{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":22,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":22,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"8eedc4ff3541","filters":{"venue":"Language Assessment Quarterly"}},"results":[{"id":"W2096160735","doi":"10.1080/15434300701375832","title":"Three Generations of DIF Analyses: Considering Where It Has Been, Where It Is Now, and Where It Is Going","year":2007,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":386,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Differential item functioning; Contrast (vision); Psychology; Cognitive psychology; Item response theory; Econometrics; Computer science; Psychometrics; Artificial intelligence; Mathematics; Developmental psychology","authors":[{"name":"Bruno D. Zumbo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08492024923436474,"gpt":0.4363221750131228,"spread":0.351401925778758,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1041699,0.001791943,0.001939708,0.01927868,0.004767225,0.01213836,0.002440873,0.00215729,0.003266453],"category_scores_gemma":[0.2220772,0.001162728,0.001593553,0.01179421,0.01537552,0.0139856,0.01085634,0.007929076,0.0006842125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005226667,"about_ca_system_score_gemma":0.004919982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005083711,"about_ca_topic_score_gemma":0.0061287,"domain_scores_codex":[0.917119,0.05767624,0.006607662,0.004064245,0.01331299,0.001219902],"domain_scores_gemma":[0.741699,0.2046002,0.0119559,0.01647621,0.02223352,0.003035182],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001838492,0.0001204594,0.0823416,0.00127193,0.0002630008,0.0003471134,0.05132769,0.0006732952,0.0009597238,0.3719549,0.01000366,0.4805528],"study_design_scores_gemma":[0.00004422999,0.000357651,0.05490009,0.003329027,0.0002413032,0.002001452,0.05268281,0.006659271,0.001163268,0.7976819,0.08053613,0.0004028425],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.1483581,0.06134102,0.6552822,0.05771285,0.003394233,0.002176081,0.0009970332,0.00113332,0.06960519],"genre_scores_gemma":[0.601673,0.01622359,0.3663352,0.007305851,0.001443408,0.002352667,0.0007570048,0.0003276632,0.003581648],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.8958301,"threshold_uncertainty_score":0.5509098,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112485328","doi":"10.1080/15434303.2015.1010726","title":"Teachers’ Grading Decision Making: Multiple Influencing Factors and Methods","year":2015,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":138,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); Psychology; Mathematics education; English language; Multivariate analysis of variance; Statistics; Engineering; Mathematics","authors":[{"name":"Liying Cheng","is_ca":true},{"name":"Youyi Sun","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04392888403571169,"gpt":0.4426289617588582,"spread":0.3987000777231465,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01689852,0.0009483484,0.0008301566,0.003332958,0.001701881,0.003961886,0.0009623157,0.0004951389,0.002809022],"category_scores_gemma":[0.04934454,0.0005961421,0.001144686,0.002893308,0.001163524,0.001162322,0.001340243,0.0007221554,0.0002582053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002369377,"about_ca_system_score_gemma":0.004415166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01248928,"about_ca_topic_score_gemma":0.01599806,"domain_scores_codex":[0.9792632,0.008851162,0.00219875,0.002247133,0.006202952,0.001236692],"domain_scores_gemma":[0.9174977,0.05241028,0.0152197,0.003204464,0.008862635,0.002805194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001997072,0.0002141826,0.9457048,0.0001680297,0.0002129289,0.0002285701,0.01221618,0.0004780262,0.0007314763,0.000487487,0.0003178524,0.03904076],"study_design_scores_gemma":[0.00003721968,0.0002177043,0.9736769,0.0001558359,0.0003459095,0.0002730929,0.01167925,0.008557175,0.001382355,0.001270156,0.002310841,0.00009368276],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9835622,0.0004202673,0.009157084,0.0002548019,0.0000371652,0.000571558,0.0001365279,0.00007498518,0.005785475],"genre_scores_gemma":[0.9944124,0.00008485719,0.004606484,0.00002219572,0.00001150846,0.0001374426,0.00006755045,0.00001428714,0.0006432816],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01689852,"threshold_uncertainty_score":0.089369,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2975930148","doi":"10.1080/15434303.2019.1671392","title":"Incorporating Translanguaging in Language Assessment: The Case of a Test for University Professors","year":2019,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Ottawa","funders":"","keywords":"Translanguaging; Operationalization; Active listening; Test (biology); Psychology; Task (project management); Competence (human resources); Mathematics education; Pedagogy; Computer science; Social psychology","authors":[{"name":"Beverly Baker","is_ca":true},{"name":"Amelia Hope","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01280746938865259,"gpt":0.2800899580955242,"spread":0.2672824887068716,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04853543,0.001084704,0.0008183272,0.00181296,0.006970806,0.00757589,0.003401704,0.003385118,0.001890314],"category_scores_gemma":[0.0932605,0.0007631566,0.0006507157,0.001411231,0.005577439,0.004097545,0.007174117,0.004080228,0.001221319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006768251,"about_ca_system_score_gemma":0.01373809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03368212,"about_ca_topic_score_gemma":0.09645731,"domain_scores_codex":[0.9325162,0.05079912,0.002441832,0.002132076,0.008638538,0.003472261],"domain_scores_gemma":[0.9257531,0.04373267,0.002871875,0.00539998,0.01567625,0.006566146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006223324,0.001709831,0.04733107,0.0008749393,0.00006717374,0.01626385,0.402647,0.004127084,0.03320277,0.009034125,0.00516914,0.4789506],"study_design_scores_gemma":[0.0003949609,0.007366755,0.06418993,0.001535794,0.0002683249,0.02701412,0.3644589,0.0268166,0.1180857,0.01537208,0.3733196,0.001177238],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8727782,0.0007789026,0.08489715,0.007754609,0.0003416549,0.001270631,0.00007927167,0.001017738,0.03108184],"genre_scores_gemma":[0.8081688,0.0003823613,0.1790459,0.001451426,0.00008832728,0.0003998234,0.00008731456,0.0003211962,0.01005491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04853543,"threshold_uncertainty_score":0.2566829,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389294437","doi":"10.1080/15434303.2023.2288253","title":"Validity Arguments for Automated Essay Scoring of Young Students’ Writing Traits","year":2023,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Writing assessment; Consistency (knowledge bases); Context (archaeology); Vocabulary; Psychology; Inference; Argument (complex analysis); Formative assessment; Trait; Artificial intelligence; Natural language processing; Computer science; Mathematics education; Linguistics","authors":[{"name":"Liam Hannah","is_ca":true},{"name":"Eunice Eunhee Jang","is_ca":true},{"name":"Maitree Shah","is_ca":true},{"name":"Vaibhav Gupta","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0296680655231284,"gpt":0.359881211422216,"spread":0.3302131458990876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2394291,0.001394173,0.00154497,0.005948508,0.003165643,0.008760588,0.004888351,0.003590815,0.00286906],"category_scores_gemma":[0.679516,0.001080217,0.002295502,0.00358941,0.01344043,0.009080148,0.007059562,0.004919419,0.0009716409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00489859,"about_ca_system_score_gemma":0.004150737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004871405,"about_ca_topic_score_gemma":0.002731176,"domain_scores_codex":[0.7255397,0.200425,0.01324781,0.02016597,0.03779344,0.002828021],"domain_scores_gemma":[0.1397443,0.7501418,0.02765603,0.04884825,0.03226558,0.001343967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004930359,0.001313598,0.5719006,0.0009624443,0.00182869,0.0005078285,0.01339225,0.02890253,0.003111244,0.1539545,0.00586557,0.2133304],"study_design_scores_gemma":[0.0008671816,0.002453372,0.2207034,0.001611138,0.0006872055,0.0007309751,0.005711642,0.4239153,0.01574371,0.3160672,0.01114306,0.0003658762],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5678994,0.002271663,0.361417,0.01914079,0.0007077638,0.001817696,0.001172129,0.0008032663,0.04477027],"genre_scores_gemma":[0.9499434,0.000104779,0.04696103,0.0007895456,0.0002151254,0.0006306105,0.000387895,0.0000935221,0.0008741515],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2394291,"threshold_uncertainty_score":0.9379193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2015223621","doi":"10.1080/15434303.2014.981334","title":"Interpreting the Impact of the Ontario Secondary School Literacy Test on Second Language Students Within an Argument-Based Validation Framework","year":2015,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Queen's University","funders":"","keywords":"Argument (complex analysis); Literacy; Context (archaeology); Mathematics education; Test (biology); Curriculum; Reading (process); Ell; Language proficiency; Empirical research; Psychology; Pedagogy; Language assessment; Linguistics; Teaching method; Mathematics","authors":[{"name":"Liying Cheng","is_ca":true},{"name":"Youyi Sun","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01646036534847547,"gpt":0.3890332495887422,"spread":0.3725728842402667,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1783687,0.0008130009,0.001010267,0.006722518,0.00523628,0.009038216,0.004826706,0.002168444,0.002485752],"category_scores_gemma":[0.5317957,0.0006734873,0.001641216,0.006111457,0.01809934,0.004133444,0.008799448,0.002775795,0.000191719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.04590621,"about_ca_system_score_gemma":0.04270188,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.4577401,"about_ca_topic_score_gemma":0.4440976,"domain_scores_codex":[0.8053914,0.131009,0.007624681,0.004572826,0.04813973,0.003262399],"domain_scores_gemma":[0.3516014,0.5002401,0.06280159,0.01280341,0.07066703,0.001886627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001097542,0.0003335537,0.6406736,0.002815852,0.0009401556,0.0008947505,0.1903153,0.002683178,0.0007447829,0.0645788,0.006554093,0.08836835],"study_design_scores_gemma":[0.0003664152,0.0009282005,0.7094768,0.0114942,0.001389317,0.0001902798,0.1912088,0.01114879,0.004854373,0.03023581,0.0384125,0.0002943715],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8734542,0.006931508,0.01446214,0.0334613,0.0005854814,0.0012063,0.001570117,0.00006345061,0.06826553],"genre_scores_gemma":[0.992042,0.0004945359,0.004812666,0.000926743,0.00004284059,0.0005099642,0.0002940349,0.00001919496,0.0008579599],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5422599,"threshold_uncertainty_score":0.9433153,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3209416046","doi":"10.1080/15434303.2021.1992629","title":"The Relationship between Word Difficulty and Frequency: A Response to Hashimoto (2021)","year":2021,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Word lists by frequency; Correlation; Vocabulary; Rank (graph theory); Word (group theory); Linguistics; Psychology; Range (aeronautics); Mathematics; Statistics; Sentence; Philosophy","authors":[{"name":"Jeffrey Stewart","is_ca":false},{"name":"Joseph P. Vitta","is_ca":false},{"name":"Christopher Nicklin","is_ca":false},{"name":"Stuart McLean","is_ca":false},{"name":"Geoffrey G. Pinchbeck","is_ca":true},{"name":"Brandon Kramer","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01621099591469831,"gpt":0.3205802786497973,"spread":0.304369282735099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01150953,0.0006895202,0.0005166484,0.001049753,0.002629448,0.001602353,0.0009629316,0.007035044,0.005616477],"category_scores_gemma":[0.08191672,0.000452251,0.0006699364,0.0007401052,0.001892738,0.002722168,0.002517843,0.00870917,0.002428496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002401458,"about_ca_system_score_gemma":0.001448933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004864427,"about_ca_topic_score_gemma":0.005692496,"domain_scores_codex":[0.9949883,0.001939895,0.0007243869,0.0007211984,0.001413827,0.0002123945],"domain_scores_gemma":[0.9269078,0.05599312,0.00216267,0.00145889,0.01177169,0.00170585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001183139,0.0005507195,0.07132431,0.0008161707,0.0001333145,0.00290801,0.03837986,0.00103074,0.01375931,0.03185965,0.6264687,0.2115863],"study_design_scores_gemma":[0.0002063546,0.002115818,0.1098154,0.001199917,0.0001832838,0.00880321,0.04938745,0.005274378,0.0116255,0.04394077,0.7667146,0.0007333368],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.1167834,0.005152242,0.0164113,0.8313345,0.01488416,0.0002784691,0.0006488194,0.000250302,0.01425675],"genre_scores_gemma":[0.4585101,0.003797163,0.01258812,0.492303,0.009501652,0.0005226714,0.0004115453,0.0002327874,0.02213305],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.01150953,"threshold_uncertainty_score":0.06086892,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2002561419","doi":"10.1080/15434303.2014.936603","title":"Using Lexical Profiling Tools to Investigate Children’s Written Vocabulary in Grade 3: An Exploratory Study","year":2015,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Calgary","funders":"","keywords":"Vocabulary; Rubric; Lexical diversity; Salient; Psychology; Computer science; Linguistics; Profiling (computer programming); Exploratory research; Vocabulary development; Natural language processing; Lexical density; Trait; Artificial intelligence; Mathematics education; Lexical item; Sociology","authors":[{"name":"Hetty Roessingh","is_ca":true},{"name":"Susan Elgie","is_ca":true},{"name":"Pat Kover","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1277240996145899,"gpt":0.430229454825071,"spread":0.3025053552104811,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002850315,0.0007036569,0.0008918109,0.002811108,0.001272065,0.002369019,0.0007815477,0.0007717659,0.0009342774],"category_scores_gemma":[0.007339039,0.0004934218,0.0006881803,0.001456923,0.0009905923,0.001120888,0.001743506,0.0009924689,0.0005055233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008771924,"about_ca_system_score_gemma":0.001079227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01331392,"about_ca_topic_score_gemma":0.02763288,"domain_scores_codex":[0.9982528,0.0003965021,0.000264854,0.0002717743,0.0004599855,0.0003540693],"domain_scores_gemma":[0.995279,0.001518429,0.001186627,0.0003573123,0.001179117,0.0004796107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001436547,0.0008237435,0.8325698,0.0001270803,0.00003999272,0.001497062,0.1294196,0.0001112468,0.008976339,0.0001639265,0.0001761132,0.02595139],"study_design_scores_gemma":[0.000008310734,0.0009486577,0.9523659,0.0000432082,0.00002849524,0.0008380734,0.0422304,0.000144015,0.002025608,0.00008787864,0.001257081,0.00002238704],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9995182,0.00002386856,0.00007612131,0.000005214041,7.02961e-7,0.00002028983,0.00004481736,0.000003337695,0.0003075753],"genre_scores_gemma":[0.9985531,0.00007456695,0.0006464273,0.00001641259,0.000001543682,0.00009305344,0.0001154383,0.000005291793,0.0004942061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01331392,"threshold_uncertainty_score":0.02647287,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2028824355","doi":"10.1080/15434300801934751","title":"Comments on “Evaluation of the Usefulness of the<i>Versant for English</i>Test: A Response”: The Author Responds","year":2008,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Institute for Christian Studies","funders":"","keywords":"Test (biology); Psychology; English language; Language assessment; Mathematics education; Linguistics; Computer science; Cognitive psychology","authors":[{"name":"Christian W. Chun","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0786983967731293,"gpt":0.3273672114131697,"spread":0.2486688146400404,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007785209,0.0007931348,0.0007018366,0.0008130772,0.003767208,0.002068208,0.002001436,0.01730015,0.0220489],"category_scores_gemma":[0.06828541,0.000516494,0.001025759,0.0005715948,0.001803197,0.001776213,0.002229784,0.01137853,0.0104588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00392913,"about_ca_system_score_gemma":0.004885445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01421702,"about_ca_topic_score_gemma":0.0174463,"domain_scores_codex":[0.9934301,0.001787563,0.0008969206,0.0005631503,0.002703737,0.0006185037],"domain_scores_gemma":[0.9502862,0.02403782,0.001985782,0.0006646313,0.02074259,0.002283022],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006607659,0.00002201164,0.0007469557,0.0000810778,0.000007650087,0.0002840449,0.0008409622,0.00007568295,0.0005888028,0.0004435115,0.9921175,0.004725642],"study_design_scores_gemma":[0.0000497866,0.0002185223,0.005076589,0.000373127,0.00004827512,0.0005352452,0.006613724,0.0003863351,0.002398401,0.0008301411,0.983313,0.0001568986],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.005004733,0.0005747456,0.00133595,0.9361749,0.04337118,0.0002595985,0.0006235459,0.0006279194,0.01202753],"genre_scores_gemma":[0.01884953,0.0004992539,0.00133704,0.9294025,0.008572477,0.0003251793,0.0002694968,0.0002871124,0.04045741],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.0220489,"threshold_uncertainty_score":0.07376087,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2955380721","doi":"10.1080/15434303.2019.1628238","title":"“Be a Machine”: International Graduate Students’ Narratives around High-Stakes English Tests","year":2019,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"","keywords":"Test of English as a Foreign Language; Narrative; Test (biology); Agency (philosophy); Language proficiency; Mathematics education; Language assessment; Psychology; Pedagogy; Study abroad; Medical education; Sociology; Linguistics; Social science","authors":[{"name":"Jeanne Sinclair","is_ca":false},{"name":"Elizabeth Larson","is_ca":true},{"name":"Shakina Rajendram","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02159823643195352,"gpt":0.2981795875042351,"spread":0.2765813510722815,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0137053,0.001835674,0.001181007,0.002439241,0.02712742,0.02381902,0.003879211,0.005530028,0.003261979],"category_scores_gemma":[0.0248186,0.001106175,0.000763237,0.002255472,0.03667172,0.01124142,0.01808511,0.01749676,0.000847611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01615055,"about_ca_system_score_gemma":0.008569967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06362532,"about_ca_topic_score_gemma":0.09987503,"domain_scores_codex":[0.9854171,0.008440397,0.0003895883,0.0008882053,0.001944113,0.00292072],"domain_scores_gemma":[0.9789456,0.01025006,0.00219187,0.0007295132,0.001842752,0.006040277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001187035,0.00001285779,0.001080786,0.00001036502,0.000001837125,0.0002114984,0.9960796,0.00001042103,0.00009896464,0.001221692,0.0005824551,0.0006776854],"study_design_scores_gemma":[0.000001192976,0.00001278289,0.000471285,0.00002769422,0.000002087888,0.00007472221,0.9941195,0.00001663512,0.00006947792,0.0001438078,0.005047378,0.00001337469],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9660091,0.001023493,0.001029338,0.01311201,0.0002807931,0.00006699381,0.0001308449,0.00004025957,0.01830716],"genre_scores_gemma":[0.9912702,0.0008435202,0.0002723977,0.00169959,0.00007235037,0.00004123701,0.00006957157,0.00007118148,0.005659981],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06362532,"threshold_uncertainty_score":0.12651,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220982091","doi":"10.1080/15434303.2022.2038172","title":"Investigating the Effects of Task Type and Linguistic Background on Accuracy in Automated Speech Recognition Systems: Implications for Use in Language Assessment of Young Learners","year":2022,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Christian Studies; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Task (project management); Computer science; Natural language processing; Artificial intelligence; Meaning (existential); Task analysis; Language proficiency; Test (biology); Psychology; Speech recognition","authors":[{"name":"Liam Hannah","is_ca":true},{"name":"Hyun-Ah Kim","is_ca":true},{"name":"Eunice Eunhee Jang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03373161378752211,"gpt":0.3391697548696433,"spread":0.3054381410821213,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0276012,0.0005707684,0.0006161383,0.0008754489,0.0005279558,0.002089377,0.0006898741,0.0005519352,0.001320998],"category_scores_gemma":[0.1251388,0.0003379596,0.0005875561,0.0006994721,0.0008229289,0.001895223,0.001277196,0.000683877,0.0004997022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005326518,"about_ca_system_score_gemma":0.0007736636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002245166,"about_ca_topic_score_gemma":0.003831139,"domain_scores_codex":[0.9804509,0.01182758,0.001429139,0.001850513,0.003993077,0.0004488006],"domain_scores_gemma":[0.7141353,0.2442859,0.01904168,0.00793962,0.01100274,0.003594718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002799876,0.001215494,0.9232199,0.0001295387,0.0002738255,0.0001204004,0.004019212,0.001097117,0.01186227,0.0001894528,0.0001485276,0.05492426],"study_design_scores_gemma":[0.00002893162,0.003095093,0.9895056,0.00002535039,0.00005838739,0.00008529557,0.001024094,0.001676191,0.004172727,0.0001572137,0.0001474342,0.0000236309],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975151,0.00009934288,0.00154056,0.00004908243,0.000007638987,0.00003830981,0.00002942575,0.00001274445,0.0007077893],"genre_scores_gemma":[0.996762,0.00006673537,0.002521081,0.00005072579,0.00001429689,0.00006319594,0.00007304451,0.00001640098,0.0004325242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0276012,"threshold_uncertainty_score":0.1459708,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4290958425","doi":"10.1080/15434303.2022.2073886","title":"Developing a Scenario-Based English Language Assessment in an Asian University","year":2022,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Language assessment; Linguistics; Language proficiency; Psychology; Mathematics education; Sociology; Computer science","authors":[{"name":"Antony John Kunnan","is_ca":false},{"name":"Coral Yiwei Qin","is_ca":true},{"name":"Cecilia Guanfang Zhao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01712562869737202,"gpt":0.2795077938743099,"spread":0.2623821651769379,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008776259,0.0007051748,0.0003047969,0.0008761144,0.002114645,0.003702386,0.001946215,0.001386028,0.002719635],"category_scores_gemma":[0.0125861,0.0004562959,0.0004948117,0.0005220273,0.001191946,0.003479391,0.003036566,0.001426995,0.0006677856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003035573,"about_ca_system_score_gemma":0.005583114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003319,"about_ca_topic_score_gemma":0.008437269,"domain_scores_codex":[0.9928288,0.005554812,0.0003157376,0.0002988654,0.0005905689,0.0004112198],"domain_scores_gemma":[0.992303,0.002902016,0.000468829,0.0004499121,0.002093159,0.001783057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0009217536,0.02187661,0.1026526,0.0009320241,0.0001818091,0.01087938,0.2411086,0.09661947,0.04734749,0.05089191,0.02132377,0.4052646],"study_design_scores_gemma":[0.0005159819,0.01243172,0.05518021,0.001197118,0.0001660292,0.005988545,0.3904881,0.2635636,0.05645583,0.03027283,0.1827128,0.001027317],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8692669,0.00007200305,0.09608491,0.001870965,0.00009420318,0.00344583,0.0001961708,0.0005951173,0.02837387],"genre_scores_gemma":[0.8168699,0.000127254,0.177422,0.0001718322,0.00001388182,0.001024783,0.0002472946,0.00004176223,0.004081364],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008776259,"threshold_uncertainty_score":0.04641384,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396694688","doi":"10.1080/15434303.2024.2346089","title":"The Academic Achievement of Undergraduate Students with Different English Language Proficiency Profiles","year":2024,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"York University","funders":"York University","keywords":"Language proficiency; Mathematics education; Academic achievement; Psychology; Language assessment","authors":[{"name":"Khaled Barkaoui","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009969094360222603,"gpt":0.2888573473264172,"spread":0.2788882529661946,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00109055,0.0002716393,0.0004123853,0.002185665,0.0008759095,0.001517637,0.0004501005,0.0003259712,0.0019784],"category_scores_gemma":[0.005593992,0.0001325531,0.0003185017,0.001251645,0.0006905171,0.000470024,0.001307877,0.0005422633,0.000625052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001102617,"about_ca_system_score_gemma":0.001103603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03020758,"about_ca_topic_score_gemma":0.04860394,"domain_scores_codex":[0.9989478,0.0001333078,0.0001057371,0.0001227873,0.0003359756,0.0003544677],"domain_scores_gemma":[0.9974873,0.0003147817,0.0005242043,0.0001079324,0.0005973319,0.0009685363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005206433,0.00009643704,0.9926695,0.000004531668,0.00002181006,0.00006024071,0.0008478237,0.00003509369,0.0004741886,0.00005382949,0.00007515547,0.005609398],"study_design_scores_gemma":[0.00000168711,0.0001142955,0.9979195,0.000002392017,0.000004532796,0.00008693885,0.001447464,0.00007805488,0.0001971611,0.00003976735,0.000104137,0.000004052252],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9994936,0.00001589057,0.00002602805,0.00001372392,0.000001433961,0.000003365944,0.00004032292,0.000002248489,0.0004033775],"genre_scores_gemma":[0.9995409,0.00001652196,0.00003415327,0.00001070619,0.000001531134,0.000003298238,0.0001036905,0.000001062114,0.0002881202],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03020758,"threshold_uncertainty_score":0.06006348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4323544073","doi":"10.1080/15434303.2023.2184266","title":"Aligning Language Frameworks: An Example with the CLB and CEFR","year":2023,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"","keywords":"Rasch model; Benchmarking; Dimension (graph theory); Computer science; German; Argument (complex analysis); Linguistics; Vocabulary; Certificate; Natural language processing; Computational linguistics; Language proficiency; Artificial intelligence; Psychology; Mathematics education","authors":[{"name":"Brian North","is_ca":false},{"name":"Enrica Piccardo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02005334755489001,"gpt":0.2752021690098073,"spread":0.2551488214549173,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02701222,0.0007620074,0.0006920103,0.008431097,0.006819684,0.008710169,0.00244239,0.002290601,0.00721273],"category_scores_gemma":[0.07585738,0.0005260843,0.0006020141,0.01304957,0.009718081,0.006842485,0.008984303,0.004057551,0.001512418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01748711,"about_ca_system_score_gemma":0.02539293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2938808,"about_ca_topic_score_gemma":0.3671863,"domain_scores_codex":[0.9576035,0.02317956,0.001561584,0.002366807,0.01254604,0.002742643],"domain_scores_gemma":[0.9657239,0.01131534,0.001253413,0.006226084,0.01422957,0.001251593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000986126,0.0001094095,0.007945474,0.0002833651,0.00001937144,0.0004960372,0.09645028,0.002067208,0.002496927,0.647805,0.01061321,0.2316151],"study_design_scores_gemma":[0.0000437103,0.0001314777,0.02071795,0.001141197,0.00004224747,0.0006152316,0.107568,0.008786783,0.005651643,0.1661758,0.6889187,0.0002072858],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1069079,0.001371336,0.4822515,0.01350898,0.0006634633,0.001253147,0.001105093,0.001488622,0.39145],"genre_scores_gemma":[0.4770626,0.000422284,0.5005577,0.0009912142,0.00004041865,0.0008494413,0.001089604,0.000829996,0.01815676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2938808,"threshold_uncertainty_score":0.5843405,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391927924","doi":"10.1080/15434303.2024.2311724","title":"The Development and Initial Validation of O-WSVLT, a Meaning-Recall Online L2 Spanish Vocabulary Levels Test","year":2024,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Psychology; Meaning (existential); Vocabulary; Linguistics; Test (biology); Language proficiency; Recall; Vocabulary development; Cognitive psychology; Mathematics education","authors":[{"name":"Pablo Robles‐García","is_ca":true},{"name":"Stuart McLean","is_ca":false},{"name":"Jeffrey Stewart","is_ca":false},{"name":"Ji-young Shin","is_ca":true},{"name":"Claudia Sánchez‐Gutiérrez","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02360608309281445,"gpt":0.3639875715569394,"spread":0.3403814884641249,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01078403,0.000613523,0.0005258482,0.001650075,0.000438357,0.001153359,0.001076501,0.000781909,0.002056349],"category_scores_gemma":[0.03084334,0.0002975633,0.0007330292,0.0006614106,0.0006329305,0.001218778,0.001904542,0.001063902,0.001469125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007189761,"about_ca_system_score_gemma":0.003151255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002914475,"about_ca_topic_score_gemma":0.004102418,"domain_scores_codex":[0.9951651,0.001745143,0.0006832956,0.0005966481,0.00155044,0.0002593554],"domain_scores_gemma":[0.9872125,0.003936199,0.0008462637,0.0009403001,0.006373797,0.0006909869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008381261,0.00349126,0.3720025,0.0004720263,0.0001262166,0.0006635051,0.009505229,0.001713345,0.0272573,0.002036755,0.005575188,0.5763185],"study_design_scores_gemma":[0.0006449897,0.01113904,0.8602297,0.0006257858,0.0001861698,0.002183216,0.01036654,0.01084792,0.0407306,0.002992215,0.05985945,0.0001943969],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9578837,0.0002053133,0.02527267,0.0004449849,0.0001438748,0.004666598,0.001801464,0.0003574187,0.009223995],"genre_scores_gemma":[0.817521,0.0006287137,0.1446248,0.0006168443,0.0001050371,0.01545596,0.008366533,0.0003240116,0.01235704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01078403,"threshold_uncertainty_score":0.05703211,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405148704","doi":"10.1080/15434303.2024.2438142","title":"The Academic Achievement of Undergraduate Students with Different TOEFL iBT Score Profiles: A Replication Study","year":2024,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"York University","funders":"York University","keywords":"Test of English as a Foreign Language; Replication (statistics); Psychology; Mathematics education; Academic achievement; Language assessment; Statistics; Mathematics","authors":[{"name":"Khaled Barkaoui","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01246481434015625,"gpt":0.349279442253663,"spread":0.3368146279135067,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009226554,0.0009591193,0.000808911,0.001608114,0.001560697,0.001218094,0.001274795,0.000798494,0.001127127],"category_scores_gemma":[0.03241068,0.0004558857,0.001499526,0.001205634,0.0009459849,0.0008798053,0.001439031,0.001272332,0.0007012258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001287685,"about_ca_system_score_gemma":0.001913473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01720099,"about_ca_topic_score_gemma":0.01660092,"domain_scores_codex":[0.9959336,0.001500147,0.000460659,0.0005692292,0.001070691,0.0004657603],"domain_scores_gemma":[0.9766491,0.00305887,0.001712447,0.00826813,0.009028341,0.001283083],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002148264,0.004081462,0.8997283,0.0001244472,0.0004095348,0.0007087006,0.02175501,0.0004293546,0.0141186,0.0003564533,0.00124448,0.05489529],"study_design_scores_gemma":[0.000196586,0.005083371,0.9767035,0.00003135064,0.000151408,0.0005656211,0.008160716,0.0009838291,0.005599527,0.000344681,0.002114555,0.0000650209],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9981441,0.00002475589,0.0006066244,0.00003480648,0.00001850829,0.0002654103,0.0001575782,0.00002556549,0.000722535],"genre_scores_gemma":[0.9975048,0.00001929043,0.0009679022,0.00003936189,0.00000794648,0.0003330121,0.0003341186,0.00001523157,0.0007784191],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9907734,"threshold_uncertainty_score":0.04879528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406605978","doi":"10.1080/15434303.2024.2448963","title":"Test Takers’ Attitudes Toward Varieties of Accents in Listening Tasks of the Duolingo English Test (2021 test version)","year":2025,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Linguistics, Language Diversity, and Identity","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brock University","funders":"","keywords":"Test (biology); Active listening; Psychology; Communication","authors":[{"name":"Okim Kang","is_ca":false},{"name":"Maria Kostromitina","is_ca":false},{"name":"Xu Yan","is_ca":false},{"name":"Ron I. Thomson","is_ca":true},{"name":"Talia Isaacs","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01004874064719094,"gpt":0.2588661768107817,"spread":0.2488174361635908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006004031,0.0003173224,0.0003939106,0.001154717,0.0004846261,0.001494053,0.0003419982,0.0004579164,0.001507053],"category_scores_gemma":[0.02204057,0.0002370067,0.0005464428,0.0003710056,0.0008329727,0.0008539944,0.001510652,0.0007291586,0.0005765598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003965274,"about_ca_system_score_gemma":0.0002229648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002746739,"about_ca_topic_score_gemma":0.003945307,"domain_scores_codex":[0.9967253,0.0009924544,0.0003489486,0.0003474088,0.001336262,0.0002496324],"domain_scores_gemma":[0.9844096,0.005875305,0.004420427,0.0008490531,0.002636164,0.001809549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002970331,0.0002724123,0.9504811,0.00004528909,0.00007134487,0.00029438,0.02558159,0.00009629679,0.00460243,0.0001058655,0.0003943498,0.01775791],"study_design_scores_gemma":[0.00001900236,0.0009716425,0.9703981,0.0000417154,0.00003253595,0.0005083285,0.02415025,0.0003427087,0.001914823,0.0001113244,0.001463577,0.00004600652],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9992341,0.00004181582,0.00007628677,0.00004264703,0.000006041947,0.00001018434,0.00001818137,0.000003621517,0.0005670688],"genre_scores_gemma":[0.9988999,0.0000687453,0.0001594316,0.00006999215,0.000007325918,0.00001925671,0.00006328724,0.000004533262,0.0007074396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006004031,"threshold_uncertainty_score":0.03175277,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385361752","doi":"10.1080/15434303.2023.2237487","title":"The Canadian English Language Proficiency Index Program (CELPIP) Test","year":2023,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Index (typography); Language proficiency; Language assessment; Test (biology); Linguistics; Test of English as a Foreign Language; Psychology; Mathematics education; Computer science; Programming language","authors":[{"name":"Melissa McLeod","is_ca":true},{"name":"Liying Cheng","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01261532384898779,"gpt":0.2915964155539256,"spread":0.2789810917049378,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002009908,0.0005565409,0.0005348078,0.002795792,0.002418279,0.001313547,0.00155327,0.0003942247,0.007643822],"category_scores_gemma":[0.009605777,0.0001899964,0.0004907112,0.003020847,0.0006340572,0.0008439224,0.001469765,0.0009902286,0.001449032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01262053,"about_ca_system_score_gemma":0.04633079,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9039007,"about_ca_topic_score_gemma":0.9432771,"domain_scores_codex":[0.9972378,0.0001726049,0.0001401853,0.0001609631,0.002050404,0.0002380271],"domain_scores_gemma":[0.9943698,0.0002883055,0.000226858,0.00005772438,0.00470282,0.0003544819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002299983,0.000244694,0.1586728,0.00128448,0.0001304862,0.0005291351,0.001959945,0.001025086,0.001273073,0.008984288,0.2233174,0.6023486],"study_design_scores_gemma":[0.00007133929,0.0002500425,0.6965152,0.001500662,0.000177414,0.000837019,0.00205604,0.001780375,0.00222743,0.001897412,0.2925484,0.0001387424],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.3486323,0.02810365,0.02433718,0.009043639,0.001582545,0.00540474,0.06157377,0.0014631,0.5198591],"genre_scores_gemma":[0.7771406,0.02530272,0.03788955,0.002628725,0.0001702877,0.004543413,0.04140421,0.0002402623,0.1106804],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.09609932,"threshold_uncertainty_score":0.1933305,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3111103222","doi":"10.1080/15434303.2020.1846190","title":"“Follow Your Interests Because Those Will Motivate You to Excel”: An Interview with Alister Cumming","year":2020,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of British Columbia; York University","funders":"","keywords":"Psychology; Library science; Computer science","authors":[{"name":"Khaled Barkaoui","is_ca":true},{"name":"Ling Shi","is_ca":true},{"name":"A. Mehdi Riazi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07021481758870055,"gpt":0.395323558554342,"spread":0.3251087409656415,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01424677,0.0008218489,0.000820258,0.001168669,0.02611123,0.006617396,0.002034336,0.007346157,0.003056635],"category_scores_gemma":[0.02653117,0.001122355,0.0004714347,0.001281562,0.01253615,0.01029325,0.004859091,0.02004725,0.001035025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008935649,"about_ca_system_score_gemma":0.008784625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05037967,"about_ca_topic_score_gemma":0.06769289,"domain_scores_codex":[0.9853087,0.01066321,0.0002739634,0.0005061603,0.001684009,0.001563975],"domain_scores_gemma":[0.9809985,0.008803953,0.001047765,0.0003574356,0.003015416,0.005776993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002925589,0.00009536205,0.001829344,0.00009508408,0.000008458416,0.001106403,0.840051,0.00005669321,0.0005467723,0.007177117,0.1378271,0.0111774],"study_design_scores_gemma":[0.00001057043,0.00006691457,0.002125207,0.0003018708,0.000006219284,0.0007927716,0.783208,0.0001315388,0.0002315514,0.001368448,0.2116897,0.00006727795],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1530359,0.009134789,0.001636692,0.7925745,0.00294505,0.0003315146,0.00008030925,0.00007591745,0.04018533],"genre_scores_gemma":[0.6981586,0.0106898,0.003284797,0.2359226,0.0008265948,0.0005607809,0.0000548168,0.0001742442,0.05032777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05037967,"threshold_uncertainty_score":0.1001728,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407098810","doi":"10.1080/15434303.2025.2455196","title":"Differential Item Functioning Due to Cultural Familiarity on a Large-Scale Reading Test: Does the Length of Residence Matter?","year":2025,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"","keywords":"Differential item functioning; Psychology; Reading (process); Scale (ratio); Test (biology); Residence; Item response theory; Psychometrics; Developmental psychology; Linguistics; Geography; Sociology; Demography","authors":[{"name":"Hyun-Ah Kim","is_ca":true},{"name":"Eunice Eunhee Jang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07156230965493464,"gpt":0.4314743672554329,"spread":0.3599120576004983,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01408432,0.0005070386,0.0005269156,0.001544476,0.000669659,0.001224308,0.0009580818,0.0005282943,0.001098979],"category_scores_gemma":[0.06694912,0.000184333,0.0008161954,0.001377239,0.001339086,0.001111742,0.001069905,0.0006815896,0.0002489616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00137022,"about_ca_system_score_gemma":0.001496205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0226352,"about_ca_topic_score_gemma":0.06294477,"domain_scores_codex":[0.9909858,0.003205487,0.001009461,0.0008656328,0.003412416,0.0005212133],"domain_scores_gemma":[0.9428045,0.03120666,0.0134485,0.00376458,0.007078586,0.00169715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009315178,0.00003770415,0.9871761,0.00001846927,0.00007747139,0.00004917333,0.0007262327,0.0000811414,0.0004823262,0.0000477848,0.00006007154,0.0111505],"study_design_scores_gemma":[0.000005276985,0.0001780044,0.9977207,0.0000185831,0.00003263343,0.0001541004,0.000754178,0.0003507922,0.0005197769,0.00007934845,0.0001762188,0.00001031547],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9977977,0.0001195137,0.001108883,0.00008706714,0.00000988499,0.00002937704,0.00007265891,0.000009353273,0.0007656211],"genre_scores_gemma":[0.9987018,0.00004126863,0.0009784529,0.00004114277,0.000008308337,0.0000192154,0.0001017489,0.000006024228,0.0001020883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0226352,"threshold_uncertainty_score":0.0744859,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410015948","doi":"10.1080/15434303.2025.2497818","title":"On the Interplay Between Conceptions of Assessment and Assessment Agency: Perspectives of Iranian EFL Preservice Teachers","year":2025,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Mathematics education; Pedagogy; Agency (philosophy); Psychology; Alternative assessment; Semi-structured interview; Qualitative research; Sociology; Social science","authors":[{"name":"Zahra Banitalebi","is_ca":false},{"name":"Masoomeh Estaji","is_ca":false},{"name":"Andrew Coombs","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01747647657889719,"gpt":0.4119940254646767,"spread":0.3945175488857796,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01137808,0.000305934,0.0003282383,0.001640994,0.004836992,0.006694677,0.0007749652,0.0008716239,0.0006438482],"category_scores_gemma":[0.0132535,0.0003669425,0.0002680928,0.0009923446,0.01413034,0.002955193,0.002368236,0.003114628,0.0000688814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006337504,"about_ca_system_score_gemma":0.006597237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02382147,"about_ca_topic_score_gemma":0.02462208,"domain_scores_codex":[0.9921255,0.005459922,0.0002443368,0.0003140334,0.001159654,0.0006966524],"domain_scores_gemma":[0.9842217,0.009286229,0.002746321,0.0004329726,0.001921436,0.00139135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003718337,0.0001053536,0.0614876,0.00005197553,0.00001188383,0.0004587531,0.9081308,0.0002439968,0.0007051123,0.01719747,0.0003450235,0.01122468],"study_design_scores_gemma":[0.00001101574,0.00008079194,0.03818171,0.0000993865,0.00001345305,0.0004755961,0.9464256,0.0007074408,0.0003456064,0.006358413,0.007263135,0.00003785331],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9864352,0.0007517707,0.001507769,0.002659538,0.00001456385,0.00001502712,0.000007356064,0.000005499275,0.008603334],"genre_scores_gemma":[0.9994466,0.0001345522,0.000184324,0.00005688247,0.000002681146,0.000003314663,0.000002025581,9.517702e-7,0.0001686074],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02382147,"threshold_uncertainty_score":0.06017375,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399443232","doi":"10.1080/15434303.2024.2364172","title":"Adapting to a New Normal: A Review of <i>Technology Assisted Language Assessment in Diverse Contexts</i>","year":2024,"lang":"en","type":"review","venue":"Language Assessment Quarterly","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Language assessment; Psychology; Computer science; Linguistics; Mathematics education","authors":[{"name":"Johanathan Woodworth","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05299991408977252,"gpt":0.4712575397084361,"spread":0.4182576256186636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003623579,0.0007219666,0.001433688,0.004030467,0.0004235879,0.001740123,0.00134762,0.001569934,0.002571179],"category_scores_gemma":[0.009537996,0.0003648757,0.001039015,0.004272188,0.0009429618,0.002679405,0.001321979,0.002466381,0.0008076968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001091672,"about_ca_system_score_gemma":0.004875649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003274708,"about_ca_topic_score_gemma":0.01070899,"domain_scores_codex":[0.9987504,0.00040962,0.0003089586,0.0001423947,0.000333283,0.00005536334],"domain_scores_gemma":[0.992673,0.005484492,0.0006040359,0.0001090489,0.0009523254,0.0001770539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005499825,0.00003900529,0.0002392232,0.07497822,0.0002369551,0.00006036322,0.0001832929,0.0001535068,0.0002831236,0.002708842,0.02971952,0.8913429],"study_design_scores_gemma":[0.00003419376,0.0001561427,0.002418002,0.1193477,0.0008843815,0.0008795271,0.0003661563,0.0001167792,0.0002218916,0.002698782,0.8728279,0.00004850315],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000034457,0.9990388,0.00005240319,0.0005042003,0.0001276854,0.000004211006,0.000008700246,0.0000024889,0.0002270297],"genre_scores_gemma":[0.0003908583,0.998686,0.0001525808,0.0005831255,0.0001031439,0.000007203015,0.00001400076,0.00000119222,0.0000618382],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.004030467,"threshold_uncertainty_score":0.01916355,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406929912","doi":"10.1080/15434303.2025.2458599","title":"From Global Dependence to Local Expertise: An Interview with Rama Mathew","year":2025,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Education and Islamic Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Regional science; Economic geography; Sociology; Geography","authors":[{"name":"Coral Yiwei Qin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01536946584694614,"gpt":0.3964436286729267,"spread":0.3810741628259806,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0084247,0.0004892029,0.0008854762,0.001781185,0.01339535,0.005066667,0.001927216,0.003703032,0.00550174],"category_scores_gemma":[0.01128459,0.001071583,0.0003376643,0.001766356,0.009872278,0.01063548,0.007924514,0.0109761,0.0007388294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007045932,"about_ca_system_score_gemma":0.005690943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04887993,"about_ca_topic_score_gemma":0.1019077,"domain_scores_codex":[0.9916846,0.005313301,0.0001970218,0.0004339421,0.001153873,0.001217263],"domain_scores_gemma":[0.992277,0.003852154,0.000557069,0.0001573752,0.0008119039,0.002344482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001785299,0.00007095284,0.002172274,0.0001171938,0.000006408499,0.002204115,0.9585942,0.00004911461,0.000851331,0.005203286,0.02373514,0.006978231],"study_design_scores_gemma":[0.000002508204,0.00002070133,0.001681778,0.0001338854,0.000002486916,0.0005645019,0.957875,0.00004750161,0.00006324967,0.0004488514,0.03913837,0.00002117369],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6482892,0.006406382,0.001167458,0.2781796,0.0007752692,0.0001545127,0.0001289106,0.00006725368,0.06483151],"genre_scores_gemma":[0.943482,0.004395444,0.0009912063,0.03010064,0.000101037,0.0001492427,0.00004773442,0.0000679965,0.02066481],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04887993,"threshold_uncertainty_score":0.0971908,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}