{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":45,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":45,"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":"7fae06dd8c7e","filters":{"venue":"British Journal of Mathematical and Statistical Psychology"}},"results":[{"id":"W2168627095","doi":"10.1348/000711004849222","title":"A note on preliminary tests of equality of variances","year":2004,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":313,"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":"F-test of equality of variances; Statistics; Test (biology); Type I and type II errors; Levene's test; Mathematics; Sample size determination; Econometrics; Nominal level; Statistical hypothesis testing; Test statistic","authors":[{"name":"Donald W. Zimmerman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3838805211543762,"gpt":0.5674083538348488,"spread":0.1835278326804726,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00412746,0.0001945669,0.001517728,0.0000911515,0.00004219319,0.00001731188,0.0003097609,0.0002468731,0.0004698087],"category_scores_gemma":[0.09060911,0.0001666467,0.0001760292,0.0001560628,0.001126205,0.0000573902,0.00006973734,0.0005707582,0.000007760424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001986632,"about_ca_system_score_gemma":0.00007503292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006584369,"about_ca_topic_score_gemma":0.000002344968,"domain_scores_codex":[0.995394,0.0008016667,0.00262454,0.0002798519,0.0006001014,0.0002998368],"domain_scores_gemma":[0.9570193,0.04111833,0.001022374,0.0002528609,0.000321433,0.0002657015],"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":[0.00106733,0.002550074,0.00003223445,0.0008726931,0.0001160038,0.0003531162,0.0001389029,0.000002944742,0.0003774954,0.9304078,0.0007061607,0.06337528],"study_design_scores_gemma":[0.00262484,0.003483661,0.007188027,0.001213235,0.0001725237,0.001472117,0.0000290219,0.00002485114,0.0002914882,0.9833226,0.00002904682,0.0001486122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06149862,0.0001712837,0.9338751,0.0006439546,0.0002774198,0.0002473978,0.0002872996,0.00001198294,0.002986924],"genre_scores_gemma":[0.3750048,0.00009841636,0.6246401,0.0001423871,0.00008170565,0.000003197998,4.410184e-7,0.00001668823,0.0000122633],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3135062,"threshold_uncertainty_score":0.9170511,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125118056","doi":"10.1348/000711001159357","title":"The analysis of repeated measures designs: A review","year":2001,"lang":"en","type":"review","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":299,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Univariate; Strengths and weaknesses; Statistic; Repeated measures design; Statistics; Multivariate statistics; Multivariate analysis; Type I and type II errors; Statistical analysis; Multivariate analysis of variance; Statistical hypothesis testing; Analysis of variance; Term (time); Econometrics; Mathematics; Computer science; Psychology; Social psychology","authors":[{"name":"H. J. Keselman","is_ca":true},{"name":"James Algina","is_ca":false},{"name":"Rhonda K. Kowalchuk","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3533793608111171,"gpt":0.5400826959220477,"spread":0.1867033351109306,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004701435,0.0004136639,0.005482862,0.000215217,0.0001462172,0.000056407,0.0005246152,0.0003150353,0.0004017163],"category_scores_gemma":[0.02168314,0.0002628073,0.0008756037,0.0008469179,0.0007949711,0.00005128397,0.00008124059,0.000966205,0.000004353224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002680793,"about_ca_system_score_gemma":0.0001021221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002271889,"about_ca_topic_score_gemma":0.000005735102,"domain_scores_codex":[0.9928846,0.001860385,0.003756977,0.0004019298,0.0006426417,0.0004534755],"domain_scores_gemma":[0.9777251,0.0190827,0.001918697,0.0004411994,0.0004999524,0.0003323474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002211996,0.0001963024,8.256971e-8,0.0129795,0.001866607,0.0004185266,0.000008765947,8.280642e-8,9.231245e-8,0.1387915,0.005225002,0.8404914],"study_design_scores_gemma":[0.0002416946,0.0002137291,0.000003852603,0.03036264,0.01874739,0.005181399,0.00001000496,0.00004016533,3.509943e-8,0.7004115,0.2445268,0.0002607694],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.293651e-7,0.5279285,0.4710799,0.00004682268,0.00005167068,0.0002698666,0.0001592083,0.000006197792,0.0004575905],"genre_scores_gemma":[0.000001060243,0.7841513,0.2155391,0.0000844137,0.00004629294,0.0000228034,0.000009020921,0.00003828158,0.0001076575],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8402306,"threshold_uncertainty_score":0.9999824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1561373080","doi":"10.1111/j.2044-8317.2012.02049.x","title":"The performance of robust test statistics with categorical data","year":2012,"lang":"en","type":"review","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":162,"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; University of British Columbia Hospital","funders":"","keywords":"Statistics; Categorical variable; Mathematics; Statistic; Estimator; Standard error; Test statistic; Robust statistics; Type I and type II errors; Sample size determination; Statistical hypothesis testing; Variance (accounting)","authors":[{"name":"Victoria Savalei","is_ca":true},{"name":"Mijke Rhemtulla","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3136864516944847,"gpt":0.4807478002530468,"spread":0.1670613485585621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002734601,0.0004615731,0.002851997,0.00007957781,0.0002093847,0.00008154719,0.0009941289,0.0003215684,0.0001778771],"category_scores_gemma":[0.007277373,0.0002753399,0.0001141286,0.0001864147,0.001391562,0.0001533887,0.0002792073,0.001355669,0.000009877515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002729155,"about_ca_system_score_gemma":0.0001841573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001912853,"about_ca_topic_score_gemma":0.0000054723,"domain_scores_codex":[0.995171,0.0006052281,0.002494203,0.0004338354,0.0006538849,0.000641894],"domain_scores_gemma":[0.9697126,0.02732288,0.001457424,0.0007076876,0.0003547815,0.000444628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004348757,0.0004235609,0.000001369183,0.007769881,0.0001753413,0.0002309006,0.00001329174,1.756349e-7,7.122863e-8,0.2253191,0.003222236,0.7628006],"study_design_scores_gemma":[0.0009395711,0.001705286,0.00002618663,0.007430436,0.00421172,0.03274582,0.00003839747,0.0007521479,1.55423e-7,0.6978435,0.253631,0.000675807],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.000002374721,0.4373949,0.5608176,0.00002177332,0.0001043413,0.0002361794,0.00119907,0.000006406087,0.0002173134],"genre_scores_gemma":[0.00002247762,0.5520787,0.4476044,0.00001275482,0.0001232677,0.000008871667,0.00002696692,0.00005033343,0.00007232333],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7621248,"threshold_uncertainty_score":0.9999699,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2113330311","doi":"10.1348/000711002159680","title":"Controlling the rate of Type I error over a large set of statistical tests","year":2002,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":160,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"False discovery rate; Type I and type II errors; Multiple comparisons problem; Statistical power; Null hypothesis; Statistics; Statistical hypothesis testing; p-value; Mathematics; Word error rate; Null (SQL); Set (abstract data type); Statistical process control; Statistical significance; Sample size determination; False positive rate; Computer science; Data mining; Artificial intelligence; Process (computing); Biology","authors":[{"name":"H. J. Keselman","is_ca":true},{"name":"Robert A. Cribbie","is_ca":true},{"name":"Burt Holland","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3972428971676623,"gpt":0.5422999661469321,"spread":0.1450570689792698,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006056384,0.0002465922,0.001739017,0.00008486458,0.0000882426,0.00003945405,0.0004039667,0.0002496839,0.004760579],"category_scores_gemma":[0.1209736,0.0001780418,0.0001757572,0.0002334068,0.001292687,0.00006496126,0.0001000855,0.0007770594,0.0000191237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001835888,"about_ca_system_score_gemma":0.00003292916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006199057,"about_ca_topic_score_gemma":0.000004026519,"domain_scores_codex":[0.994015,0.001812485,0.002845096,0.0003046253,0.0005406337,0.0004821958],"domain_scores_gemma":[0.9232587,0.07469788,0.0009660983,0.0003047733,0.0004775012,0.0002950419],"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":[0.0006178417,0.001263908,0.0001653288,0.0005327695,0.000324484,0.0004743162,0.0001934005,0.000001037379,0.0002709169,0.9506126,0.02115838,0.02438502],"study_design_scores_gemma":[0.003386142,0.001134514,0.002685969,0.0004371873,0.0003728166,0.001238113,0.00008443206,0.00316707,0.00002477271,0.9868596,0.0004234015,0.0001860406],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05637467,0.00078247,0.9377987,0.0009135175,0.000473007,0.0004550552,0.001208808,0.00001722352,0.00197655],"genre_scores_gemma":[0.5133141,0.0003528513,0.4855653,0.0004300406,0.0002101849,0.0000042559,0.000001849927,0.00004221961,0.00007917677],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4569395,"threshold_uncertainty_score":0.9961492,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2620799017","doi":"10.1111/bmsp.12103","title":"<scp>ANOVA</scp> and the variance homogeneity assumption: Exploring a better gatekeeper","year":2017,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":81,"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":"Homogeneity (statistics); Analysis of variance; F-test of equality of variances; Null hypothesis; Statistics; Mathematics; Levene's test; One-way analysis of variance; Equivalence (formal languages); Statistical hypothesis testing; Variance (accounting); Econometrics; Mixed-design analysis of variance; Population variance; Population; Test statistic; Demography; Discrete mathematics","authors":[{"name":"Yoosun Jamie Kim","is_ca":true},{"name":"Robert A. Cribbie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4557394537833383,"gpt":0.5102854334071317,"spread":0.05454597962379343,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.007023971,0.0002508022,0.001292547,0.00004792467,0.0005870883,0.0004202721,0.0005672998,0.0002235423,0.0004379693],"category_scores_gemma":[0.1446372,0.0001809692,0.0001573558,0.00005076233,0.002891323,0.0002111681,0.0002459436,0.000942072,0.00003019243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000135854,"about_ca_system_score_gemma":0.00002515927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006997605,"about_ca_topic_score_gemma":0.000003569713,"domain_scores_codex":[0.9959061,0.001137134,0.00159175,0.0004061923,0.0005006839,0.0004581281],"domain_scores_gemma":[0.9511646,0.04692145,0.0008096529,0.0005083604,0.000232048,0.0003638766],"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":[0.0001979419,0.0003588063,0.0003501987,0.000277859,0.0002458397,0.0008252288,0.0001807469,8.320208e-8,0.00004500342,0.8660449,0.008514993,0.1229584],"study_design_scores_gemma":[0.004066713,0.0002061815,0.02237256,0.0003199644,0.0002523027,0.004559471,0.00004850178,0.0001393582,0.00001317457,0.9669433,0.0009742418,0.000104192],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.146149,0.0005507852,0.8444591,0.003503533,0.0007243465,0.0003628835,0.00009386559,0.00002341094,0.004133147],"genre_scores_gemma":[0.1204255,0.001467063,0.8758939,0.001098597,0.0008085318,0.00004482491,5.447311e-7,0.00004908578,0.0002120119],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1376132,"threshold_uncertainty_score":0.9998223,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2584362917","doi":"10.1111/bmsp.12085","title":"Population models and simulation methods: The case of the Spearman rank correlation","year":2017,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":76,"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":"Spearman's rank correlation coefficient; Rank correlation; Correlation; Statistic; Copula (linguistics); Statistics; Rank (graph theory); Population; Sample size determination; Mathematics; Nonparametric statistics; Econometrics; Test statistic; Statistical hypothesis testing; Demography","authors":[{"name":"Oscar L. Olvera Astivia","is_ca":true},{"name":"Bruno D. Zumbo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1233661564023228,"gpt":0.4800994533102129,"spread":0.35673329690789,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002100129,0.0001121486,0.0004350121,0.00002876512,0.000396518,0.0001094644,0.0002041036,0.000105688,0.0001011225],"category_scores_gemma":[0.009084335,0.00006897678,0.00006187762,0.00003891838,0.0007881274,0.0001504486,0.00008344791,0.0003516362,6.817606e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000814121,"about_ca_system_score_gemma":0.00001173356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003876191,"about_ca_topic_score_gemma":0.00001557781,"domain_scores_codex":[0.998059,0.0006921523,0.0007725478,0.0001490541,0.0001748019,0.0001524653],"domain_scores_gemma":[0.9931265,0.005682028,0.000661852,0.000266063,0.000164388,0.000099205],"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":[0.0000447727,0.00007383878,0.0001071906,0.00009607445,0.00002794553,0.0001445913,0.0001614367,0.00001283304,0.00001441864,0.6872796,0.0001425158,0.3118948],"study_design_scores_gemma":[0.0004895097,0.00008499023,0.01825121,0.0001625019,0.0001297926,0.007345956,0.00006607652,0.0847298,0.00000341801,0.8886524,0.00001255033,0.00007178138],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04493261,0.0001286562,0.9532382,0.0005228575,0.0001511561,0.0001763779,0.00003472865,0.000004017625,0.0008114307],"genre_scores_gemma":[0.5588543,0.00003543553,0.4410057,0.00004679913,0.00003822329,0.000001438867,3.232379e-7,0.000007629784,0.0000101645],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5139217,"threshold_uncertainty_score":0.9992626,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151152712","doi":"10.1348/000711002760554516","title":"Skill set analysis in knowledge structures","year":2002,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":58,"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":"Consistency (knowledge bases); Set (abstract data type); Interpretation (philosophy); Computer science; Test (biology); Cognitive psychology; Empirical research; Test theory; Artificial intelligence; Mathematics; Psychology; Statistics; Psychometrics","authors":[{"name":"Günther Gediga","is_ca":false},{"name":"Ivo Düntsch","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03577935715460232,"gpt":0.328755334554809,"spread":0.2929759774002066,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007357316,0.0001401594,0.0006476368,0.0002602336,0.00005312444,0.0001388179,0.0005401931,0.0001109335,0.0007711897],"category_scores_gemma":[0.0007089167,0.0001284013,0.0001140313,0.0006056633,0.0002605133,0.0001512375,0.0001454173,0.0004272278,0.000026261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002366665,"about_ca_system_score_gemma":0.00001199616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005946128,"about_ca_topic_score_gemma":0.00002490341,"domain_scores_codex":[0.9979457,0.0003172724,0.0008255974,0.0003321493,0.0002554925,0.0003237558],"domain_scores_gemma":[0.9981568,0.001090691,0.0001502592,0.0002263391,0.0001273676,0.000248526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001828366,0.001440096,0.001301199,0.00009974018,0.0002700989,0.002604365,0.001402099,0.00004818897,0.00001136785,0.3498204,0.006656264,0.6363279],"study_design_scores_gemma":[0.0008280896,0.0002877227,0.1108771,0.00003632495,0.00007623617,0.005636346,0.00002454136,0.07742089,0.000001672432,0.8042653,0.0003540709,0.0001916984],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04176292,0.001261583,0.9538164,0.0006744095,0.0001715429,0.00007400856,0.00001811864,0.00001782229,0.002203172],"genre_scores_gemma":[0.7676089,0.0001444578,0.2318949,0.0002319465,0.0000651236,0.000001836059,9.287687e-7,0.000006357167,0.00004554939],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.725846,"threshold_uncertainty_score":0.8443987,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1572657933","doi":"10.1111/j.2044-8317.2011.02014.x","title":"Effect of non‐normality on test statistics for one‐way independent groups designs","year":2011,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; York University","funders":"","keywords":"Statistics; Normality; Estimator; Truncated mean; Type I and type II errors; Mathematics; Test statistic; Nominal level; Parametric statistics; Statistic; Statistical hypothesis testing; Normal distribution; Variance (accounting); Econometrics; Nonparametric statistics; Asymptotic distribution; Confidence interval","authors":[{"name":"Robert A. Cribbie","is_ca":true},{"name":"Lisa Fıksenbaum","is_ca":true},{"name":"H. J. Keselman","is_ca":true},{"name":"Rand R. Wilcox","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4357774667779384,"gpt":0.5329337513487912,"spread":0.09715628457085279,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009202754,0.000331547,0.001964821,0.0001218214,0.0001004012,0.00004057855,0.0004205421,0.0003622202,0.001115125],"category_scores_gemma":[0.1324564,0.0002834386,0.000225358,0.0001235369,0.0008919203,0.00007332848,0.00008069435,0.0007665355,0.00001751063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003112656,"about_ca_system_score_gemma":0.00004376225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005134364,"about_ca_topic_score_gemma":0.00000284005,"domain_scores_codex":[0.9943103,0.001369906,0.002706472,0.0004230539,0.0006572371,0.0005330935],"domain_scores_gemma":[0.8855559,0.1124012,0.000915735,0.0002933421,0.0003873402,0.0004465313],"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":[0.003875927,0.004546482,0.0004340518,0.002725645,0.0003900421,0.000555186,0.0002209702,2.150834e-7,0.0003245818,0.7915285,0.007564418,0.187834],"study_design_scores_gemma":[0.004247807,0.01289431,0.00704985,0.0005756752,0.0005421136,0.0009003656,0.0000202966,0.000202723,0.0008999745,0.9723749,0.00002164644,0.0002703705],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02845143,0.00004363883,0.9671117,0.00005918967,0.000349489,0.0007620359,0.001304568,0.00001734825,0.001900604],"genre_scores_gemma":[0.2153418,0.00007459577,0.7841613,0.0001476826,0.0001565427,0.00003278505,0.000002954602,0.00004759596,0.00003473833],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1875636,"threshold_uncertainty_score":0.9999618,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2075806409","doi":"10.1111/bmsp.12045","title":"Equivalence tests for comparing correlation and regression coefficients","year":2014,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":55,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Equivalence (formal languages); Mathematics; Statistics; Correlation; Regression analysis; Regression; Linear regression; Applied mathematics; Null hypothesis; Econometrics; Pure mathematics","authors":[{"name":"Alyssa Counsell","is_ca":true},{"name":"Robert A. Cribbie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4380628287343638,"gpt":0.5641740061112318,"spread":0.126111177376868,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004176043,0.0001650599,0.0009302446,0.00006266285,0.0001295194,0.00007518494,0.0001625197,0.0001817731,0.0001144742],"category_scores_gemma":[0.1064759,0.0001392772,0.00007168234,0.00007176376,0.000552094,0.00006663056,0.00007038334,0.0003879778,0.000004894787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001191823,"about_ca_system_score_gemma":0.00001335217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.635494e-7,"about_ca_topic_score_gemma":9.468086e-7,"domain_scores_codex":[0.9971558,0.0006044715,0.001321739,0.0002952772,0.0003187425,0.0003039117],"domain_scores_gemma":[0.9517521,0.04712495,0.0004574871,0.0001372618,0.0002227096,0.000305553],"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":[0.0003541697,0.0004892002,0.0004224518,0.0005537031,0.00004706828,0.00005001892,0.00006515581,0.000001351176,0.0001137871,0.7354068,0.005629856,0.2568665],"study_design_scores_gemma":[0.002289988,0.0007339989,0.004699898,0.0007104512,0.0001251419,0.001542086,0.0000176427,0.009230399,0.000009121891,0.9801806,0.0003062186,0.0001544769],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03612513,0.0001473888,0.961938,0.0002878743,0.0003288609,0.000255756,0.00004140731,0.00001714833,0.0008583814],"genre_scores_gemma":[0.3029173,0.00008068496,0.6966165,0.000170867,0.0001485998,0.000006846712,0.000001025567,0.00001980411,0.00003842175],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2667921,"threshold_uncertainty_score":0.9010507,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036701577","doi":"10.1348/000711009x475853","title":"Detecting a lack of association: An equivalence testing approach","year":2009,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":54,"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":"Association (psychology); Type I and type II errors; Equivalence (formal languages); Sample size determination; Test (biology); Association test; Statistics; Statistical hypothesis testing; Econometrics; Independence (probability theory); Statistical power; Sample (material); Psychology; Computer science; Mathematics","authors":[{"name":"Jason R. Goertzen","is_ca":true},{"name":"Robert A. Cribbie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6273935671893198,"gpt":0.5794021805264894,"spread":0.04799138666283043,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007354874,0.0001892447,0.001245514,0.00008063737,0.00009037142,0.00006742842,0.0003231706,0.0002683832,0.0002492396],"category_scores_gemma":[0.2028431,0.0001761477,0.0001141966,0.0002402877,0.0003036052,0.0001284395,0.0000449117,0.0007477421,0.00000421721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003438376,"about_ca_system_score_gemma":0.00004201106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001925447,"about_ca_topic_score_gemma":3.801069e-7,"domain_scores_codex":[0.9952832,0.001141042,0.002213082,0.0003213194,0.0006260123,0.0004153094],"domain_scores_gemma":[0.9584871,0.03930609,0.001135931,0.0002063033,0.0005175509,0.000347047],"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":[0.0003153898,0.002764691,0.0004364204,0.0006081299,0.0001581411,0.0005013947,0.0002277667,0.000002240865,0.001058298,0.517347,0.00168804,0.4748925],"study_design_scores_gemma":[0.00122538,0.001531595,0.004767342,0.0003385993,0.000159671,0.003426387,0.0000671879,0.0009956433,0.00004392458,0.9872526,0.0000142602,0.0001774417],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.050041,0.0001287223,0.9417574,0.0002824424,0.0001575901,0.0001970781,0.00006229778,0.00002900707,0.007344409],"genre_scores_gemma":[0.2146921,0.00003462701,0.7847619,0.0002590359,0.000202945,0.000002150949,4.076725e-7,0.0000161372,0.00003070758],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.474715,"threshold_uncertainty_score":0.8038716,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4283316432","doi":"10.1111/bmsp.12272","title":"An explanatory mixture <scp>IRT</scp> model for careless and insufficient effort responding in self‐report measures","year":2022,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Respondent; Set (abstract data type); Scale (ratio); Computer science; Trait; Statistics; Econometrics; Mathematics; Data mining","authors":[{"name":"Esther Ulitzsch","is_ca":false},{"name":"Seyma N. Yildirim‐Erbasli","is_ca":true},{"name":"Guher Gorgun","is_ca":true},{"name":"Okan Bulut","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1287896801544608,"gpt":0.4405964656351253,"spread":0.3118067854806645,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02412769,0.0001074177,0.0004425541,0.000204945,0.0004565604,0.00004856128,0.0002011069,0.0001524265,0.00004657319],"category_scores_gemma":[0.01195794,0.0001133247,0.00004869821,0.0001663817,0.0004094115,0.0000945298,0.00004340275,0.0005260912,4.109851e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004755574,"about_ca_system_score_gemma":0.0001674194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002158054,"about_ca_topic_score_gemma":0.0001086682,"domain_scores_codex":[0.9944699,0.003890075,0.0006165725,0.0002714155,0.0003927854,0.0003592526],"domain_scores_gemma":[0.9897746,0.009550526,0.0001885048,0.00008604365,0.0001231536,0.0002771886],"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":[0.008691396,0.006784,0.01697302,0.0004673784,0.0004011969,0.02369074,0.1059689,0.0005672926,0.001342537,0.7215223,0.02277957,0.09081167],"study_design_scores_gemma":[0.005528781,0.002534785,0.176125,0.0001893552,0.000210756,0.02832306,0.02347755,0.01392993,0.00002349455,0.7327805,0.01642382,0.0004530349],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.816598,0.0007651,0.1814169,0.0002418173,0.0002057235,0.0001902407,0.00009421312,0.00001282474,0.0004751225],"genre_scores_gemma":[0.9555597,0.0001893653,0.04363973,0.0003602983,0.00007018318,0.00003175458,0.00000609402,0.00001465362,0.0001281637],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.159152,"threshold_uncertainty_score":0.9963648,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3205145300","doi":"10.1111/bmsp.12255","title":"A comparative evaluation of factor‐ and component‐based structural equation modelling approaches under (in)correct construct representations","year":2021,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Component (thermodynamics); Construct (python library); Structural equation modeling; Misrepresentation; Population; Principal component analysis; Factor analysis; Mathematics; Econometrics; Factor (programming language); Statistics; Computer science","authors":[{"name":"Gyeongcheol Cho","is_ca":true},{"name":"Marko Sarstedt","is_ca":false},{"name":"Heungsun Hwang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.8016671738027995,"gpt":0.5424559714075778,"spread":0.2592112023952217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004137191,0.00009592115,0.0006229411,0.0002144832,0.00006907243,0.00010196,0.0001263294,0.00007680793,0.0003773958],"category_scores_gemma":[0.01886131,0.00008066414,0.00005291954,0.0004265096,0.0003869274,0.0001250436,0.00003655397,0.0002512234,9.838326e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000166167,"about_ca_system_score_gemma":0.00007980638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009927747,"about_ca_topic_score_gemma":0.000008598924,"domain_scores_codex":[0.9959045,0.001580954,0.001196537,0.0002858382,0.0008767975,0.0001553469],"domain_scores_gemma":[0.9784634,0.02019897,0.0004780798,0.0001246467,0.0006270996,0.0001077705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004694892,0.0009132118,0.03714766,0.0001843217,0.0002469002,0.0002906278,0.002496109,0.04074813,0.001139726,0.1725195,0.0004390646,0.7434053],"study_design_scores_gemma":[0.0009392886,0.00006656194,0.1188634,0.00006412327,0.00003135364,0.000948025,0.0009523974,0.3795527,0.00003052075,0.4984916,0.000001692129,0.00005835117],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4819427,0.000559792,0.5167004,0.0001368813,0.00008295537,0.00007078569,0.00002424235,0.000001684754,0.0004805977],"genre_scores_gemma":[0.8185953,0.00002484793,0.1813173,0.00003400674,0.00001592612,0.000001889886,0.000003552927,0.000003200308,0.000003862127],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.743347,"threshold_uncertainty_score":0.9894032,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2171530386","doi":"10.1348/000711000159286","title":"Testing treatment effects in repeated measures designs: Trimmed means and bootstrapping","year":2000,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Saskatchewan Health; Health Canada; University of Manitoba","funders":"","keywords":"Estimator; Type I and type II errors; Statistics; Mathematics; Covariance; Sphericity; Bootstrapping (finance); Normality; Statistical hypothesis testing; Repeated measures design; Econometrics","authors":[{"name":"H. J. Keselman","is_ca":true},{"name":"Rhonda K. Kowalchuk","is_ca":true},{"name":"James Algina","is_ca":false},{"name":"Lisa M. Lix","is_ca":true},{"name":"Rand R. Wilcox","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06834616108167536,"gpt":0.3423298604087666,"spread":0.2739836993270913,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006072756,0.0001621695,0.0005299986,0.00009257947,0.00007381834,0.00009916127,0.0002023597,0.00009610298,0.00002719651],"category_scores_gemma":[0.001750879,0.0001455186,0.0000313051,0.000160981,0.0002289701,0.0001653924,0.00002879212,0.0002757021,0.000002988413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003259136,"about_ca_system_score_gemma":0.00002794826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001480979,"about_ca_topic_score_gemma":0.000004158721,"domain_scores_codex":[0.9981323,0.0002859666,0.0007281924,0.0003203642,0.0002115368,0.0003216456],"domain_scores_gemma":[0.9970528,0.002385775,0.0001082263,0.0001380757,0.00008385209,0.0002311999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000546779,0.0002692005,0.00005182814,0.00005310395,0.00002168578,0.001882391,0.0001335605,0.00001524371,0.0003416011,0.05120581,0.00008850788,0.9458824],"study_design_scores_gemma":[0.001593443,0.001301531,0.009187208,0.0005236024,0.00002864724,0.007668755,0.000008259784,0.03312875,0.00004971863,0.9462198,0.00008932601,0.0002009478],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02150683,0.0006962483,0.9765844,0.0002500501,0.00002676458,0.0001752002,0.000006639762,0.00004636736,0.0007075058],"genre_scores_gemma":[0.3601481,0.0002920409,0.6393544,0.0001571998,0.00001804214,0.000008641475,4.382453e-7,0.000009039732,0.00001214118],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9456815,"threshold_uncertainty_score":0.5934078,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2088581243","doi":"10.1348/000711005x63755","title":"Adaptive robust estimation and testing","year":2006,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Normality; Type I and type II errors; Trimming; Mathematics; Sample size determination; Variance (accounting); Econometrics; Null hypothesis; Population; Computer science; Medicine","authors":[{"name":"H. J. Keselman","is_ca":true},{"name":"Rand R. Wilcox","is_ca":false},{"name":"Lisa M. Lix","is_ca":true},{"name":"James Algina","is_ca":false},{"name":"Katherine Fradette","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09456399157201978,"gpt":0.3782400034171062,"spread":0.2836760118450865,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009061399,0.0001499085,0.0005311089,0.000063992,0.0001081343,0.00009287072,0.00009269868,0.0001139033,0.0001950606],"category_scores_gemma":[0.006062201,0.0001346875,0.00003374464,0.0001047107,0.0004679369,0.0000967599,0.00003849897,0.0003516593,0.000005266609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000117238,"about_ca_system_score_gemma":0.00002122893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001409806,"about_ca_topic_score_gemma":0.00000416678,"domain_scores_codex":[0.9982265,0.0002248671,0.000834158,0.0002116641,0.0002403137,0.0002625628],"domain_scores_gemma":[0.9936547,0.005616932,0.0002689167,0.00008194042,0.0001952865,0.0001822322],"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":[0.00003336565,0.0001706727,0.00006875542,0.00009664388,0.00001548601,0.0003197619,0.00001758943,7.819157e-7,0.00003977271,0.7033953,0.001809841,0.294032],"study_design_scores_gemma":[0.0006223042,0.0003919376,0.01120782,0.0002678023,0.00007857633,0.008364815,0.00002888723,0.009864626,0.000006820776,0.9689919,0.0000278621,0.0001466838],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01233674,0.0002371337,0.9827238,0.0002094494,0.00006281801,0.0001014615,0.00004555299,0.00001753147,0.004265536],"genre_scores_gemma":[0.1399408,0.00002369402,0.8598244,0.00008193931,0.00008909524,0.00000313329,0.000001064337,0.00001491266,0.00002092046],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2938854,"threshold_uncertainty_score":0.7257459,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1968781945","doi":"10.1348/000711007x270843","title":"Nearly unbiased estimators for the three‐parameter Weibull distribution with greater efficiency than the iterative likelihood method","year":2008,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Mathematics; Statistics; Weibull distribution; Estimator; Monte Carlo method; Sample size determination; Maximum likelihood; Population; Estimation theory; Shape parameter; Sample (material); Applied mathematics; Physics","authors":[{"name":"Denis Cousineau","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06871545134842222,"gpt":0.3775750273567284,"spread":0.3088595760083062,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009598563,0.0002075569,0.0004682915,0.00002917351,0.0006249032,0.0001247633,0.0002790016,0.0001036404,0.000264031],"category_scores_gemma":[0.003575366,0.0001143231,0.0001117146,0.0001925386,0.00101251,0.00008587015,0.00003148874,0.0004151801,0.00001268024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002565681,"about_ca_system_score_gemma":0.00005711264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006466502,"about_ca_topic_score_gemma":0.000007219767,"domain_scores_codex":[0.9979722,0.0002198045,0.000802871,0.0002609698,0.0003792116,0.0003648701],"domain_scores_gemma":[0.9891337,0.009694293,0.0003228486,0.0002277458,0.0004107977,0.0002106601],"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":[0.0003469123,0.0006746417,0.0001496542,0.00009627527,0.0001979942,0.0001295821,0.0003762959,0.000009582523,0.00001943549,0.9503943,0.02166427,0.02594104],"study_design_scores_gemma":[0.002103854,0.0008208564,0.03434428,0.000146845,0.000383274,0.01033348,0.0001190037,0.02980775,0.00002927746,0.9206136,0.001034023,0.0002637337],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01976251,0.00009641221,0.9752021,0.003316591,0.00006224445,0.0005787821,0.0008208869,0.00002237258,0.0001381161],"genre_scores_gemma":[0.6473719,0.00003586063,0.3517069,0.0005227529,0.00009924079,0.0001315257,0.000044148,0.00002847946,0.00005924086],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6276094,"threshold_uncertainty_score":0.4806314,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2006005214","doi":"10.1348/000711000159187","title":"Repeated measures ANOVA: Some new results on comparing trimmed means and means","year":2000,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Univariate; Mathematics; Percentile; Statistics; Bonferroni correction; Pairwise comparison; Type I and type II errors; Repeated measures design; Truncated mean; Multivariate statistics; Extant taxon; Confidence interval; Econometrics","authors":[{"name":"Rand R. Wilcox","is_ca":false},{"name":"H. J. Keselman","is_ca":true},{"name":"Jan Muska","is_ca":false},{"name":"Robert A. Cribbie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1574561485689929,"gpt":0.4242876479967463,"spread":0.2668314994277534,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001470981,0.0002682362,0.001072422,0.00009100937,0.0001461656,0.0000873429,0.0001804817,0.0001802537,0.0004228088],"category_scores_gemma":[0.005693106,0.0002335318,0.00008543547,0.0001035921,0.0004331303,0.0001369052,0.00003185454,0.0006781569,0.00001484145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001892336,"about_ca_system_score_gemma":0.00003593352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001030215,"about_ca_topic_score_gemma":0.000008275004,"domain_scores_codex":[0.9967886,0.0004131111,0.001438602,0.0004346429,0.0004642992,0.0004607335],"domain_scores_gemma":[0.9949608,0.003808065,0.000268233,0.000217044,0.0001302749,0.000615512],"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":[0.00131459,0.0005027187,0.000005193295,0.0001078644,0.000109627,0.0008125515,0.0002250162,0.000009929036,0.00007548742,0.5041727,0.01235496,0.4803094],"study_design_scores_gemma":[0.003894522,0.0008470833,0.0008120947,0.0004422846,0.0001361393,0.004180866,0.00004623531,0.001720364,0.00001885897,0.9857885,0.00185153,0.0002614953],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02492878,0.0005463235,0.962572,0.001307772,0.0001151372,0.0002365712,0.0001413038,0.00004064965,0.0101114],"genre_scores_gemma":[0.1156737,0.001281677,0.8809108,0.0008101987,0.0002660753,0.000005173498,0.0000063499,0.00005728038,0.0009887149],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4816159,"threshold_uncertainty_score":0.9523152,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2995591168","doi":"10.1111/bmsp.12194","title":"The danger of conflating level‐specific effects of control variables when primary interest lies in level‐2 effects","year":2019,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":38,"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":"Conflation; Cluster (spacecraft); Variable (mathematics); Control variable; Econometrics; Multilevel model; Estimation; Control (management); Statistics; Variables; Psychology; Computer science; Mathematics; Economics; Epistemology; Artificial intelligence","authors":[{"name":"Jason D. Rights","is_ca":true},{"name":"Kristopher J. Preacher","is_ca":false},{"name":"David A. Cole","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0946494624905834,"gpt":0.3728073056028315,"spread":0.2781578431122481,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001351515,0.0001805454,0.001039645,0.00009086921,0.00003835369,0.0000330777,0.0002819761,0.0001606662,0.00009391041],"category_scores_gemma":[0.004523314,0.0001371165,0.00008190862,0.00008160687,0.0005658722,0.0001104039,0.00007150819,0.0005222717,0.000003733357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002671874,"about_ca_system_score_gemma":0.00003198156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005056084,"about_ca_topic_score_gemma":0.000007836086,"domain_scores_codex":[0.9975129,0.0004115092,0.001301579,0.0001889862,0.0002838893,0.0003010748],"domain_scores_gemma":[0.9803374,0.01852815,0.000617507,0.0002062128,0.0002132811,0.00009747048],"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":[0.0003478267,0.0006039984,0.0004987929,0.002950531,0.0001484339,0.0002966962,0.0003923,6.829562e-7,0.01375976,0.8922089,0.002383933,0.08640815],"study_design_scores_gemma":[0.002055763,0.0008327299,0.01102425,0.002390325,0.00005654746,0.000751756,0.00006212022,0.00006425487,0.001062011,0.9814175,0.0001349632,0.0001477479],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2450831,0.001347734,0.7505732,0.0001761527,0.0001856896,0.0005992572,0.00006102996,0.00001610856,0.001957806],"genre_scores_gemma":[0.8198214,0.0003071079,0.1796177,0.00009794741,0.00003744144,0.00001336906,0.000001360651,0.00002621757,0.0000775019],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5747383,"threshold_uncertainty_score":0.5591448,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140217706","doi":"10.1348/000711003321645412","title":"Pairwise multiple comparisons: A model comparison approach versus stepwise procedures","year":2003,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; York University","funders":"","keywords":"Pairwise comparison; Selection (genetic algorithm); Normality; Model selection; Multiple comparisons problem; Set (abstract data type); Variance (accounting); Mathematics; Statistics; Type I and type II errors; Computer science; Econometrics; Machine learning","authors":[{"name":"Robert A. Cribbie","is_ca":true},{"name":"H. J. Keselman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2715206547783738,"gpt":0.4866960714425734,"spread":0.2151754166641996,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004214033,0.0002199207,0.001033768,0.0001494682,0.0001521193,0.0002721469,0.0004868354,0.0001689518,0.0004544082],"category_scores_gemma":[0.01908389,0.0001808818,0.0001403566,0.0002566504,0.0006746527,0.000207851,0.0000668162,0.0005538597,0.00005319386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002603101,"about_ca_system_score_gemma":0.00008966122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002092263,"about_ca_topic_score_gemma":0.000002842764,"domain_scores_codex":[0.9951512,0.001102604,0.001776594,0.00046508,0.001087768,0.000416742],"domain_scores_gemma":[0.9930182,0.005416847,0.0004818027,0.0002563735,0.0003183979,0.0005084319],"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":[0.004841383,0.01062352,0.00290718,0.0002743962,0.0003540334,0.0008753542,0.001853881,0.00194995,0.001647909,0.6336246,0.2053784,0.1356693],"study_design_scores_gemma":[0.008575572,0.001771056,0.003664838,0.0001494341,0.0001291212,0.006980786,0.002424435,0.2827255,0.0001210897,0.6909167,0.001949166,0.000592271],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02812224,0.001523545,0.9566978,0.0001153947,0.0002180462,0.0002138967,0.00003849315,0.00001526223,0.01305528],"genre_scores_gemma":[0.4780823,0.00003499978,0.5216356,0.0001206705,0.00002226563,0.000006821894,9.648272e-7,0.00001272582,0.00008370102],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.44996,"threshold_uncertainty_score":0.9891788,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163998574","doi":"10.1111/j.2044-8317.2011.02017.x","title":"A note on consistency of non‐parametric rank tests and related rank transformations","year":2011,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":26,"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":"Wilcoxon signed-rank test; Mathematics; Rank (graph theory); Consistency (knowledge bases); Statistics; Null hypothesis; Nonparametric statistics; Mann–Whitney U test; Parametric statistics; Statistical hypothesis testing; Kruskal–Wallis one-way analysis of variance; Type I and type II errors; Sample size determination; Null (SQL); Statistical significance; Sample (material); Econometrics; Combinatorics; Computer science; Discrete mathematics; Data mining","authors":[{"name":"Donald W. Zimmerman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09940994877516365,"gpt":0.415083829253759,"spread":0.3156738804785953,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001079341,0.0001917483,0.000900699,0.0001760145,0.00009073275,0.00001922834,0.0001333083,0.0001833853,0.0005031403],"category_scores_gemma":[0.005662089,0.0001656039,0.00009735238,0.0001893716,0.0007150945,0.0001094537,0.00002379493,0.000515097,0.000006769956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008967532,"about_ca_system_score_gemma":0.00003008948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003515605,"about_ca_topic_score_gemma":0.000001932639,"domain_scores_codex":[0.9975039,0.000254724,0.001429639,0.0002285745,0.00028885,0.0002943158],"domain_scores_gemma":[0.9939669,0.004967004,0.000380935,0.0001526329,0.0002189096,0.0003136597],"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":[0.000332397,0.0009781779,0.00001512244,0.0004219414,0.00010198,0.0004446456,0.000702857,5.800098e-7,0.0001570909,0.8176208,0.0006896647,0.1785348],"study_design_scores_gemma":[0.002167864,0.001158754,0.003933717,0.0003941341,0.0001966281,0.005098411,0.00007279493,0.0008980073,0.00003919625,0.9858307,0.00003610124,0.0001736655],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03143396,0.0002861143,0.9536695,0.0001585404,0.0001024223,0.0002463028,0.0001379913,0.00001274521,0.01395243],"genre_scores_gemma":[0.4473913,0.0003388109,0.55211,0.00008956603,0.0000127092,0.000004797379,0.000001140283,0.0000173486,0.00003436114],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4159574,"threshold_uncertainty_score":0.6778459,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1899992665","doi":"10.1348/000711010x524739","title":"A simple and effective decision rule for choosing a significance test to protect against non‐normality","year":2010,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":24,"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":"Normality; Normality test; Statistics; Parametric statistics; Sample size determination; Wilcoxon signed-rank test; Statistical hypothesis testing; Mathematics; Test (biology); Type I and type II errors; Nominal level; Variance (accounting); Mann–Whitney U test; Sample (material); Computer science; Econometrics; Confidence interval","authors":[{"name":"Donald W. Zimmerman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0458017058659475,"gpt":0.4343341516830923,"spread":0.3885324458171447,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001848391,0.0002068823,0.0007654266,0.000070867,0.0001805584,0.00009355351,0.000149838,0.0001622814,0.00006809953],"category_scores_gemma":[0.02597378,0.000181689,0.00007388025,0.00009307203,0.0003321851,0.0001072593,0.00006693157,0.0006081511,0.000003152119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001284961,"about_ca_system_score_gemma":0.0000278204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002681957,"about_ca_topic_score_gemma":0.00001034897,"domain_scores_codex":[0.9979883,0.0001326389,0.0008584693,0.0003694622,0.0002455059,0.0004056476],"domain_scores_gemma":[0.9856138,0.01320817,0.0002306658,0.0001588405,0.0002770261,0.0005115313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004981589,0.0006882979,0.00007010957,0.0005166417,0.00004585614,0.0002103707,0.0001701706,0.000001640307,0.01104709,0.1253735,0.002053087,0.8593251],"study_design_scores_gemma":[0.001516622,0.0009154587,0.005106032,0.0002588656,0.00006344601,0.001349716,0.00003559737,0.00158288,0.0001847175,0.9882912,0.0004718755,0.000223593],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.156335,0.00003437297,0.8418872,0.0001864159,0.00009895011,0.0008804157,0.0002513674,0.00001284374,0.0003134247],"genre_scores_gemma":[0.2929356,0.00002032107,0.7065504,0.0002830146,0.00009875532,0.00007361299,0.00000135801,0.00002454524,0.00001248644],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8629177,"threshold_uncertainty_score":0.9822308,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1602526694","doi":"10.1111/j.2044-8317.2012.02052.x","title":"A unified approach to multiple‐set canonical correlation analysis and principal components analysis","year":2012,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre for Addiction and Mental Health; University of British Columbia; McGill University","funders":"","keywords":"Canonical correlation; Principal component analysis; Set (abstract data type); Data set; Variance (accounting); Reduction (mathematics); Mathematics; Data mining; Computer science; Function (biology); Data reduction; Canonical analysis; Variance reduction; Algorithm; Statistics","authors":[{"name":"Heungsun Hwang","is_ca":true},{"name":"Kwanghee Jung","is_ca":true},{"name":"Yoshio Takane","is_ca":true},{"name":"Todd S. Woodward","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08086236820783665,"gpt":0.3405298912365928,"spread":0.2596675230287562,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00151209,0.0001743256,0.0009505636,0.0001194729,0.0001605313,0.00009634143,0.0001539888,0.0001557533,0.0004805523],"category_scores_gemma":[0.001549235,0.00008986249,0.000214059,0.001041474,0.0002351777,0.0000960523,0.00006531326,0.0003233055,0.000008151392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001472526,"about_ca_system_score_gemma":0.000004168581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008348238,"about_ca_topic_score_gemma":0.00008569063,"domain_scores_codex":[0.9974174,0.0006387297,0.000862525,0.0003108786,0.0003574874,0.000412923],"domain_scores_gemma":[0.9961637,0.002632971,0.0002169606,0.00006858194,0.0001339935,0.0007837636],"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":[0.001290384,0.005572597,0.3525756,0.0001405915,0.01113696,0.0003234194,0.001068361,0.0002536275,0.007081889,0.162876,0.001375042,0.4563056],"study_design_scores_gemma":[0.0003293165,0.0002347161,0.979233,0.00001335855,0.002709393,0.0004919204,0.0001174748,0.00953219,0.000004082271,0.006693167,0.0004409469,0.0002004211],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6060721,0.0001557059,0.3927835,0.0001846261,0.00003724002,0.00008778317,0.0001518713,0.000007500777,0.000519686],"genre_scores_gemma":[0.9087799,0.00005021257,0.09067046,0.0002951094,0.0001018825,0.000004252649,0.00005939988,0.000001723069,0.00003706137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6266574,"threshold_uncertainty_score":0.526171,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3005846352","doi":"10.1111/bmsp.12201","title":"Can we disregard the whole model? Omnibus non‐inferiority testing for <i>R</i> <sup>2</sup> in multi‐variable linear regression and in ANOVA","year":2020,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":23,"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":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Statistics; Null hypothesis; Statistical hypothesis testing; Outcome (game theory); Type I and type II errors; Multiple comparisons problem; Linear regression; Bayesian probability; Econometrics; Regression analysis; Linear model; Analysis of variance; Statistical power; Variable (mathematics); Computer science; Mathematics","authors":[{"name":"Harlan Campbell","is_ca":true},{"name":"Daniël Lakens","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.165318622558917,"gpt":0.426819047784887,"spread":0.2615004252259699,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001257793,0.0002204607,0.0008596738,0.00005243011,0.0001102695,0.00005656452,0.0001889018,0.0001678937,0.00002393282],"category_scores_gemma":[0.01197699,0.0001638755,0.00004841247,0.0001807405,0.0003418073,0.0001015948,0.00009194956,0.0007532911,8.784371e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001884716,"about_ca_system_score_gemma":0.0000558266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008406578,"about_ca_topic_score_gemma":0.00001905501,"domain_scores_codex":[0.9976405,0.000243732,0.001096801,0.0003576941,0.0002245118,0.0004367938],"domain_scores_gemma":[0.9939352,0.005239261,0.0002255392,0.0001282022,0.0001523738,0.0003194236],"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":[0.002902598,0.003414985,0.001328936,0.005230795,0.000169641,0.002812699,0.00646618,0.005238076,0.002712563,0.5708261,0.00721154,0.3916859],"study_design_scores_gemma":[0.001751832,0.0002534718,0.0002333664,0.0004599893,0.00003285424,0.0005217418,0.0001520906,0.3989171,0.000004523253,0.5974704,0.0000718458,0.0001307998],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02607851,0.0002652103,0.9693604,0.00343314,0.0000296645,0.0004122155,0.000264293,0.00001087363,0.0001456993],"genre_scores_gemma":[0.1392683,0.0001182407,0.8598099,0.0006580291,0.00006566436,0.00002175357,0.000002699599,0.00002969851,0.00002569174],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.393679,"threshold_uncertainty_score":0.9963455,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1607630103","doi":"10.1348/2044-8317.002007","title":"Bootstrap standard error and confidence intervals for the correlations corrected for indirect range restriction","year":2010,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Confidence interval; Statistics; Standard error; Estimator; Range (aeronautics); Mathematics; Monte Carlo method; Correlation coefficient; Sample size determination; Correlation; Robust confidence intervals; CDF-based nonparametric confidence interval; Coverage probability","authors":[{"name":"Johnson Ching‐Hong Li","is_ca":true},{"name":"Wai Chan","is_ca":false},{"name":"Ying Cui","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1615129551479159,"gpt":0.4710917790123959,"spread":0.30957882386448,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001587004,0.0001484465,0.0005556982,0.00005305648,0.0002481313,0.00008193754,0.0001343949,0.0001545527,0.0001372747],"category_scores_gemma":[0.01630047,0.0001116245,0.00008426255,0.00006383653,0.0005422315,0.00009211854,0.00002584585,0.0005189563,7.054065e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007630063,"about_ca_system_score_gemma":0.00003360217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002174018,"about_ca_topic_score_gemma":0.00002425673,"domain_scores_codex":[0.998378,0.000139183,0.0007980482,0.0002252621,0.0001896989,0.0002697822],"domain_scores_gemma":[0.9806932,0.01831972,0.0003019432,0.0001228913,0.000362828,0.0001994825],"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":[0.0005280073,0.0001451093,0.00002290295,0.0001851943,0.00007662363,0.00002638709,0.0001389822,7.343164e-7,0.0002262502,0.8616517,0.00913268,0.1278655],"study_design_scores_gemma":[0.001601565,0.0007004386,0.001695846,0.0001341283,0.0002232455,0.00192872,0.0001036811,0.00388857,0.00001390272,0.9881351,0.001441041,0.0001337874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008925645,0.0002485835,0.9878895,0.0009386335,0.0004978946,0.0006443235,0.0006268467,0.00001632853,0.0002122368],"genre_scores_gemma":[0.1315961,0.0002372361,0.8675857,0.0002087459,0.0001681093,0.00007308464,0.000004615468,0.00002800363,0.00009839801],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1277317,"threshold_uncertainty_score":0.9919856,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2030349076","doi":"10.1348/000711005x66770","title":"Bootstrap scree tests: A Monte Carlo simulation and applications to published data","year":2006,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; Alberta Advanced Education","funders":"","keywords":"Parametric statistics; Statistics; Statistical hypothesis testing; Econometrics; Monte Carlo method; Eigenvalues and eigenvectors; Nonparametric statistics; Mathematics; Principal component analysis; Goodness of fit; Computer science","authors":[{"name":"Sungjin Hong","is_ca":false},{"name":"Stephen K. Mitchell","is_ca":true},{"name":"Richard A. Harshman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.199457742686795,"gpt":0.4912955240526531,"spread":0.2918377813658581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001117368,0.0001793538,0.0006091012,0.00009270786,0.0001215358,0.0001545334,0.0002933134,0.0001249689,0.00015795],"category_scores_gemma":[0.00458053,0.0001667152,0.00003488831,0.0001356881,0.000297075,0.0002529786,0.0001461541,0.0003588604,0.00000605013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000123976,"about_ca_system_score_gemma":0.00002341674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001277824,"about_ca_topic_score_gemma":0.00002687705,"domain_scores_codex":[0.9977215,0.0001721741,0.001034341,0.0004326471,0.0003142429,0.0003251275],"domain_scores_gemma":[0.9948506,0.00394322,0.0002363441,0.0003608141,0.0002405025,0.0003685073],"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":[0.0001089107,0.000597986,0.00004568534,0.0002192889,0.00004907809,0.0002253453,0.00003676695,0.0001253914,0.00005857851,0.7655237,0.01466478,0.2183445],"study_design_scores_gemma":[0.0007704309,0.0002200069,0.002481632,0.0001192422,0.000100281,0.001490304,0.00003320359,0.01118358,9.801537e-7,0.9798911,0.003521596,0.0001876543],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003968447,0.0003897751,0.9923837,0.0006829096,0.00004314963,0.0003570146,0.0005008126,0.00002349856,0.00165072],"genre_scores_gemma":[0.1827473,0.00004620891,0.8165381,0.0002868228,0.0002094628,0.0000177395,0.000009338545,0.00002777485,0.0001172639],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2181568,"threshold_uncertainty_score":0.6798447,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102817893","doi":"10.1111/j.2044-8317.2012.02056.x","title":"Robust tests of equivalence for <i>k</i> independent groups","year":2012,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"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":"Mathematics; Statistics; Equivalence (formal languages); Population; Null hypothesis; Analysis of variance; Psychology; Social psychology; Econometrics; Pure mathematics; Demography","authors":[{"name":"Andy Koh","is_ca":true},{"name":"Robert A. Cribbie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5007231631368919,"gpt":0.5401128261342657,"spread":0.03938966299737379,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006336575,0.000205383,0.001285321,0.00007892391,0.00006728344,0.00003209565,0.0003150935,0.0002588173,0.0006648179],"category_scores_gemma":[0.08847126,0.0001816212,0.0001922005,0.0001151529,0.0007060056,0.0001305868,0.00009068628,0.0005003466,0.000008325077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001882352,"about_ca_system_score_gemma":0.00003280396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001185318,"about_ca_topic_score_gemma":0.0000010576,"domain_scores_codex":[0.995901,0.0006022414,0.002186376,0.0002449968,0.0005120902,0.000553221],"domain_scores_gemma":[0.9496258,0.04858591,0.0007471517,0.0002059688,0.0003409711,0.0004941372],"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":[0.000397444,0.001859969,0.0004471022,0.0009773535,0.0001515798,0.00007962037,0.0001120695,3.80178e-7,0.0003249024,0.9262589,0.009860469,0.05953022],"study_design_scores_gemma":[0.001981612,0.0007948834,0.005816716,0.0003879865,0.0002452037,0.002870399,0.00005250881,0.00006091504,0.00007161372,0.9873152,0.0002126214,0.0001903794],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02971284,0.0005393483,0.9671225,0.000261302,0.0005650924,0.0003600419,0.000277937,0.00001400713,0.001146925],"genre_scores_gemma":[0.2187475,0.0001543319,0.7804552,0.0002068102,0.0003523307,0.00001424934,9.132922e-7,0.00003037492,0.0000383192],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1890346,"threshold_uncertainty_score":0.9192069,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2131040314","doi":"10.1348/000711000159178","title":"An examination of the robustness of the empirical Bayes and other approaches for testing main and interaction effects in repeated measures designs","year":2000,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Univariate; Multivariate statistics; Statistics; Mathematics; Covariance; Type I and type II errors; Estimator; Statistic; Multivariate analysis; Robustness (evolution); Bayes' theorem; Covariance matrix; Statistical hypothesis testing; Econometrics; Bayesian probability","authors":[{"name":"H. J. Keselman","is_ca":true},{"name":"Rhonda K. Kowalchuk","is_ca":true},{"name":"Robert J. Boik","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3734672765204762,"gpt":0.4522036593699145,"spread":0.07873638284943824,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001473542,0.0001049356,0.0004256776,0.00003500589,0.00006237291,0.00001944129,0.0001002893,0.00009242666,0.00002569751],"category_scores_gemma":[0.005612549,0.00006691324,0.00003449049,0.00009142747,0.0004409559,0.00006814574,0.00002028018,0.0002248045,4.270338e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008220813,"about_ca_system_score_gemma":0.00001340486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002806622,"about_ca_topic_score_gemma":0.00001008318,"domain_scores_codex":[0.9981372,0.0007334801,0.000649863,0.0001669691,0.0001675697,0.0001449204],"domain_scores_gemma":[0.9936742,0.005825086,0.0002392828,0.0001055418,0.0000833477,0.00007250412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002548526,0.000641129,0.0004470046,0.0008091056,0.00004017041,0.00001286224,0.0006672539,0.00008966957,0.0007726238,0.09132457,0.00005526314,0.9048855],"study_design_scores_gemma":[0.00114957,0.0004963211,0.04898228,0.000726842,0.00009879188,0.001315935,0.0001932164,0.03469735,0.000116284,0.912113,0.000009460363,0.0001010022],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3692119,0.00005725185,0.6302631,0.00006907749,0.00002330584,0.0002205942,0.00001891556,0.000002181453,0.0001336124],"genre_scores_gemma":[0.6312156,0.00001265504,0.3686903,0.00003627305,0.00001716857,0.000007878179,2.264126e-7,0.00001050918,0.000009429957],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9047845,"threshold_uncertainty_score":0.6719151,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2164006511","doi":"10.1348/000711008x299742","title":"A comparative study of robust tests for spread: Asymmetric trimming strategies","year":2008,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Trimming; Estimator; Mathematics; A priori and a posteriori; Statistics; Robustness (evolution); Type I and type II errors; Levene's test; F-test of equality of variances; Variance (accounting); Analysis of variance; Econometrics; Adaptive estimator; Statistical hypothesis testing; Computer science; Test statistic; Homogeneity (statistics)","authors":[{"name":"H. J. Keselman","is_ca":true},{"name":"Rand R. Wilcox","is_ca":false},{"name":"James Algina","is_ca":false},{"name":"Abdul Rahim Othman","is_ca":false},{"name":"Katherine Fradette","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2892882943145064,"gpt":0.4905955814410748,"spread":0.2013072871265684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009583969,0.0002002956,0.001300896,0.0001491469,0.0001395137,0.00002976167,0.000186104,0.0001083211,0.00007567165],"category_scores_gemma":[0.004571238,0.0001753806,0.0000955341,0.0001875141,0.0004626817,0.0001397133,0.00003938347,0.0003563648,0.000001362414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001202976,"about_ca_system_score_gemma":0.00005446839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005537907,"about_ca_topic_score_gemma":0.000008594166,"domain_scores_codex":[0.9973599,0.0003200707,0.001373597,0.0002714242,0.0003515609,0.0003233997],"domain_scores_gemma":[0.9893338,0.009372382,0.0004987294,0.0001466026,0.0004177899,0.0002306712],"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":[0.0009553787,0.008118179,0.00009989934,0.0007497601,0.0004215948,0.001160829,0.002950214,0.0000476106,0.000217964,0.9203968,0.006355725,0.05852604],"study_design_scores_gemma":[0.003344891,0.003243575,0.002605756,0.0001639266,0.0001877095,0.004173757,0.002319837,0.0009064999,0.00001807906,0.9827859,0.00005167057,0.000198437],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1519649,0.0002590418,0.8459667,0.00003461843,0.00007476944,0.0004388982,0.00009628,0.00001023188,0.001154562],"genre_scores_gemma":[0.4823058,0.00005400305,0.5175228,0.00002044956,0.00004118172,0.00001303677,0.000001020467,0.00001417593,0.00002755978],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3303409,"threshold_uncertainty_score":0.7151812,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1594740803","doi":"10.1111/j.2044-8317.2012.02038.x","title":"Evaluating the performance of different procedures for constructing confidence intervals for coefficient alpha: A simulation study","year":2012,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Confidence interval; Statistics; Reliability (semiconductor); Parametric statistics; Mathematics; Rubric; Robust confidence intervals; Population; Sample (material); CDF-based nonparametric confidence interval; Arithmetic; Medicine","authors":[{"name":"Ying Cui","is_ca":true},{"name":"Johnson Li","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5157300170116348,"gpt":0.571068175661356,"spread":0.05533815864972125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01315649,0.0001055956,0.0005789927,0.0001032135,0.0001640775,0.00008767207,0.0003217199,0.00005164213,0.00007753111],"category_scores_gemma":[0.170638,0.00006283245,0.00008894416,0.0001906855,0.0003060947,0.0001060816,0.00005887541,0.0001655392,7.407168e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008547442,"about_ca_system_score_gemma":0.00002388925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.522258e-7,"about_ca_topic_score_gemma":6.770212e-7,"domain_scores_codex":[0.996898,0.000522209,0.001496816,0.0001961745,0.0006051113,0.0002816896],"domain_scores_gemma":[0.9231047,0.07521234,0.0008126289,0.0001284454,0.0006350264,0.0001068399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001026193,0.001860829,0.03135046,0.0004255964,0.0001495085,0.000004996781,0.002102349,0.000443941,0.0006260576,0.0309036,0.0007271382,0.9303793],"study_design_scores_gemma":[0.005072211,0.01138059,0.2860393,0.0006926906,0.0003086374,0.002547823,0.006752347,0.2076899,0.00012781,0.4789921,0.00007283466,0.0003237718],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5396488,0.0002213925,0.4594357,0.00006876617,0.0002024445,0.0003662117,0.00001527828,0.000002304246,0.0000391711],"genre_scores_gemma":[0.9001005,0.00001138012,0.09968421,0.00006774196,0.00009662277,0.00002057283,3.488578e-7,0.000006210743,0.00001240467],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9300556,"threshold_uncertainty_score":0.8363481,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2942651266","doi":"10.1111/bmsp.12166","title":"Bayesian generalized structured component analysis","year":2019,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National University of Singapore","keywords":"Component (thermodynamics); Bayesian probability; Component analysis; Econometrics; Mathematics; Statistics; Computer science; Applied mathematics","authors":[{"name":"Ji Yeh Choi","is_ca":false},{"name":"Heungsun Hwang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0576921882517152,"gpt":0.4172079433688679,"spread":0.3595157551171527,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009310232,0.0002047494,0.001211902,0.0001525945,0.00006854827,0.00006277856,0.0002035965,0.0001506436,0.003235145],"category_scores_gemma":[0.001438272,0.0001770343,0.0001971559,0.0002197104,0.0002509925,0.00008478045,0.00005283467,0.0004543182,0.00001451467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001565356,"about_ca_system_score_gemma":0.00001973149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003690516,"about_ca_topic_score_gemma":0.000005560431,"domain_scores_codex":[0.9973703,0.0003995725,0.001138173,0.0003206944,0.00040035,0.0003709252],"domain_scores_gemma":[0.9964494,0.002419228,0.0003545098,0.0002197742,0.0001803975,0.0003766739],"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":[0.0001970107,0.000362774,0.0001652248,0.0001967384,0.0006717607,0.0004906046,0.00009102751,0.00002067256,0.0004203444,0.9432666,0.0018945,0.05222278],"study_design_scores_gemma":[0.001433004,0.0002878605,0.003135748,0.00006588927,0.0006000849,0.002018759,0.0000428908,0.005331385,0.00001208389,0.9865221,0.0003390686,0.0002110661],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06421437,0.0002291589,0.9331979,0.0002214032,0.0001584577,0.000175029,0.0001167733,0.00001634373,0.001670571],"genre_scores_gemma":[0.3263868,0.00008708128,0.6730499,0.0002534867,0.00005499025,0.000002773465,0.000005215849,0.0000204632,0.0001392451],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2621725,"threshold_uncertainty_score":0.997676,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005050546","doi":"10.1348/000711006x117853","title":"Robust step‐down tests for multivariate independent group designs","year":2006,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of Manitoba","funders":"University of Manitoba","keywords":"Statistics; Estimator; Mathematics; Truncated mean; Multivariate statistics; Covariance; Statistic; Type I and type II errors; Sample size determination; Analysis of covariance; Test statistic; Statistical hypothesis testing; Econometrics","authors":[{"name":"Lisa M. Lix","is_ca":true},{"name":"Rachel T. Fouladi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4820414490728596,"gpt":0.527100397187587,"spread":0.04505894811472749,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00522889,0.0003076511,0.001430897,0.0001115902,0.0001572869,0.0001405673,0.0003595657,0.0003775619,0.0007334144],"category_scores_gemma":[0.05433635,0.0002742636,0.000232682,0.0001344519,0.0006172802,0.0001037764,0.00008251043,0.000698933,0.00001748851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003883458,"about_ca_system_score_gemma":0.00004209709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001540608,"about_ca_topic_score_gemma":0.00001766188,"domain_scores_codex":[0.9948656,0.0009252586,0.002545219,0.0004815033,0.0005621338,0.0006202771],"domain_scores_gemma":[0.9453536,0.05296318,0.0006990146,0.0002382391,0.0003581796,0.0003878001],"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":[0.0005477358,0.001925156,0.00007355249,0.0004094517,0.0001457936,0.0006471434,0.00002205692,0.000002403588,0.0003665444,0.9056756,0.03101159,0.05917297],"study_design_scores_gemma":[0.004335063,0.001032063,0.00552369,0.000310455,0.0002724666,0.003096709,0.00002473929,0.0008163772,0.0000171588,0.9835989,0.0006644239,0.0003079244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005416574,0.0002065019,0.9910566,0.0004483973,0.0004727573,0.0006104599,0.0003600728,0.00003736297,0.001391301],"genre_scores_gemma":[0.04050319,0.00005387122,0.9583488,0.0002778457,0.0005638913,0.00003823973,0.000004551987,0.00005957143,0.0001501071],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07792331,"threshold_uncertainty_score":0.999971,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2330570680","doi":"10.1111/bmsp.12066","title":"Testing for negligible interaction: A coherent and robust approach","year":2016,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"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":"Categorical variable; Contrast (vision); Type I and type II errors; Normality; Econometrics; Homoscedasticity; Statistical hypothesis testing; Interaction; Homogeneity (statistics); Statistics; Variance (accounting); Null hypothesis; Statistical power; Bootstrapping (finance); Computer science; Mathematics; Heteroscedasticity; Artificial intelligence; Economics","authors":[{"name":"Robert A. Cribbie","is_ca":true},{"name":"Chantal Ragoonanan","is_ca":true},{"name":"Alyssa Counsell","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5714294779352754,"gpt":0.5466511481811501,"spread":0.02477832975412531,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002797637,0.0001850831,0.0009287995,0.00006483377,0.00009877985,0.00008291579,0.0001615387,0.0001790112,0.0003003588],"category_scores_gemma":[0.1023577,0.0001284457,0.00008885696,0.0000847003,0.0005926171,0.00009926138,0.00006856401,0.0003123405,0.000004980845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002024343,"about_ca_system_score_gemma":0.00002668246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001242778,"about_ca_topic_score_gemma":6.433167e-7,"domain_scores_codex":[0.9971574,0.0004485168,0.001443111,0.0003438561,0.0002589272,0.0003481665],"domain_scores_gemma":[0.934677,0.06414041,0.0004196568,0.0001357024,0.000288462,0.0003387903],"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":[0.0004346688,0.0007429902,0.0001199641,0.0005769439,0.0001420248,0.0001354318,0.00004158979,2.271585e-7,0.000404851,0.5404044,0.01208078,0.4449161],"study_design_scores_gemma":[0.002616023,0.0009522566,0.001103244,0.000581523,0.0001499324,0.006122453,0.00004476522,0.0003456028,0.00001613775,0.9875143,0.0003764794,0.0001773387],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009491453,0.0001526475,0.9866731,0.0007723316,0.0002510076,0.0003393302,0.0001285256,0.00002192866,0.002169722],"genre_scores_gemma":[0.02671371,0.0000795563,0.9725502,0.0002026122,0.0003021199,0.00002829801,4.234019e-7,0.0000306228,0.00009252826],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4471098,"threshold_uncertainty_score":0.9052035,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099457688","doi":"10.1111/bmsp.12015","title":"Evaluating clinical significance: Incorporating robust statistics with normative comparison tests","year":2013,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"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":"Statistics; Normative; Econometrics; Statistical hypothesis testing; Mathematics; Epistemology; Philosophy","authors":[{"name":"Katrina van Wieringen","is_ca":true},{"name":"Robert A. Cribbie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6101012297971987,"gpt":0.6102618176534461,"spread":0.0001605878562473961,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008745326,0.0004092379,0.002289513,0.0001127979,0.0002225252,0.0002669047,0.0004571406,0.0003574651,0.001810756],"category_scores_gemma":[0.115373,0.0003286546,0.0001394296,0.0002688788,0.001882453,0.0002555984,0.000133113,0.001767227,0.00009774339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004262259,"about_ca_system_score_gemma":0.0001590453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001404856,"about_ca_topic_score_gemma":0.00001054344,"domain_scores_codex":[0.989989,0.002990463,0.004742363,0.0005806143,0.001051345,0.0006461556],"domain_scores_gemma":[0.9140266,0.0816954,0.00199552,0.0003289632,0.001201414,0.0007521299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006887756,0.003091198,0.003508532,0.0008614534,0.0005616484,0.0009975286,0.000276813,0.00002304709,0.0001118841,0.4520267,0.0418581,0.4959943],"study_design_scores_gemma":[0.003100289,0.003383483,0.01303599,0.0006428364,0.0003226431,0.002351528,0.0002469734,0.007094473,0.00000884751,0.9693679,0.00003572528,0.0004093139],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04905751,0.0001173288,0.9475271,0.0004721711,0.0003462035,0.0007619636,0.0002091629,0.00004345259,0.001465145],"genre_scores_gemma":[0.09328864,0.00006195567,0.9056772,0.0004542693,0.0003506414,0.00004128045,0.000004271246,0.0000618045,0.00005994684],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5173412,"threshold_uncertainty_score":0.9999166,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2082983435","doi":"10.1111/bmsp.12001","title":"Consequences of choosing samples in hypothesis testing to ensure homogeneity of variance","year":2013,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"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":"Statistics; Mathematics; Homogeneity (statistics); F-test of equality of variances; Type I and type II errors; Sample size determination; Variance (accounting); Levene's test; Standard deviation; Population; Econometrics; Statistical hypothesis testing; Test statistic; Demography","authors":[{"name":"Donald W. Zimmerman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5089277066177947,"gpt":0.5105138001551611,"spread":0.001586093537366384,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003561287,0.0001738458,0.001470638,0.0001328011,0.00003596157,0.00003217835,0.0002954497,0.0001817033,0.0007082716],"category_scores_gemma":[0.2442217,0.0001558211,0.00009216076,0.0002956148,0.0009299186,0.00007190069,0.00007062525,0.000400723,0.000007600413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001566121,"about_ca_system_score_gemma":0.00005736703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007224587,"about_ca_topic_score_gemma":0.000008560138,"domain_scores_codex":[0.9955393,0.0009225098,0.002532024,0.0002719539,0.0003988297,0.0003353836],"domain_scores_gemma":[0.9180248,0.08037716,0.0006999263,0.000181565,0.0004496274,0.0002669466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003635877,0.002232744,0.004863988,0.001919833,0.0002342834,0.0004801627,0.0003407258,0.000005615622,0.02835537,0.4234866,0.002527706,0.5351893],"study_design_scores_gemma":[0.0007963313,0.0005000694,0.05117899,0.001043955,0.00006916356,0.0009971987,0.00006557255,0.00004961409,0.0007708415,0.9443818,0.000006032184,0.00014038],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4065748,0.0001585475,0.5909809,0.0005309901,0.0001204352,0.0003648617,0.0001889132,0.000008484204,0.001072053],"genre_scores_gemma":[0.3685066,0.00003842587,0.6312853,0.0001037181,0.00004078637,0.000006868792,1.025044e-7,0.00001295999,0.000005241133],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.535049,"threshold_uncertainty_score":0.7755077,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3047129708","doi":"10.1111/bmsp.12207","title":"A note on computing Louis’ observed information matrix identity for IRT and cognitive diagnostic models","year":2020,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"National Taiwan Normal University","keywords":"Latent variable; Latent variable model; Computer science; Representation (politics); Variable (mathematics); Identity matrix; Monte Carlo method; Flexibility (engineering); Algorithm; Matrix (chemical analysis); Mathematics; Algebraic number; Maximization; Applied mathematics; Theoretical computer science; Artificial intelligence; Mathematical optimization; Statistics; Eigenvalues and eigenvectors","authors":[{"name":"Chen‐Wei Liu","is_ca":false},{"name":"R. Philip Chalmers","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4207820878078694,"gpt":0.4914274748681893,"spread":0.07064538706031998,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003639545,0.0001277225,0.0006104057,0.0001330191,0.000145674,0.0004159762,0.0002556983,0.0001055355,0.00009519637],"category_scores_gemma":[0.2360558,0.0001047922,0.00007812697,0.0003229172,0.000234652,0.0004985028,0.000092309,0.0003320247,0.00001748949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006843668,"about_ca_system_score_gemma":0.00002077695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002646053,"about_ca_topic_score_gemma":7.102096e-7,"domain_scores_codex":[0.9972804,0.0003556787,0.001273337,0.0002513202,0.0005881586,0.000251155],"domain_scores_gemma":[0.926991,0.07170064,0.0004933927,0.00007191662,0.000432908,0.0003101235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005252109,0.0001940624,0.0007469518,0.0001844022,0.00005940609,0.0001970992,0.0007724484,0.0000658494,0.0000143739,0.1337892,0.00565555,0.8577954],"study_design_scores_gemma":[0.001886849,0.001059461,0.03649589,0.0002183169,0.00006065582,0.00120118,0.0003570449,0.04529993,0.000001873524,0.9130515,0.0002231223,0.0001441368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1133213,0.0003453153,0.8838493,0.001408683,0.0001587167,0.0002022232,0.0001256298,0.00001084064,0.0005779823],"genre_scores_gemma":[0.8197263,0.00009780025,0.1782214,0.001826286,0.0001100666,0.0000028822,0.000003064197,0.000007140416,0.000005045849],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8576513,"threshold_uncertainty_score":0.7703792,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2782608753","doi":"10.1111/bmsp.12126","title":"On the solution multiplicity of the Fleishman method and its impact in simulation studies","year":2018,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":9,"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":"Normality; Monte Carlo method; Multiplicity (mathematics); Population; Applied mathematics; Mathematics; Computer science; Algorithm; Statistics; Mathematical analysis","authors":[{"name":"Oscar L. Olvera Astivia","is_ca":true},{"name":"Bruno D. Zumbo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1375020765400967,"gpt":0.50524852138227,"spread":0.3677464448421734,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002129456,0.0001227651,0.0005015659,0.00004798772,0.0001113091,0.00002490326,0.0001438684,0.00008930782,0.0001595866],"category_scores_gemma":[0.01996999,0.00006760047,0.00005891853,0.0001285352,0.0005901477,0.00004690331,0.00006411057,0.0003532342,0.00000198586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001898886,"about_ca_system_score_gemma":0.00001722177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005169339,"about_ca_topic_score_gemma":0.00001162243,"domain_scores_codex":[0.9978802,0.0007941758,0.0007277288,0.0001568345,0.0002444014,0.0001966932],"domain_scores_gemma":[0.9847988,0.01446415,0.0002890029,0.0001185832,0.0002480071,0.00008141245],"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":[0.0001652957,0.0002838947,0.0001384112,0.0001440836,0.00007274168,0.00002608741,0.0004322468,0.000002117067,0.0002715659,0.9149533,0.0007605542,0.08274968],"study_design_scores_gemma":[0.0005108787,0.0004960934,0.02603459,0.000388792,0.00004924441,0.0004312401,0.00005813025,0.0120126,0.00006761352,0.9598728,0.000005429235,0.00007260974],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1880275,0.0001631152,0.8106396,0.0006150336,0.00007476724,0.0001713567,0.00003928446,0.000003174653,0.0002661773],"genre_scores_gemma":[0.8071162,0.00005389182,0.192613,0.0001536611,0.00004674695,0.000002883195,1.206299e-7,0.000007642574,0.000005948122],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6190886,"threshold_uncertainty_score":0.9882852,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4214686438","doi":"10.1111/bmsp.12269","title":"Reliability coefficients for multiple group item response theory models","year":2022,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Item response theory; Group (periodic table); Mathematics; Statistics; Econometrics; Reliability engineering; Psychology; Psychometrics; Engineering; Physics","authors":[{"name":"Björn Andersson","is_ca":false},{"name":"Hao Luo","is_ca":false},{"name":"Kseniia Marcq","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3057821453871747,"gpt":0.4634622157514617,"spread":0.157680070364287,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03522916,0.0001264905,0.0006549987,0.000241104,0.0003908334,0.0001259741,0.0006489491,0.00007528038,0.0007664826],"category_scores_gemma":[0.276087,0.0001032004,0.0001535407,0.0004838722,0.0003862845,0.0001176152,0.0002081888,0.0004804239,0.000004951632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003004739,"about_ca_system_score_gemma":0.00003440288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001867048,"about_ca_topic_score_gemma":3.976097e-7,"domain_scores_codex":[0.993342,0.003390525,0.001492911,0.0004355767,0.0009813923,0.0003575357],"domain_scores_gemma":[0.8488432,0.1499602,0.0004322104,0.0002394418,0.0003045209,0.0002204192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.009728293,0.001916321,0.00103793,0.0000604491,0.00006645095,0.0005000552,0.0004195643,0.000590894,0.0002491807,0.2258634,0.02972569,0.7298418],"study_design_scores_gemma":[0.001555067,0.001125391,0.01857813,0.00001986251,0.00002108507,0.003260338,0.0006468656,0.01862223,9.072709e-7,0.9520822,0.003968183,0.0001197397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2135176,0.0003832331,0.7843809,0.0003648262,0.0004600329,0.0001911009,0.0002330067,0.00001088875,0.0004583873],"genre_scores_gemma":[0.8021678,0.00002007177,0.1970024,0.0005429733,0.00005502924,0.00002136333,0.000002008625,0.00001287623,0.0001755064],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.729722,"threshold_uncertainty_score":0.9934346,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4384277172","doi":"10.1111/bmsp.12317","title":"Evaluating the performance of existing and novel equivalence tests for fit indices in structural equation modelling","year":2023,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"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":"Equivalence (formal languages); Mathematics; Monte Carlo method; Statistics; Sample size determination; Structural equation modeling; Statistical hypothesis testing; Goodness of fit; Applied mathematics; Discrete mathematics","authors":[{"name":"Nataly Beribisky","is_ca":true},{"name":"Robert A. Cribbie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.8160285585535664,"gpt":0.5966260124549783,"spread":0.2194025460985881,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01216777,0.00008411139,0.0004060855,0.000218131,0.0001362448,0.00009453848,0.0002829958,0.00006407997,0.00003279918],"category_scores_gemma":[0.0734489,0.00005670528,0.0000365296,0.0005801358,0.0002945911,0.0001381505,0.00007699458,0.0002394469,0.000001097744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006299519,"about_ca_system_score_gemma":0.00002146186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005031767,"about_ca_topic_score_gemma":0.000001417191,"domain_scores_codex":[0.9975231,0.0002505213,0.001191679,0.0002248846,0.0005697307,0.0002400333],"domain_scores_gemma":[0.9502944,0.0487599,0.0005361115,0.00009832848,0.000242726,0.00006857844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002339447,0.00007821571,0.0102213,0.0002664848,0.00002524,0.0000294592,0.0006891447,0.005330279,0.0007979454,0.04399235,0.0001956358,0.93814],"study_design_scores_gemma":[0.0005020238,0.0003964854,0.07313863,0.0001814572,0.00001036699,0.0005097189,0.0001988156,0.576131,0.000004095592,0.3488702,0.000006325629,0.0000508489],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.644032,0.0002142845,0.3552376,0.0002226876,0.00008612178,0.00009201142,0.00001677063,0.000003392664,0.00009516274],"genre_scores_gemma":[0.7977203,0.00008521797,0.2020741,0.00005138468,0.00004143378,0.000003857413,5.578423e-7,0.000004846984,0.00001833525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9380891,"threshold_uncertainty_score":0.9343559,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168460233","doi":"10.1348/000711009x480640","title":"Coping with stress through decisional control: Quantification of negotiating the environment","year":2010,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Coping (psychology); Negotiation; Cognition; Computer science; Cognitive psychology; Psychology; Hierarchy; Social psychology; Clinical psychology; Economics","authors":[{"name":"Matthew J. Shanahan","is_ca":true},{"name":"Richard W. J. Neufeld","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08798309826525118,"gpt":0.400923746680282,"spread":0.3129406484150308,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002485512,0.0001019802,0.0004671948,0.00005149435,0.0001309357,0.0001960971,0.0004309468,0.00009027479,0.000670554],"category_scores_gemma":[0.003320954,0.00006002966,0.00006402881,0.00008420364,0.0007114699,0.0001510999,0.0000442053,0.00044659,0.00002714002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000543368,"about_ca_system_score_gemma":0.0000294588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005723677,"about_ca_topic_score_gemma":0.000007090377,"domain_scores_codex":[0.997425,0.0001879155,0.001271892,0.0002365474,0.0007078394,0.0001708517],"domain_scores_gemma":[0.9920001,0.006737405,0.0006766202,0.0002473774,0.0002268465,0.0001116319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003601943,0.0008988484,0.002772106,0.00001675179,0.00006423061,0.0002246589,0.0002960812,0.0004832614,0.001077898,0.1678608,0.005115076,0.82083],"study_design_scores_gemma":[0.001356089,0.0004590786,0.03728488,0.0001071671,0.00006633944,0.003577301,0.0003102492,0.002623135,0.00002967381,0.9512377,0.002805575,0.0001428529],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4652283,0.0001080944,0.5333835,0.000712993,0.0001682602,0.00006636349,0.00006442812,0.000001887566,0.0002662363],"genre_scores_gemma":[0.9425409,0.00004589562,0.05712119,0.000211544,0.00005406551,0.000002130533,0.000001129868,0.000007997851,0.00001513716],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8206872,"threshold_uncertainty_score":0.7342096,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158319724","doi":"10.1348/000711002760554606","title":"The comparative sensitivity of ordinal multiple regression and least squares regression to departures from interval scaling","year":2002,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Decision-Making Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Mathematics; Statistics; Ordinal regression; Raw score; Ordinal data; Regression; Regression analysis; Discretization; Optimal distinctiveness theory; Scaling; Raw data; Ordinal Scale; Interval (graph theory); Psychology; Combinatorics","authors":[{"name":"Todd S. Woodward","is_ca":true},{"name":"Michael A. Hunter","is_ca":true},{"name":"Helena Kadlec","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05512543054606262,"gpt":0.3683629665918431,"spread":0.3132375360457805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007623474,0.0001302868,0.0004779966,0.00005781502,0.00017066,0.0001106744,0.0002749793,0.00007817714,0.00002184699],"category_scores_gemma":[0.002462618,0.00008474715,0.00004834768,0.00009712465,0.0003779436,0.0001598615,0.0002314603,0.0003283828,0.000003313189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001051175,"about_ca_system_score_gemma":0.000005911966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007709483,"about_ca_topic_score_gemma":0.00001508077,"domain_scores_codex":[0.9981751,0.0004241625,0.0006208196,0.0002556679,0.0003266609,0.000197628],"domain_scores_gemma":[0.993875,0.005290993,0.0002725547,0.0001921446,0.0001787233,0.0001905301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002963587,0.0003387501,0.0002714203,0.00002988382,0.00004142825,0.0009105601,0.0008631044,0.000006741225,0.002069283,0.03168704,0.01100029,0.9524851],"study_design_scores_gemma":[0.001224787,0.001048865,0.03129179,0.002773451,0.00003474486,0.009036914,0.0002430065,0.08217136,0.000981133,0.8698145,0.001053781,0.0003256922],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1569022,0.0008855255,0.8411169,0.0007932036,0.000086863,0.00008400347,0.00002316737,0.00001569838,0.00009240493],"genre_scores_gemma":[0.6669385,0.0001228244,0.3328022,0.00009478752,0.00002970083,0.000001365163,3.067673e-7,0.000004236921,0.000006052529],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9521595,"threshold_uncertainty_score":0.3455888,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4295077327","doi":"10.1111/bmsp.12285","title":"Ordinal state‐trait regression for intensive longitudinal data","year":2022,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Mental Health Research Topics","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Israel Science Foundation","keywords":"Ordinal regression; Trait; Statistics; Longitudinal data; Ordinal data; Econometrics; Regression; Regression analysis; Mathematics; Cross-sectional regression; State (computer science); Computer science; Data mining; Algorithm; Polynomial regression","authors":[{"name":"Prince P. Osei","is_ca":true},{"name":"Philip T. Reiss","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2205900365319809,"gpt":0.5017560123301307,"spread":0.2811659757981498,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002151302,0.0001426454,0.0005320127,0.0001088183,0.0003127472,0.00004503432,0.0006007825,0.00007135988,0.008000513],"category_scores_gemma":[0.001388672,0.0001332905,0.000059176,0.0001118752,0.0003915442,0.00009191438,0.0003768691,0.0009031639,0.00002124766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004618092,"about_ca_system_score_gemma":0.0000700634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002450168,"about_ca_topic_score_gemma":0.000008269028,"domain_scores_codex":[0.997128,0.000535579,0.0009061532,0.0004192733,0.0004798265,0.0005312422],"domain_scores_gemma":[0.9971517,0.001553545,0.0002889748,0.0003269267,0.0002769136,0.0004018845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003054465,0.001535826,0.0004625206,0.0003779924,0.000221331,0.005458528,0.0006399578,8.338421e-7,0.00006509053,0.1054177,0.4301212,0.4526445],"study_design_scores_gemma":[0.008875254,0.008685227,0.05885153,0.0003491791,0.0001721496,0.1030754,0.002825205,0.001086398,0.000005014611,0.7106175,0.1049213,0.0005358261],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2259894,0.005376738,0.738993,0.01023286,0.003049611,0.001596569,0.007553411,0.0000384864,0.007169859],"genre_scores_gemma":[0.8791481,0.0003979472,0.1089811,0.005173648,0.0008456846,0.0002009894,0.000385075,0.000123464,0.004743984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6531587,"threshold_uncertainty_score":0.9929063,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1514964987","doi":"10.1348/000711010x501671","title":"Power comparisons of significance tests of location using scores, ranks, and modular ranks","year":2010,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":2,"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":"Wilcoxon signed-rank test; Mathematics; Statistics; Type I and type II errors; Rank (graph theory); Mann–Whitney U test; Nominal level; Statistical power; Nonparametric statistics; Test (biology); Statistical hypothesis testing; Sign test; Sample size determination; Power (physics); Modular design; Parametric statistics; Combinatorics; Computer science; Confidence interval","authors":[{"name":"Donald W. Zimmerman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08637119769436002,"gpt":0.432115604703706,"spread":0.3457444070093459,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001177035,0.0001601677,0.000909385,0.00007808576,0.00005778163,0.00002030474,0.0001471993,0.0001780671,0.0002265711],"category_scores_gemma":[0.005825731,0.0001466225,0.00005716272,0.0001083598,0.001034123,0.00009112769,0.00004461384,0.0005777927,5.820273e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000549041,"about_ca_system_score_gemma":0.00004302371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000691289,"about_ca_topic_score_gemma":0.000007132178,"domain_scores_codex":[0.9977846,0.0002216368,0.00122304,0.0002239644,0.0003061306,0.0002406486],"domain_scores_gemma":[0.9950657,0.003568798,0.0005480399,0.0001758955,0.0004105026,0.0002310166],"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":[0.000350938,0.0009779972,0.0002225855,0.000888935,0.00009686107,0.0001356558,0.0001957628,0.00001397409,0.0233448,0.9414812,0.000650754,0.03164059],"study_design_scores_gemma":[0.001309426,0.0003970408,0.007582471,0.0003961161,0.0001250411,0.002196559,0.00006160243,0.004025255,0.0002103667,0.9834825,0.0000542931,0.0001592799],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2376797,0.0003626106,0.761309,0.0000559775,0.00009764062,0.0001433231,0.00009378497,0.000004754334,0.0002532292],"genre_scores_gemma":[0.501865,0.00005416942,0.4980193,0.00002251825,0.00001941448,0.000001382801,6.761575e-7,0.0000120417,0.000005487409],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2641854,"threshold_uncertainty_score":0.6974366,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3147659269","doi":"10.1111/bmsp.12240","title":"Model‐based recursive partitioning of extended redundancy analysis with an application to nicotine dependence among US adults","year":2021,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; University of Manitoba","funders":"","keywords":"Covariate; Recursive partitioning; Partition (number theory); Econometrics; Statistics; Mathematics; Hierarchy; Set (abstract data type); Redundancy (engineering); Computer science; Combinatorics","authors":[{"name":"Sunmee Kim","is_ca":true},{"name":"Heungsun Hwang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02750667536499382,"gpt":0.324438908424291,"spread":0.2969322330592972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005924202,0.0001253562,0.0006239907,0.00003857484,0.0001031534,0.00005556364,0.0001471133,0.00009354018,0.0005439626],"category_scores_gemma":[0.0009320911,0.00006625415,0.0001051899,0.0005782265,0.0002328246,0.00008854661,0.00002155183,0.0002117539,0.000001950297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009057609,"about_ca_system_score_gemma":0.0000166939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000342123,"about_ca_topic_score_gemma":0.0005061214,"domain_scores_codex":[0.9979915,0.0003775009,0.0007226092,0.0003468932,0.0003334686,0.0002280063],"domain_scores_gemma":[0.9977866,0.0009510708,0.0002842805,0.00008783316,0.0005276961,0.0003624543],"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":[0.002577314,0.004390534,0.01382222,0.0002128041,0.001018871,0.001194134,0.0002923136,0.00330396,0.02554749,0.1047406,0.0002924788,0.8426073],"study_design_scores_gemma":[0.001076546,0.003031527,0.6467252,0.0004138086,0.0012897,0.0009928105,0.0004051517,0.1157966,0.00107808,0.2286991,0.00004192309,0.0004495137],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5075119,0.00005675423,0.4919217,0.0002207969,0.000008327047,0.00005671725,0.00009315005,0.000004381336,0.0001262929],"genre_scores_gemma":[0.7728654,0.00002647053,0.2268145,0.000211705,0.00003003305,0.000005853806,0.00003202291,0.000001571352,0.00001253859],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8421578,"threshold_uncertainty_score":0.5956009,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4281689061","doi":"10.1111/bmsp.12274","title":"Theoretical considerations when simulating data from the <i>g</i> ‐and‐ <i>h</i> family of distributions","year":2022,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":1,"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":"Kurtosis; Skewness; Copula (linguistics); Multivariate statistics; Marginal distribution; Mathematics; Generalization; Multivariate normal distribution; Population; Gaussian; Statistics; Statistical physics; Applied mathematics; Econometrics; Random variable; Mathematical analysis; Physics","authors":[{"name":"Oscar L. Olvera Astivia","is_ca":false},{"name":"Edward Kroc","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1119805846752673,"gpt":0.3920424655277526,"spread":0.2800618808524853,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001195649,0.0001227592,0.0004321793,0.00002491052,0.0004786861,0.00006810682,0.0003273849,0.00005449867,0.004725117],"category_scores_gemma":[0.007914994,0.0001025955,0.0000473578,0.000101032,0.001190084,0.00007709351,0.0003297313,0.0005145433,0.000004187395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001567966,"about_ca_system_score_gemma":0.00006214566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001206713,"about_ca_topic_score_gemma":0.0000036959,"domain_scores_codex":[0.9976533,0.0004667352,0.001043301,0.0002463828,0.0003951995,0.0001951032],"domain_scores_gemma":[0.9858381,0.01315192,0.0003353537,0.0003318133,0.0001748965,0.000167878],"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":[0.00002593416,0.000333353,0.00002648699,0.00002005312,0.00005150273,0.00003583209,0.0001017898,0.000001960159,0.00007262341,0.9631267,0.03182622,0.004377498],"study_design_scores_gemma":[0.0006989838,0.0001043411,0.003188281,0.00004416547,0.0001669108,0.001276007,0.0002994162,0.007196748,0.000003031525,0.9861041,0.0008142773,0.0001036885],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01890794,0.0004279623,0.9633988,0.004988461,0.00007478095,0.0002168269,0.01073226,0.0000163548,0.001236668],"genre_scores_gemma":[0.8890314,0.00004817618,0.1098599,0.0008197756,0.00004825668,0.00001458041,0.0001606498,0.00001197959,0.000005349073],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8701234,"threshold_uncertainty_score":0.9961847,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7117121226","doi":"10.1111/bmsp.70025","title":"Power priors for latent variable mediation models under small sample sizes","year":2025,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Prior probability; Univariate; Bayesian probability; Sample size determination; Latent variable; Variable (mathematics); Bayes' theorem","authors":[{"name":"Lihan Chen","is_ca":true},{"name":"Milica Miočević","is_ca":true},{"name":"Carl F. Falk","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07205106244704894,"gpt":0.3891975518028085,"spread":0.3171464893557596,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001306623,0.0001705906,0.0006939197,0.00009287399,0.0001124226,0.00009542493,0.0001860484,0.0001871212,0.000627691],"category_scores_gemma":[0.01033486,0.0001510194,0.00009542099,0.0001383253,0.0002585037,0.00008080862,0.00004592323,0.0003186958,0.000002459586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002620123,"about_ca_system_score_gemma":0.00008473868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005381235,"about_ca_topic_score_gemma":0.000003810697,"domain_scores_codex":[0.9979483,0.000216674,0.001022152,0.0002560014,0.0002102703,0.0003465882],"domain_scores_gemma":[0.9867535,0.01229415,0.0002384247,0.0001373964,0.0003763793,0.0002001565],"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":[0.0001254141,0.0003525837,0.00001215783,0.0002670368,0.0001082182,0.00002679315,0.00005031504,0.000001689369,0.00005336015,0.944262,0.004830384,0.04991001],"study_design_scores_gemma":[0.001240967,0.0003225267,0.0008254597,0.0002857805,0.0001418166,0.0003651535,0.00005407468,0.003372921,0.000007067762,0.9929204,0.000311416,0.0001523901],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00125349,0.0002475773,0.9940798,0.0008623687,0.0002638075,0.0002774176,0.0002456154,0.00001824569,0.002751729],"genre_scores_gemma":[0.01973904,0.0001058727,0.9793271,0.0006547036,0.00005312152,0.00001993727,0.000004919064,0.00001873446,0.00007653271],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04975762,"threshold_uncertainty_score":0.9980015,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406715877","doi":"10.1111/bmsp.12381","title":"Efficient and accurate variational inference for multilevel threshold autoregressive models in intensive longitudinal data","year":2025,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Markov chain Monte Carlo; Inference; Autoregressive model; Bayes' theorem; Bayesian inference; Bayesian probability; Computer science; Algorithm; Data set; Mathematics; Statistics; Artificial intelligence","authors":[{"name":"Azizur Rahman","is_ca":true},{"name":"Depeng Jiang","is_ca":true},{"name":"Lisa M. Lix","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1796597795581923,"gpt":0.4642400169581189,"spread":0.2845802373999267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001301478,0.0001788427,0.0007071114,0.0001319904,0.00008720872,0.00009430272,0.0003010297,0.0001490789,0.0000807877],"category_scores_gemma":[0.01648399,0.000156147,0.00003617018,0.00009017577,0.0004543497,0.00009493165,0.0001925785,0.0004233374,9.404592e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002063004,"about_ca_system_score_gemma":0.00009050523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006017726,"about_ca_topic_score_gemma":0.000008873111,"domain_scores_codex":[0.9979059,0.00016379,0.001005652,0.0003968276,0.0002201668,0.0003076335],"domain_scores_gemma":[0.9892571,0.009638645,0.000259283,0.0002082885,0.0004762316,0.0001604536],"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":[0.0001920574,0.0002983576,0.0001041969,0.0002806101,0.00006038354,0.0002132944,0.0001168046,0.00001005683,0.00001455894,0.9397982,0.001523653,0.0573878],"study_design_scores_gemma":[0.001255043,0.0001210996,0.01014131,0.000589388,0.0000729036,0.0006662227,0.00005865233,0.2443217,0.000001446526,0.7426453,0.00001284581,0.0001141202],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006779263,0.0003127509,0.990706,0.0007119462,0.0001453151,0.0002848695,0.0005765618,0.000006903215,0.0004763585],"genre_scores_gemma":[0.2657731,0.00008013138,0.7338138,0.0002430769,0.00003738148,0.00001503357,0.000008341598,0.00001067499,0.00001839153],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2589939,"threshold_uncertainty_score":0.9918006,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}