic_score_gemma":0.36173874,"teacher_disagreement_score":0.8541849,"about_ca_system_score_codex":0.000120184595,"about_ca_system_score_gemma":0.0017199581,"threshold_uncertainty_score":0.798526},"labels":[],"label_agreement":null},{"id":"W4407931412","doi":"10.1177/02655322251319284","title":"The relationship between English language proficiency test scores and academic achievement: A longitudinal study of two tests","year":2025,"lang":"en","type":"article","venue":"Language Testing","topic":"Higher Education Learning Practices","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"","keywords":"Psychology; Language proficiency; Test (biology); Language assessment; Achievement test; Academic achievement; Mathematics education; English language; Test of English as a Foreign Language; Standardized test","score_opus":0.10730362990051857,"score_gpt":0.4529902981757598,"score_spread":0.34568666827524125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407931412","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":[0.9916908,0.0009025748,0.000014661727,0.00065209303,0.00012634494,0.00046821893,0.0000024418457,0.00014238946,0.0060004396],"genre_scores_gemma":[0.9974722,0.0000025973527,0.0005632708,0.0000238835,0.00027981692,0.000035366746,0.000001987813,0.000009082518,0.0016117931],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99836236,0.0004655701,0.00031538756,0.00024521234,0.00034030346,0.0002711549],"domain_scores_gemma":[0.98080057,0.01849031,0.0002943639,0.00021782682,0.00013876722,0.00005815417],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002328164,0.00010255638,0.00013200458,0.00009088909,0.0011646992,0.00013451446,0.00034725605,0.000056160745,0.000008894818],"category_scores_gemma":[0.05939497,0.00008349853,0.000016361224,0.0010561035,0.00022976453,0.000265949,0.000106387706,0.00048530946,0.0000044706976],"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":[0.0000015808985,0.00006401684,0.81982464,0.000015452753,0.000008235719,0.0000018332935,0.17570895,0.0000033365022,0.000097135155,0.0015942171,0.000018835683,0.0026617814],"study_design_scores_gemma":[0.00022387262,0.000057926984,0.8783645,0.000086951964,0.000047881887,2.5859586e-7,0.12084174,0.0000060660805,0.000021200156,0.00017450278,0.00010209888,0.00007299994],"about_ca_topic_score_codex":0.0046843155,"about_ca_topic_score_gemma":0.0019467989,"teacher_disagreement_score":0.058539867,"about_ca_system_score_codex":0.000050316397,"about_ca_system_score_gemma":0.00019584261,"threshold_uncertainty_score":0.9485282},"labels":[],"label_agreement":null},{"id":"W4412676320","doi":"10.1177/02655322251359320","title":"Book review: Innovation in Learning-Oriented Language Assessment ChongS.ReindersH. (Eds.), Innovation in Learning-Oriented Language Assessment. Palgrave MacMillan, 2023. 333 pp. ISBN 978-3-031-18949-4 (hbk) US$169.99 ISBN 978-3-031-18952-4 (sbk) US$169.99 ISBN 978-3-031-18950-0 (ebk) US$129.99","year":2025,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","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":"University of Saskatchewan","funders":"","keywords":"Psychology; Linguistics; Sociology; Philosophy","score_opus":0.01741045735498279,"score_gpt":0.3375408814479155,"score_spread":0.3201304240929327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412676320","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":[0.75942755,0.09312202,0.0021636742,0.006341017,0.0031513004,0.008493182,0.00017245693,0.0028348654,0.12429394],"genre_scores_gemma":[0.9216686,0.013450223,0.009134124,0.011433268,0.002136762,0.0013032486,0.0050940053,0.0005349128,0.035244875],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9835112,0.0026757766,0.004356312,0.0028642542,0.00338429,0.0032081516],"domain_scores_gemma":[0.99159396,0.0016749776,0.003065192,0.0015795608,0.0016819931,0.00040433253],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0079984935,0.001879939,0.002420376,0.0023528943,0.0016956516,0.000857047,0.0018746025,0.0011398356,0.0029819317],"category_scores_gemma":[0.00837872,0.0020229935,0.000453341,0.019530984,0.0006879977,0.0010191818,0.0012060003,0.004428082,0.00024966843],"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":[0.00026296757,0.0011216992,0.8396774,0.0020890946,0.00065975875,0.0016585835,0.030674106,0.0007213392,0.019346053,0.009898183,0.05337339,0.04051743],"study_design_scores_gemma":[0.019724227,0.001885326,0.44323745,0.017004244,0.0012561472,0.00009305384,0.18195847,0.017454697,0.0020459483,0.0006542268,0.3059624,0.008723797],"about_ca_topic_score_codex":0.018995095,"about_ca_topic_score_gemma":0.0045508286,"teacher_disagreement_score":0.39643994,"about_ca_system_score_codex":0.0025953478,"about_ca_system_score_gemma":0.0019041235,"threshold_uncertainty_score":0.99997413},"labels":[],"label_agreement":null},{"id":"W4412969591","doi":"10.1177/02655322251348956","title":"Investigating construct representativeness and linguistic equity of automated oral reading fluency assessment with prosody","year":2025,"lang":"en","type":"article","venue":"Language Testing","topic":"Reading and Literacy Development","field":"Psychology","cited_by":3,"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","funders":"Iran Science Elites Federation; University of Toronto","keywords":"Prosody; Fluency; Psychology; Ell; Natural language processing; Linguistics; Reading comprehension; Reading (process); Cognitive psychology; Computer science; Artificial intelligence; Mathematics education; Speech recognition; Teaching method; Vocabulary development","score_opus":0.03767559474110727,"score_gpt":0.4197115117810315,"score_spread":0.38203591703992423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412969591","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":[0.93381757,0.00014510937,0.0005653152,0.000022805958,0.00015792043,0.00024575475,0.000006272701,0.00034786243,0.06469138],"genre_scores_gemma":[0.9152763,2.566853e-7,0.08413101,0.00006670257,0.00002402311,0.000033459888,0.0000121107605,0.00001417085,0.0004419631],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986468,0.00016792995,0.0003940305,0.0003623433,0.0001525348,0.00027639297],"domain_scores_gemma":[0.99853504,0.00077053567,0.0002423141,0.00024674006,0.000143951,0.00006141149],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059053407,0.00015959716,0.00028929833,0.00013092569,0.00013398465,0.000057391022,0.00012245677,0.000051549752,0.000027960083],"category_scores_gemma":[0.0014648152,0.00013450977,0.000015761449,0.0005225188,0.00017237545,0.000055184475,0.00013348085,0.00018810717,0.0000015141765],"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":[0.000014900881,0.000047360052,0.91697204,0.0003527353,0.00012078631,0.00012218412,0.023691578,0.000028536,0.018966602,0.006431818,0.00004191571,0.033209525],"study_design_scores_gemma":[0.001836812,0.00019436279,0.9677733,0.0032991567,0.00012915464,0.0001636559,0.010265796,0.008894078,0.00549959,0.0014608377,0.00003580002,0.00044742448],"about_ca_topic_score_codex":0.001128564,"about_ca_topic_score_gemma":0.000010270265,"teacher_disagreement_score":0.08356569,"about_ca_system_score_codex":0.000060488037,"about_ca_system_score_gemma":0.00015468845,"threshold_uncertainty_score":0.5485149},"labels":[],"label_agreement":null},{"id":"W4414209357","doi":"10.1177/02655322251348685","title":"Advancing language assessment for teaching and learning in the era of the artificial intelligence (AI) revolution: Promises and challenges","year":2025,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Japan Society for the Promotion of Science; Waseda University","keywords":"Language assessment; Language proficiency; Language acquisition; Applications of artificial intelligence; Assessment for learning; Teaching method","score_opus":0.036526360261197204,"score_gpt":0.3059178929668351,"score_spread":0.26939153270563787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414209357","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":[0.9741301,0.0103039425,0.00063193275,0.002710881,0.000111760826,0.00034086802,0.0000030981973,0.00006943182,0.011698],"genre_scores_gemma":[0.99612343,0.000015653119,0.0029176006,0.00037523915,0.00019803103,0.00003035032,0.0000023781981,0.000010397818,0.00032692053],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9989185,0.0003702898,0.00023068914,0.00019237358,0.000096475735,0.00019168474],"domain_scores_gemma":[0.99786973,0.0018280239,0.0001155477,0.00014415431,0.0000288906,0.000013680801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017576342,0.00011180673,0.0001548855,0.0000586237,0.00074755435,0.00011593137,0.00013965038,0.00002938337,0.000016633365],"category_scores_gemma":[0.0026001295,0.00007082817,0.000032284992,0.000050189556,0.00012591481,0.000112208356,0.00007478649,0.0008792472,1.6607464e-7],"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":[0.000005948374,0.000025954925,0.0013919318,0.00029632312,0.000011765573,0.00000435305,0.3203359,0.000094814444,0.00078802556,0.05944712,0.000008399749,0.6175895],"study_design_scores_gemma":[0.00020258837,0.00011510302,0.005608365,0.0013097434,0.00005652868,0.000016322276,0.9757233,0.012622981,0.00021184298,0.0019147466,0.002014853,0.00020361622],"about_ca_topic_score_codex":0.0014297655,"about_ca_topic_score_gemma":0.0021149123,"teacher_disagreement_score":0.6553874,"about_ca_system_score_codex":0.00001988695,"about_ca_system_score_gemma":0.000031220396,"threshold_uncertainty_score":0.57496595},"labels":[],"label_agreement":null},{"id":"W7117366349","doi":"10.1177/02655322251406223","title":"Book review: Comprehensibility in language assessment: A broader perspective TavakoliP.CookeS.Comprehensibility in Language Assessment: A Broader Perspective. University of Toronto Press, 2024. 224 pp. ISBN 978 1 80050 434 9 (ePDF), 978 1 80050 433 2 (paperback), 978 1 80050 432 5 (hardback), £23.06 (Kindle), £24.27 (Paperback), £66.03 (Hardcover)","year":2025,"lang":"en","type":"article","venue":"Language Testing","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Second language; On Language; Language assessment; Language proficiency","score_opus":0.025777876961311307,"score_gpt":0.36001450487924097,"score_spread":0.3342366279179297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117366349","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21345638,0.4747777,0.00011100882,0.0026613125,0.0018701779,0.004935317,0.0009796633,0.00062199775,0.30058643],"genre_scores_gemma":[0.740278,0.031635012,0.033070806,0.027469274,0.0022205354,0.000793791,0.0023374753,0.0007036518,0.16149142],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9884877,0.0027453136,0.0020812005,0.003444473,0.0013021277,0.0019391751],"domain_scores_gemma":[0.9921941,0.002591727,0.001101828,0.002736736,0.00087905105,0.0004965648],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0020258795,0.0014769376,0.0024204564,0.0002197978,0.0004166175,0.00017947063,0.0018031842,0.0008415765,0.018651113],"category_scores_gemma":[0.0011273103,0.0015119103,0.0007450413,0.001560422,0.00070851535,0.0010761518,0.00086764834,0.0023619602,0.00025637556],"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":[0.0013402689,0.01685186,0.3356371,0.0048902533,0.002136253,0.001967515,0.083375975,0.00022526848,0.01642377,0.009006599,0.52061707,0.007528058],"study_design_scores_gemma":[0.008537662,0.00063804566,0.76151586,0.0043898765,0.0006437171,0.00010584428,0.14502914,0.00053389405,0.000119321965,0.00088770996,0.075114064,0.00248488],"about_ca_topic_score_codex":0.06555572,"about_ca_topic_score_gemma":0.015410045,"teacher_disagreement_score":0.5268217,"about_ca_system_score_codex":0.0036447565,"about_ca_system_score_gemma":0.0009353808,"threshold_uncertainty_score":0.9999396},"labels":[],"label_agreement":null}]}