{"meta":{"query_hash":"7fae06dd8c7e","filters":{"venue":"British Journal of Mathematical and Statistical Psychology"},"cohort_total":45,"direct_labels_cover":0,"predictions_cover":45,"exported":45,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/7fae06dd8c7e","api":"https://metacan.xera.ac/api/v1/cohort?venue=British+Journal+of+Mathematical+and+Statistical+Psychology"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08637119769436002,"score_gpt":0.43211560470370597,"score_spread":0.34574440700934594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514964987","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23767966,0.00036261065,0.761309,0.0000559775,0.00009764062,0.00014332306,0.00009378497,0.0000047543344,0.00025322923],"genre_scores_gemma":[0.501865,0.00005416942,0.4980193,0.000022518252,0.00001941448,0.000001382801,6.761575e-7,0.000012041701,0.000005487409],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99778455,0.00022163682,0.0012230402,0.00022396441,0.00030613065,0.00024064856],"domain_scores_gemma":[0.99506575,0.0035687976,0.00054803985,0.00017589546,0.0004105026,0.00023101657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011770352,0.00016016768,0.000909385,0.00007808576,0.00005778163,0.000020304737,0.00014719927,0.00017806714,0.00022657108],"category_scores_gemma":[0.0058257314,0.00014662246,0.000057162717,0.000108359774,0.0010341234,0.000091127695,0.00004461384,0.0005777927,5.8202727e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035093803,0.0009779972,0.00022258548,0.000888935,0.00009686107,0.0001356558,0.00019576275,0.000013974092,0.023344804,0.9414812,0.000650754,0.031640586],"study_design_scores_gemma":[0.001309426,0.00039704083,0.0075824712,0.00039611608,0.00012504112,0.0021965594,0.00006160243,0.0040252553,0.0002103667,0.98348254,0.000054293097,0.0001592799],"about_ca_topic_score_codex":0.00000691289,"about_ca_topic_score_gemma":0.0000071321783,"teacher_disagreement_score":0.26418537,"about_ca_system_score_codex":0.0000054904103,"about_ca_system_score_gemma":0.00004302371,"threshold_uncertainty_score":0.6974366},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.3136864516944847,"score_gpt":0.4807478002530468,"score_spread":0.16706134855856208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1561373080","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023747214,0.43739495,0.5608176,0.000021773325,0.00010434134,0.00023617945,0.0011990705,0.0000064060873,0.0002173134],"genre_scores_gemma":[0.000022477621,0.55207866,0.44760436,0.000012754824,0.00012326769,0.000008871667,0.000026966918,0.000050333427,0.00007232333],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99517095,0.00060522807,0.002494203,0.00043383543,0.0006538849,0.000641894],"domain_scores_gemma":[0.9697126,0.027322883,0.001457424,0.0007076876,0.0003547815,0.00044462798],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027346015,0.00046157307,0.0028519966,0.00007957781,0.00020938474,0.000081547194,0.0009941289,0.00032156843,0.00017787714],"category_scores_gemma":[0.007277373,0.00027533987,0.00011412856,0.0001864147,0.0013915619,0.0001533887,0.00027920728,0.0013556688,0.000009877515],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043487573,0.00042356088,0.0000013691832,0.0077698813,0.0001753413,0.00023090062,0.000013291737,1.7563485e-7,7.122863e-8,0.2253191,0.003222236,0.7628006],"study_design_scores_gemma":[0.00093957107,0.0017052864,0.000026186626,0.0074304356,0.00421172,0.03274582,0.000038397466,0.0007521479,1.5542295e-7,0.6978435,0.253631,0.00067580695],"about_ca_topic_score_codex":0.0000019128531,"about_ca_topic_score_gemma":0.0000054723005,"teacher_disagreement_score":0.7621248,"about_ca_system_score_codex":0.000027291551,"about_ca_system_score_gemma":0.00018415727,"threshold_uncertainty_score":0.9999699},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.4357774667779384,"score_gpt":0.5329337513487912,"score_spread":0.09715628457085279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1572657933","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028451428,0.00004363883,0.9671117,0.00005918967,0.000349489,0.0007620359,0.0013045676,0.00001734825,0.0019006036],"genre_scores_gemma":[0.21534178,0.00007459577,0.7841613,0.00014768264,0.00015654271,0.00003278505,0.0000029546015,0.000047595964,0.00003473833],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99431026,0.0013699055,0.0027064723,0.00042305392,0.00065723713,0.0005330935],"domain_scores_gemma":[0.88555586,0.1124012,0.000915735,0.0002933421,0.0003873402,0.00044653128],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009202754,0.00033154697,0.0019648215,0.00012182138,0.000100401245,0.00004057855,0.00042054214,0.00036222025,0.0011151247],"category_scores_gemma":[0.13245636,0.0002834386,0.00022535802,0.00012353693,0.0008919203,0.00007332848,0.00008069435,0.00076653546,0.000017510632],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038759273,0.0045464817,0.00043405185,0.0027256452,0.00039004214,0.00055518595,0.00022097019,2.1508338e-7,0.0003245818,0.79152846,0.0075644185,0.187834],"study_design_scores_gemma":[0.004247807,0.012894307,0.00704985,0.0005756752,0.00054211356,0.0009003656,0.000020296597,0.00020272298,0.00089997455,0.97237486,0.00002164644,0.00027037048],"about_ca_topic_score_codex":0.000005134364,"about_ca_topic_score_gemma":0.0000028400498,"teacher_disagreement_score":0.18756361,"about_ca_system_score_codex":0.000031126565,"about_ca_system_score_gemma":0.000043762255,"threshold_uncertainty_score":0.9999618},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5157300170116348,"score_gpt":0.571068175661356,"score_spread":0.05533815864972125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594740803","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5396488,0.00022139246,0.45943567,0.000068766174,0.00020244447,0.00036621167,0.000015278278,0.0000023042462,0.000039171104],"genre_scores_gemma":[0.9001005,0.000011380122,0.09968421,0.00006774196,0.000096622774,0.00002057283,3.4885775e-7,0.000006210743,0.000012404669],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996898,0.00052220904,0.0014968163,0.00019617451,0.0006051113,0.00028168963],"domain_scores_gemma":[0.9231047,0.075212345,0.0008126289,0.0001284454,0.0006350264,0.000106839885],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013156486,0.000105595616,0.00057899265,0.00010321355,0.0001640775,0.00008767207,0.0003217199,0.00005164213,0.000077531105],"category_scores_gemma":[0.17063797,0.00006283245,0.00008894416,0.0001906855,0.0003060947,0.00010608156,0.000058875412,0.00016553917,7.407168e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010261927,0.001860829,0.03135046,0.00042559643,0.0001495085,0.000004996781,0.0021023492,0.00044394104,0.0006260576,0.030903604,0.00072713825,0.93037933],"study_design_scores_gemma":[0.005072211,0.011380591,0.28603932,0.0006926906,0.0003086374,0.0025478234,0.006752347,0.20768985,0.00012780997,0.4789921,0.000072834664,0.00032377185],"about_ca_topic_score_codex":7.522258e-7,"about_ca_topic_score_gemma":6.770212e-7,"teacher_disagreement_score":0.93005556,"about_ca_system_score_codex":0.000008547442,"about_ca_system_score_gemma":0.000023889246,"threshold_uncertainty_score":0.8363481},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08086236820783665,"score_gpt":0.34052989123659283,"score_spread":0.2596675230287562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1602526694","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60607207,0.00015570587,0.39278352,0.00018462611,0.000037240017,0.00008778317,0.00015187133,0.0000075007774,0.00051968603],"genre_scores_gemma":[0.9087799,0.000050212566,0.09067046,0.0002951094,0.000101882455,0.0000042526494,0.00005939988,0.0000017230694,0.000037061374],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99741745,0.00063872966,0.000862525,0.00031087862,0.00035748744,0.00041292302],"domain_scores_gemma":[0.9961637,0.0026329707,0.00021696062,0.00006858194,0.00013399353,0.0007837636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015120903,0.00017432561,0.0009505636,0.00011947286,0.00016053127,0.000096341435,0.00015398883,0.00015575327,0.0004805523],"category_scores_gemma":[0.0015492348,0.000089862486,0.000214059,0.0010414739,0.00023517768,0.0000960523,0.00006531326,0.0003233055,0.000008151392],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001290384,0.005572597,0.35257557,0.00014059151,0.0111369565,0.00032341937,0.0010683615,0.00025362754,0.0070818886,0.16287598,0.0013750424,0.45630556],"study_design_scores_gemma":[0.0003293165,0.00023471615,0.979233,0.000013358553,0.0027093932,0.0004919204,0.00011747477,0.00953219,0.000004082271,0.0066931667,0.0004409469,0.00020042111],"about_ca_topic_score_codex":0.00008348238,"about_ca_topic_score_gemma":0.00008569063,"teacher_disagreement_score":0.6266574,"about_ca_system_score_codex":0.00001472526,"about_ca_system_score_gemma":0.0000041685807,"threshold_uncertainty_score":0.526171},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16151295514791586,"score_gpt":0.47109177901239585,"score_spread":0.30957882386448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1607630103","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008925645,0.00024858353,0.9878895,0.0009386335,0.0004978946,0.00064432353,0.0006268467,0.000016328531,0.00021223676],"genre_scores_gemma":[0.13159606,0.00023723613,0.8675857,0.00020874586,0.0001681093,0.00007308464,0.0000046154682,0.000028003631,0.00009839801],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99837804,0.00013918299,0.0007980482,0.00022526213,0.00018969891,0.0002697822],"domain_scores_gemma":[0.98069316,0.01831972,0.00030194325,0.00012289132,0.00036282797,0.00019948254],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015870042,0.00014844655,0.00055569824,0.000053056476,0.00024813128,0.00008193754,0.00013439485,0.00015455266,0.00013727468],"category_scores_gemma":[0.016300471,0.000111624526,0.00008426255,0.00006383653,0.0005422315,0.00009211854,0.000025845853,0.0005189563,7.054065e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052800734,0.00014510928,0.000022902947,0.00018519434,0.000076623626,0.000026387086,0.00013898223,7.3431636e-7,0.00022625015,0.86165166,0.0091326805,0.12786548],"study_design_scores_gemma":[0.0016015646,0.0007004386,0.0016958461,0.00013412835,0.00022324552,0.0019287198,0.00010368107,0.0038885698,0.000013902715,0.9881351,0.0014410415,0.00013378735],"about_ca_topic_score_codex":0.000002174018,"about_ca_topic_score_gemma":0.000024256735,"teacher_disagreement_score":0.1277317,"about_ca_system_score_codex":0.000007630063,"about_ca_system_score_gemma":0.00003360217,"threshold_uncertainty_score":0.9919856},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0458017058659475,"score_gpt":0.43433415168309225,"score_spread":0.38853244581714474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1899992665","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15633497,0.00003437297,0.84188724,0.00018641588,0.000098950106,0.00088041567,0.0002513674,0.000012843743,0.00031342465],"genre_scores_gemma":[0.29293555,0.00002032107,0.70655036,0.00028301455,0.00009875532,0.00007361299,0.0000013580095,0.000024545241,0.000012486438],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979883,0.00013263887,0.00085846934,0.0003694622,0.00024550594,0.0004056476],"domain_scores_gemma":[0.98561376,0.0132081695,0.00023066581,0.00015884054,0.0002770261,0.00051153125],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018483908,0.0002068823,0.0007654266,0.000070867005,0.00018055836,0.00009355351,0.000149838,0.00016228139,0.00006809953],"category_scores_gemma":[0.025973782,0.00018168899,0.00007388025,0.000093072034,0.00033218513,0.00010725927,0.00006693157,0.0006081511,0.000003152119],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004981589,0.0006882979,0.00007010957,0.0005166417,0.00004585614,0.00021037068,0.00017017059,0.0000016403069,0.011047088,0.12537353,0.002053087,0.85932505],"study_design_scores_gemma":[0.0015166223,0.0009154587,0.005106032,0.00025886556,0.00006344601,0.001349716,0.000035597368,0.0015828796,0.00018471749,0.9882912,0.00047187548,0.00022359297],"about_ca_topic_score_codex":0.000002681957,"about_ca_topic_score_gemma":0.000010348968,"teacher_disagreement_score":0.86291766,"about_ca_system_score_codex":0.0000128496085,"about_ca_system_score_gemma":0.000027820399,"threshold_uncertainty_score":0.98223084},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06871545134842222,"score_gpt":0.37757502735672843,"score_spread":0.3088595760083062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968781945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019762507,0.00009641221,0.9752021,0.003316591,0.00006224445,0.0005787821,0.0008208869,0.000022372584,0.00013811611],"genre_scores_gemma":[0.6473719,0.00003586063,0.35170686,0.0005227529,0.000099240795,0.00013152565,0.000044147997,0.000028479455,0.00005924086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99797225,0.00021980451,0.00080287096,0.00026096983,0.00037921162,0.00036487012],"domain_scores_gemma":[0.98913366,0.009694293,0.00032284862,0.00022774575,0.0004107977,0.00021066013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009598563,0.00020755689,0.00046829155,0.000029173512,0.00062490324,0.00012476332,0.00027900157,0.000103640436,0.000264031],"category_scores_gemma":[0.0035753655,0.00011432313,0.0001117146,0.0001925386,0.0010125099,0.000085870146,0.000031488737,0.00041518014,0.000012680235],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034691227,0.0006746417,0.0001496542,0.000096275275,0.00019799419,0.00012958205,0.00037629585,0.000009582523,0.000019435494,0.95039433,0.02166427,0.025941042],"study_design_scores_gemma":[0.0021038535,0.0008208564,0.034344282,0.000146845,0.000383274,0.010333479,0.000119003686,0.029807754,0.00002927746,0.92061365,0.0010340232,0.0002637337],"about_ca_topic_score_codex":0.0000064665023,"about_ca_topic_score_gemma":0.000007219767,"teacher_disagreement_score":0.6276094,"about_ca_system_score_codex":0.000025656811,"about_ca_system_score_gemma":0.000057112644,"threshold_uncertainty_score":0.48063138},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.48204144907285956,"score_gpt":0.527100397187587,"score_spread":0.04505894811472749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005050546","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005416574,0.00020650192,0.99105656,0.00044839727,0.00047275733,0.0006104599,0.00036007282,0.000037362974,0.0013913013],"genre_scores_gemma":[0.040503185,0.00005387122,0.95834875,0.0002778457,0.0005638913,0.000038239727,0.0000045519873,0.00005957143,0.00015010714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948656,0.00092525856,0.0025452187,0.00048150335,0.00056213385,0.0006202771],"domain_scores_gemma":[0.94535357,0.05296318,0.00069901464,0.00023823911,0.0003581796,0.00038780007],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0052288896,0.00030765106,0.0014308968,0.00011159025,0.00015728691,0.00014056725,0.00035956575,0.00037756193,0.00073341443],"category_scores_gemma":[0.054336347,0.00027426358,0.00023268201,0.00013445188,0.0006172802,0.00010377637,0.00008251043,0.00069893297,0.000017488514],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054773584,0.0019251565,0.00007355249,0.0004094517,0.00014579357,0.0006471434,0.000022056922,0.000002403588,0.00036654435,0.9056756,0.031011585,0.059172966],"study_design_scores_gemma":[0.0043350626,0.0010320626,0.00552369,0.00031045504,0.00027246663,0.0030967095,0.000024739285,0.00081637717,0.000017158802,0.98359895,0.00066442386,0.00030792443],"about_ca_topic_score_codex":0.00001540608,"about_ca_topic_score_gemma":0.000017661878,"teacher_disagreement_score":0.07792331,"about_ca_system_score_codex":0.00003883458,"about_ca_system_score_gemma":0.00004209709,"threshold_uncertainty_score":0.999971},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.15745614856899287,"score_gpt":0.4242876479967463,"score_spread":0.2668314994277534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006005214","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024928784,0.0005463235,0.96257204,0.0013077715,0.000115137176,0.00023657124,0.00014130381,0.000040649647,0.0101114],"genre_scores_gemma":[0.11567369,0.0012816769,0.8809108,0.00081019866,0.00026607525,0.0000051734983,0.0000063499,0.000057280384,0.0009887149],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967886,0.0004131111,0.0014386019,0.0004346429,0.00046429917,0.00046073348],"domain_scores_gemma":[0.99496084,0.003808065,0.000268233,0.00021704401,0.00013027489,0.00061551196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014709806,0.00026823624,0.0010724216,0.000091009366,0.00014616559,0.0000873429,0.00018048173,0.0001802537,0.00042280878],"category_scores_gemma":[0.0056931064,0.00023353184,0.000085435466,0.00010359206,0.00043313034,0.00013690518,0.00003185454,0.00067815685,0.000014841454],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013145903,0.00050271867,0.0000051932952,0.000107864376,0.00010962701,0.0008125515,0.00022501616,0.0000099290355,0.00007548742,0.5041727,0.012354958,0.4803094],"study_design_scores_gemma":[0.003894522,0.00084708334,0.00081209466,0.00044228463,0.00013613926,0.0041808663,0.000046235305,0.0017203643,0.000018858973,0.9857885,0.0018515298,0.0002614953],"about_ca_topic_score_codex":0.000010302148,"about_ca_topic_score_gemma":0.000008275004,"teacher_disagreement_score":0.48161587,"about_ca_system_score_codex":0.000018923361,"about_ca_system_score_gemma":0.000035933517,"threshold_uncertainty_score":0.9523152},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.19945774268679498,"score_gpt":0.4912955240526531,"score_spread":0.29183778136585814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030349076","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003968447,0.00038977514,0.99238366,0.0006829096,0.000043149634,0.0003570146,0.0005008126,0.00002349856,0.0016507196],"genre_scores_gemma":[0.18274729,0.000046208912,0.8165381,0.0002868228,0.00020946276,0.000017739501,0.000009338545,0.00002777485,0.00011726385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977215,0.00017217407,0.0010343406,0.00043264707,0.0003142429,0.00032512748],"domain_scores_gemma":[0.99485064,0.00394322,0.00023634412,0.0003608141,0.00024050254,0.00036850726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011173683,0.00017935381,0.0006091012,0.00009270786,0.00012153585,0.00015453341,0.0002933134,0.00012496891,0.00015795001],"category_scores_gemma":[0.0045805303,0.00016671517,0.000034888315,0.00013568808,0.00029707502,0.00025297864,0.00014615407,0.0003588604,0.0000060501297],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108910746,0.000597986,0.000045685338,0.00021928892,0.000049078095,0.0002253453,0.000036766945,0.00012539135,0.000058578513,0.76552373,0.014664783,0.21834446],"study_design_scores_gemma":[0.0007704309,0.00022000687,0.0024816322,0.00011924224,0.00010028096,0.0014903045,0.000033203592,0.011183576,9.801537e-7,0.9798911,0.0035215958,0.00018765427],"about_ca_topic_score_codex":0.000012778238,"about_ca_topic_score_gemma":0.000026877045,"teacher_disagreement_score":0.21815681,"about_ca_system_score_codex":0.000012397598,"about_ca_system_score_gemma":0.000023416736,"threshold_uncertainty_score":0.6798447},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.6273935671893198,"score_gpt":0.5794021805264894,"score_spread":0.047991386662830426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036701577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050041,0.0001287223,0.94175744,0.00028244243,0.00015759014,0.00019707806,0.000062297775,0.00002900707,0.0073444094],"genre_scores_gemma":[0.21469206,0.000034627014,0.7847619,0.00025903594,0.00020294501,0.0000021509486,4.0767253e-7,0.0000161372,0.00003070758],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99528325,0.0011410421,0.002213082,0.00032131936,0.0006260123,0.00041530936],"domain_scores_gemma":[0.9584871,0.039306086,0.0011359315,0.00020630335,0.00051755086,0.00034704703],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0073548737,0.00018924473,0.0012455139,0.00008063737,0.000090371424,0.000067428424,0.0003231706,0.00026838318,0.00024923962],"category_scores_gemma":[0.20284313,0.00017614766,0.000114196555,0.00024028774,0.00030360516,0.00012843951,0.0000449117,0.0007477421,0.00000421721],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003153898,0.0027646914,0.00043642038,0.0006081299,0.00015814113,0.00050139474,0.00022776668,0.0000022408651,0.001058298,0.51734704,0.0016880403,0.47489247],"study_design_scores_gemma":[0.0012253802,0.0015315952,0.004767342,0.00033859926,0.00015967102,0.0034263874,0.000067187895,0.0009956433,0.000043924578,0.9872526,0.000014260201,0.00017744167],"about_ca_topic_score_codex":0.0000019254471,"about_ca_topic_score_gemma":3.8010688e-7,"teacher_disagreement_score":0.47471502,"about_ca_system_score_codex":0.000034383756,"about_ca_system_score_gemma":0.000042011063,"threshold_uncertainty_score":0.80387163},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.4380628287343638,"score_gpt":0.5641740061112318,"score_spread":0.126111177376868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075806409","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03612513,0.00014738881,0.961938,0.0002878743,0.00032886086,0.00025575602,0.000041407307,0.000017148328,0.00085838145],"genre_scores_gemma":[0.30291727,0.000080684964,0.6966165,0.000170867,0.00014859984,0.000006846712,0.0000010255666,0.000019804107,0.000038421753],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99715585,0.00060447154,0.0013217388,0.00029527716,0.00031874247,0.00030391166],"domain_scores_gemma":[0.95175207,0.04712495,0.00045748707,0.00013726178,0.00022270958,0.00030555303],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0041760425,0.00016505986,0.00093024457,0.000062662846,0.00012951942,0.00007518494,0.00016251966,0.00018177305,0.00011447417],"category_scores_gemma":[0.10647586,0.00013927718,0.00007168234,0.00007176376,0.000552094,0.000066630564,0.00007038334,0.00038797784,0.000004894787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003541697,0.0004892002,0.00042245176,0.0005537031,0.00004706828,0.00005001892,0.00006515581,0.0000013511764,0.00011378713,0.73540676,0.005629856,0.25686648],"study_design_scores_gemma":[0.0022899879,0.0007339989,0.004699898,0.00071045116,0.00012514195,0.0015420859,0.0000176427,0.009230399,0.000009121891,0.98018056,0.0003062186,0.00015447686],"about_ca_topic_score_codex":7.635494e-7,"about_ca_topic_score_gemma":9.468086e-7,"teacher_disagreement_score":0.26679215,"about_ca_system_score_codex":0.000011918234,"about_ca_system_score_gemma":0.000013352174,"threshold_uncertainty_score":0.9010507},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5089277066177947,"score_gpt":0.5105138001551611,"score_spread":0.0015860935373663843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082983435","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40657485,0.00015854754,0.5909809,0.0005309901,0.00012043522,0.00036486168,0.00018891315,0.000008484204,0.0010720532],"genre_scores_gemma":[0.36850658,0.000038425875,0.6312853,0.000103718114,0.000040786366,0.000006868792,1.02504444e-7,0.000012959987,0.000005241133],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955393,0.0009225098,0.002532024,0.00027195388,0.0003988297,0.00033538358],"domain_scores_gemma":[0.9180248,0.08037716,0.00069992634,0.00018156496,0.00044962738,0.00026694656],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035612867,0.00017384576,0.0014706383,0.00013280107,0.000035961573,0.000032178352,0.0002954497,0.0001817033,0.0007082716],"category_scores_gemma":[0.2442217,0.00015582114,0.00009216076,0.0002956148,0.0009299186,0.00007190069,0.000070625254,0.00040072296,0.0000076004135],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036358772,0.0022327444,0.004863988,0.0019198327,0.00023428345,0.0004801627,0.00034072582,0.000005615622,0.028355367,0.42348665,0.0025277056,0.53518933],"study_design_scores_gemma":[0.0007963313,0.0005000694,0.05117899,0.0010439545,0.00006916356,0.0009971987,0.000065572545,0.00004961409,0.0007708415,0.94438183,0.0000060321836,0.00014037998],"about_ca_topic_score_codex":0.00007224587,"about_ca_topic_score_gemma":0.000008560138,"teacher_disagreement_score":0.53504896,"about_ca_system_score_codex":0.000015661213,"about_ca_system_score_gemma":0.000057367026,"threshold_uncertainty_score":0.7755077},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09456399157201978,"score_gpt":0.37824000341710623,"score_spread":0.28367601184508645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088581243","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0123367375,0.00023713372,0.9827238,0.00020944944,0.000062818006,0.00010146152,0.00004555299,0.000017531469,0.0042655356],"genre_scores_gemma":[0.13994083,0.000023694018,0.8598244,0.00008193931,0.000089095236,0.0000031332904,0.0000010643371,0.000014912661,0.000020920457],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99822646,0.00022486706,0.00083415804,0.00021166408,0.00024031368,0.00026256277],"domain_scores_gemma":[0.99365467,0.005616932,0.00026891666,0.000081940416,0.00019528654,0.0001822322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009061399,0.00014990852,0.0005311089,0.000063992,0.00010813432,0.000092870716,0.00009269868,0.00011390329,0.0001950606],"category_scores_gemma":[0.006062201,0.00013468746,0.00003374464,0.000104710736,0.00046793692,0.0000967599,0.000038498973,0.00035165928,0.0000052666087],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033365654,0.00017067273,0.00006875542,0.00009664388,0.00001548601,0.00031976192,0.000017589435,7.8191573e-7,0.000039772705,0.7033953,0.0018098413,0.29403204],"study_design_scores_gemma":[0.0006223042,0.00039193756,0.011207823,0.00026780233,0.000078576326,0.008364815,0.000028887234,0.0098646255,0.000006820776,0.9689919,0.0000278621,0.00014668376],"about_ca_topic_score_codex":0.00001409806,"about_ca_topic_score_gemma":0.0000041667804,"teacher_disagreement_score":0.29388535,"about_ca_system_score_codex":0.000011723801,"about_ca_system_score_gemma":0.000021228934,"threshold_uncertainty_score":0.72574586},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Statistics; Normative; Econometrics; Statistical hypothesis testing; Mathematics; Epistemology; Philosophy","score_opus":0.6101012297971987,"score_gpt":0.6102618176534461,"score_spread":0.00016058785624739613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099457688","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04905751,0.00011732883,0.94752705,0.00047217112,0.00034620348,0.0007619636,0.00020916293,0.000043452594,0.0014651454],"genre_scores_gemma":[0.09328864,0.000061955674,0.9056772,0.0004542693,0.00035064138,0.000041280455,0.000004271246,0.0000618045,0.00005994684],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98998904,0.0029904626,0.0047423635,0.0005806143,0.0010513448,0.0006461556],"domain_scores_gemma":[0.91402656,0.0816954,0.0019955202,0.0003289632,0.0012014138,0.00075212994],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008745326,0.00040923792,0.002289513,0.000112797905,0.0002225252,0.00026690474,0.00045714062,0.00035746512,0.0018107562],"category_scores_gemma":[0.115373015,0.00032865463,0.00013942963,0.0002688788,0.0018824532,0.00025559837,0.00013311302,0.0017672266,0.00009774339],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068877556,0.0030911984,0.0035085317,0.00086145336,0.0005616484,0.0009975286,0.000276813,0.00002304709,0.000111884096,0.4520267,0.041858096,0.49599433],"study_design_scores_gemma":[0.0031002893,0.0033834828,0.013035988,0.0006428364,0.00032264309,0.002351528,0.0002469734,0.007094473,0.00000884751,0.9693679,0.000035725283,0.00040931386],"about_ca_topic_score_codex":0.000014048558,"about_ca_topic_score_gemma":0.00001054344,"teacher_disagreement_score":0.5173412,"about_ca_system_score_codex":0.000042622585,"about_ca_system_score_gemma":0.00015904529,"threshold_uncertainty_score":0.99991655},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5007231631368919,"score_gpt":0.5401128261342657,"score_spread":0.03938966299737379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102817893","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029712843,0.0005393483,0.9671225,0.00026130202,0.00056509237,0.00036004191,0.00027793695,0.000014007125,0.0011469251],"genre_scores_gemma":[0.21874747,0.00015433194,0.7804552,0.00020681025,0.00035233074,0.000014249341,9.132922e-7,0.000030374924,0.0000383192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99590105,0.00060224143,0.002186376,0.00024499683,0.0005120902,0.00055322103],"domain_scores_gemma":[0.94962585,0.04858591,0.00074715173,0.00020596877,0.00034097114,0.00049413723],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0063365754,0.00020538298,0.0012853214,0.00007892391,0.00006728344,0.000032095646,0.00031509346,0.00025881725,0.0006648179],"category_scores_gemma":[0.08847126,0.00018162122,0.0001922005,0.000115152914,0.0007060056,0.00013058678,0.000090686284,0.0005003466,0.000008325077],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039744398,0.0018599685,0.00044710218,0.0009773535,0.00015157978,0.000079620375,0.00011206953,3.8017797e-7,0.00032490242,0.9262589,0.009860469,0.059530217],"study_design_scores_gemma":[0.001981612,0.00079488335,0.005816716,0.0003879865,0.0002452037,0.0028703988,0.000052508807,0.000060915037,0.00007161372,0.9873152,0.00021262138,0.0001903794],"about_ca_topic_score_codex":0.0000011853175,"about_ca_topic_score_gemma":0.0000010575999,"teacher_disagreement_score":0.18903463,"about_ca_system_score_codex":0.000018823515,"about_ca_system_score_gemma":0.00003280396,"threshold_uncertainty_score":0.9192069},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.39724289716766226,"score_gpt":0.5422999661469321,"score_spread":0.14505706897926984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113330311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056374665,0.00078247,0.9377987,0.00091351755,0.00047300698,0.0004550552,0.0012088083,0.00001722352,0.0019765496],"genre_scores_gemma":[0.5133141,0.00035285126,0.48556527,0.0004300406,0.0002101849,0.0000042559,0.0000018499271,0.00004221961,0.000079176774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994015,0.0018124849,0.002845096,0.00030462525,0.0005406337,0.00048219576],"domain_scores_gemma":[0.9232587,0.07469788,0.0009660983,0.0003047733,0.00047750122,0.0002950419],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0060563837,0.0002465922,0.0017390171,0.00008486458,0.0000882426,0.000039454048,0.00040396667,0.00024968386,0.0047605787],"category_scores_gemma":[0.12097358,0.00017804181,0.00017575722,0.00023340681,0.0012926867,0.000064961256,0.000100085505,0.0007770594,0.000019123705],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061784167,0.0012639081,0.00016532883,0.0005327695,0.00032448405,0.00047431616,0.00019340048,0.0000010373791,0.00027091688,0.9506126,0.021158379,0.024385016],"study_design_scores_gemma":[0.003386142,0.0011345138,0.0026859692,0.00043718732,0.00037281658,0.0012381126,0.00008443206,0.0031670704,0.000024772713,0.98685956,0.00042340154,0.00018604063],"about_ca_topic_score_codex":0.0000061990568,"about_ca_topic_score_gemma":0.0000040265195,"teacher_disagreement_score":0.4569395,"about_ca_system_score_codex":0.000018358878,"about_ca_system_score_gemma":0.000032929158,"threshold_uncertainty_score":0.9961492},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.35337936081111715,"score_gpt":0.5400826959220477,"score_spread":0.18670333511093057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125118056","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.2936511e-7,0.52792853,0.4710799,0.000046822683,0.00005167068,0.00026986658,0.00015920826,0.000006197792,0.00045759047],"genre_scores_gemma":[0.0000010602432,0.7841513,0.21553914,0.000084413696,0.00004629294,0.000022803399,0.000009020921,0.000038281578,0.00010765752],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9928846,0.0018603852,0.0037569774,0.0004019298,0.0006426417,0.00045347554],"domain_scores_gemma":[0.9777251,0.019082703,0.0019186966,0.0004411994,0.00049995235,0.00033234735],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004701435,0.00041366392,0.005482862,0.00021521696,0.00014621721,0.000056407,0.00052461517,0.00031503526,0.0004017163],"category_scores_gemma":[0.021683138,0.00026280727,0.0008756037,0.0008469179,0.00079497107,0.000051283965,0.000081240585,0.000966205,0.000004353224],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022119964,0.00019630244,8.256971e-8,0.012979498,0.0018666069,0.00041852662,0.000008765947,8.280642e-8,9.2312455e-8,0.13879153,0.0052250023,0.84049135],"study_design_scores_gemma":[0.0002416946,0.0002137291,0.0000038526027,0.030362636,0.018747395,0.0051813987,0.0000100049565,0.000040165334,3.509943e-8,0.7004115,0.24452685,0.0002607694],"about_ca_topic_score_codex":0.000002271889,"about_ca_topic_score_gemma":0.000005735102,"teacher_disagreement_score":0.8402306,"about_ca_system_score_codex":0.000026807935,"about_ca_system_score_gemma":0.0001021221,"threshold_uncertainty_score":0.9999824},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.37346727652047623,"score_gpt":0.45220365936991447,"score_spread":0.07873638284943824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131040314","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36921194,0.00005725185,0.6302631,0.00006907749,0.000023305838,0.00022059423,0.000018915556,0.0000021814528,0.00013361237],"genre_scores_gemma":[0.6312156,0.000012655041,0.36869025,0.00003627305,0.00001716857,0.000007878179,2.2641255e-7,0.000010509185,0.000009429957],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981372,0.0007334801,0.00064986304,0.00016696913,0.00016756967,0.00014492037],"domain_scores_gemma":[0.9936742,0.0058250856,0.00023928277,0.00010554183,0.000083347695,0.000072504125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014735421,0.00010493564,0.00042567763,0.00003500589,0.00006237291,0.000019441288,0.00010028931,0.00009242666,0.000025697505],"category_scores_gemma":[0.005612549,0.000066913235,0.000034490495,0.00009142747,0.00044095592,0.00006814574,0.00002028018,0.00022480453,4.270338e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025485255,0.00064112904,0.00044700457,0.00080910564,0.000040170406,0.000012862235,0.0006672539,0.00008966957,0.0007726238,0.09132457,0.000055263143,0.9048855],"study_design_scores_gemma":[0.0011495701,0.0004963211,0.048982278,0.00072684203,0.00009879188,0.0013159353,0.00019321642,0.034697354,0.00011628396,0.91211295,0.000009460363,0.00010100217],"about_ca_topic_score_codex":0.0000028066215,"about_ca_topic_score_gemma":0.000010083184,"teacher_disagreement_score":0.9047845,"about_ca_system_score_codex":0.0000082208135,"about_ca_system_score_gemma":0.000013404861,"threshold_uncertainty_score":0.67191505},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2715206547783738,"score_gpt":0.48669607144257343,"score_spread":0.21517541666419965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140217706","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028122235,0.0015235452,0.9566978,0.00011539469,0.00021804622,0.00021389665,0.000038493148,0.000015262229,0.013055278],"genre_scores_gemma":[0.47808227,0.000034999783,0.5216356,0.00012067054,0.000022265634,0.0000068218937,9.648272e-7,0.000012725816,0.00008370102],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951512,0.0011026035,0.0017765943,0.00046508,0.001087768,0.00041674203],"domain_scores_gemma":[0.99301815,0.0054168473,0.00048180268,0.00025637346,0.00031839786,0.0005084319],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0042140326,0.0002199207,0.0010337683,0.00014946816,0.00015211935,0.00027214686,0.00048683543,0.00016895177,0.0004544082],"category_scores_gemma":[0.01908389,0.0001808818,0.00014035661,0.00025665044,0.0006746527,0.00020785097,0.0000668162,0.00055385975,0.000053193857],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048413826,0.0106235165,0.00290718,0.0002743962,0.0003540334,0.00087535416,0.0018538808,0.0019499502,0.0016479086,0.6336246,0.20537844,0.1356693],"study_design_scores_gemma":[0.008575572,0.0017710557,0.0036648384,0.00014943413,0.00012912121,0.006980786,0.0024244352,0.28272554,0.000121089746,0.6909167,0.0019491663,0.000592271],"about_ca_topic_score_codex":0.0000020922635,"about_ca_topic_score_gemma":0.000002842764,"teacher_disagreement_score":0.44996002,"about_ca_system_score_codex":0.000026031008,"about_ca_system_score_gemma":0.00008966122,"threshold_uncertainty_score":0.9891788},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03577935715460232,"score_gpt":0.328755334554809,"score_spread":0.29297597740020664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151152712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04176292,0.0012615831,0.9538164,0.0006744095,0.0001715429,0.00007400856,0.000018118637,0.000017822287,0.0022031716],"genre_scores_gemma":[0.7676089,0.00014445782,0.23189491,0.00023194648,0.0000651236,0.000001836059,9.2876866e-7,0.0000063571674,0.000045549386],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979457,0.0003172724,0.00082559744,0.00033214933,0.00025549246,0.00032375575],"domain_scores_gemma":[0.99815685,0.001090691,0.00015025923,0.00022633914,0.00012736765,0.00024852596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007357316,0.0001401594,0.0006476368,0.00026023365,0.000053124444,0.00013881792,0.0005401931,0.00011093352,0.0007711897],"category_scores_gemma":[0.00070891675,0.0001284013,0.00011403128,0.0006056633,0.00026051333,0.00015123749,0.00014541735,0.00042722782,0.000026260996],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001828366,0.0014400958,0.0013011992,0.00009974018,0.0002700989,0.0026043653,0.0014020993,0.000048188966,0.0000113678525,0.3498204,0.0066562644,0.63632786],"study_design_scores_gemma":[0.0008280896,0.0002877227,0.11087715,0.000036324953,0.00007623617,0.0056363456,0.00002454136,0.07742089,0.0000016724323,0.80426526,0.00035407086,0.0001916984],"about_ca_topic_score_codex":0.000005946128,"about_ca_topic_score_gemma":0.000024903406,"teacher_disagreement_score":0.725846,"about_ca_system_score_codex":0.000023666651,"about_ca_system_score_gemma":0.000011996156,"threshold_uncertainty_score":0.8443987},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05512543054606262,"score_gpt":0.36836296659184314,"score_spread":0.31323753604578053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158319724","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15690222,0.0008855255,0.8411169,0.0007932036,0.000086863,0.00008400347,0.000023167371,0.000015698377,0.00009240493],"genre_scores_gemma":[0.6669385,0.00012282441,0.33280224,0.000094787516,0.00002970083,0.0000013651634,3.067673e-7,0.0000042369206,0.000006052529],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981751,0.00042416248,0.00062081957,0.00025566787,0.00032666087,0.00019762803],"domain_scores_gemma":[0.993875,0.0052909926,0.0002725547,0.00019214462,0.00017872326,0.00019053009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007623474,0.00013028679,0.0004779966,0.00005781502,0.00017065999,0.0001106744,0.00027497928,0.00007817714,0.000021846987],"category_scores_gemma":[0.0024626183,0.000084747146,0.000048347683,0.00009712465,0.0003779436,0.00015986149,0.00023146033,0.00032838283,0.0000033131892],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029635875,0.00033875008,0.00027142026,0.000029883819,0.000041428248,0.0009105601,0.00086310436,0.000006741225,0.0020692826,0.03168704,0.011000293,0.95248514],"study_design_scores_gemma":[0.0012247866,0.0010488647,0.031291794,0.002773451,0.000034744862,0.009036914,0.00024300654,0.08217136,0.000981133,0.86981446,0.0010537808,0.00032569218],"about_ca_topic_score_codex":0.000007709483,"about_ca_topic_score_gemma":0.000015080774,"teacher_disagreement_score":0.95215946,"about_ca_system_score_codex":0.000010511749,"about_ca_system_score_gemma":0.000005911966,"threshold_uncertainty_score":0.34558883},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09940994877516365,"score_gpt":0.415083829253759,"score_spread":0.31567388047859535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163998574","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031433962,0.00028611434,0.9536695,0.00015854042,0.000102422295,0.00024630278,0.00013799129,0.000012745208,0.013952433],"genre_scores_gemma":[0.44739133,0.0003388109,0.55210996,0.000089566034,0.000012709202,0.000004797379,0.0000011402831,0.000017348602,0.000034361143],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975039,0.00025472403,0.0014296386,0.00022857454,0.00028885005,0.00029431583],"domain_scores_gemma":[0.9939669,0.0049670036,0.00038093503,0.00015263294,0.00021890963,0.00031365966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010793406,0.00019174832,0.000900699,0.00017601452,0.00009073275,0.000019228337,0.00013330828,0.00018338529,0.00050314027],"category_scores_gemma":[0.005662089,0.00016560387,0.00009735238,0.0001893716,0.0007150945,0.000109453664,0.00002379493,0.000515097,0.000006769956],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000332397,0.0009781779,0.000015122436,0.00042194143,0.00010198005,0.00044464556,0.000702857,5.8000984e-7,0.00015709086,0.81762075,0.0006896647,0.1785348],"study_design_scores_gemma":[0.0021678645,0.0011587541,0.003933717,0.00039413414,0.00019662805,0.0050984113,0.00007279493,0.0008980073,0.00003919625,0.9858307,0.00003610124,0.00017366547],"about_ca_topic_score_codex":0.0000035156054,"about_ca_topic_score_gemma":0.0000019326394,"teacher_disagreement_score":0.41595736,"about_ca_system_score_codex":0.000008967532,"about_ca_system_score_gemma":0.00003008948,"threshold_uncertainty_score":0.6778459},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.2892882943145064,"score_gpt":0.4905955814410748,"score_spread":0.20130728712656837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164006511","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15196487,0.00025904182,0.8459667,0.000034618428,0.000074769436,0.00043889816,0.000096280004,0.000010231875,0.0011545618],"genre_scores_gemma":[0.4823058,0.000054003052,0.5175228,0.000020449555,0.00004118172,0.000013036768,0.0000010204675,0.000014175927,0.000027559778],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99735993,0.00032007069,0.0013735973,0.0002714242,0.00035156086,0.00032339967],"domain_scores_gemma":[0.9893338,0.009372382,0.00049872935,0.0001466026,0.0004177899,0.0002306712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009583969,0.00020029562,0.0013008958,0.0001491469,0.00013951366,0.000029761666,0.00018610404,0.00010832105,0.00007567165],"category_scores_gemma":[0.0045712376,0.00017538056,0.0000955341,0.0001875141,0.0004626817,0.00013971333,0.000039383474,0.00035636485,0.0000013624137],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009553787,0.008118179,0.00009989934,0.0007497601,0.00042159477,0.0011608292,0.0029502136,0.000047610603,0.00021796396,0.9203968,0.0063557248,0.05852604],"study_design_scores_gemma":[0.0033448907,0.0032435753,0.0026057556,0.00016392657,0.00018770955,0.004173757,0.0023198372,0.00090649986,0.00001807906,0.9827859,0.000051670573,0.00019843705],"about_ca_topic_score_codex":0.000005537907,"about_ca_topic_score_gemma":0.000008594166,"teacher_disagreement_score":0.33034092,"about_ca_system_score_codex":0.000012029756,"about_ca_system_score_gemma":0.000054468386,"threshold_uncertainty_score":0.7151812},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.08798309826525118,"score_gpt":0.40092374668028197,"score_spread":0.3129406484150308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168460233","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46522826,0.000108094355,0.5333835,0.00071299303,0.00016826019,0.00006636349,0.000064428124,0.0000018875659,0.0002662363],"genre_scores_gemma":[0.9425409,0.000045895616,0.05712119,0.00021154404,0.000054065513,0.0000021305334,0.0000011298683,0.000007997851,0.00001513716],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99742496,0.00018791555,0.0012718919,0.00023654739,0.0007078394,0.00017085172],"domain_scores_gemma":[0.9920001,0.006737405,0.0006766202,0.0002473774,0.00022684655,0.00011163195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024855123,0.00010198016,0.0004671948,0.000051494346,0.00013093566,0.00019609713,0.00043094676,0.00009027479,0.000670554],"category_scores_gemma":[0.003320954,0.000060029663,0.000064028805,0.00008420364,0.0007114699,0.00015109993,0.000044205302,0.00044658998,0.000027140022],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003601943,0.0008988484,0.002772106,0.000016751792,0.00006423061,0.00022465891,0.00029608118,0.00048326136,0.0010778984,0.16786084,0.0051150755,0.82083005],"study_design_scores_gemma":[0.0013560889,0.00045907855,0.037284885,0.00010716713,0.00006633944,0.003577301,0.00031024922,0.0026231355,0.00002967381,0.9512377,0.0028055746,0.0001428529],"about_ca_topic_score_codex":0.000005723677,"about_ca_topic_score_gemma":0.0000070903766,"teacher_disagreement_score":0.8206872,"about_ca_system_score_codex":0.0000054336797,"about_ca_system_score_gemma":0.000029458797,"threshold_uncertainty_score":0.7342096},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.38388052115437615,"score_gpt":0.5674083538348488,"score_spread":0.18352783268047262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168627095","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06149862,0.00017128365,0.93387514,0.0006439546,0.00027741978,0.00024739784,0.0002872996,0.000011982938,0.002986924],"genre_scores_gemma":[0.37500483,0.000098416356,0.6246401,0.00014238714,0.00008170565,0.0000031979978,4.4101836e-7,0.000016688233,0.000012263302],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995394,0.0008016667,0.00262454,0.00027985193,0.0006001014,0.0002998368],"domain_scores_gemma":[0.95701927,0.04111833,0.0010223745,0.00025286095,0.00032143298,0.00026570153],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0041274596,0.0001945669,0.0015177284,0.0000911515,0.00004219319,0.000017311875,0.00030976086,0.0002468731,0.0004698087],"category_scores_gemma":[0.09060911,0.00016664671,0.0001760292,0.00015606282,0.0011262054,0.000057390196,0.00006973734,0.0005707582,0.000007760424],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010673302,0.0025500737,0.00003223445,0.0008726931,0.00011600378,0.00035311616,0.00013890292,0.0000029447422,0.00037749537,0.93040776,0.00070616073,0.06337528],"study_design_scores_gemma":[0.0026248405,0.0034836615,0.0071880273,0.001213235,0.00017252371,0.0014721175,0.000029021896,0.000024851137,0.00029148816,0.98332256,0.000029046816,0.00014861225],"about_ca_topic_score_codex":0.000006584369,"about_ca_topic_score_gemma":0.0000023449677,"teacher_disagreement_score":0.3135062,"about_ca_system_score_codex":0.000019866317,"about_ca_system_score_gemma":0.00007503292,"threshold_uncertainty_score":0.9170511},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06834616108167536,"score_gpt":0.3423298604087666,"score_spread":0.27398369932709127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171530386","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021506827,0.00069624826,0.9765844,0.00025005007,0.00002676458,0.00017520016,0.000006639762,0.000046367364,0.0007075058],"genre_scores_gemma":[0.36014807,0.00029204093,0.6393544,0.00015719976,0.000018042145,0.000008641475,4.382453e-7,0.000009039732,0.00001214118],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981323,0.00028596655,0.0007281924,0.00032036417,0.00021153683,0.00032164564],"domain_scores_gemma":[0.99705285,0.0023857753,0.00010822628,0.00013807569,0.00008385209,0.00023119985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060727564,0.00016216945,0.00052999856,0.000092579474,0.00007381834,0.00009916127,0.00020235968,0.00009610298,0.000027196507],"category_scores_gemma":[0.0017508785,0.00014551864,0.0000313051,0.00016098096,0.00022897012,0.00016539244,0.000028792125,0.00027570207,0.000002988413],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000546779,0.00026920048,0.00005182814,0.00005310395,0.000021685784,0.0018823914,0.00013356049,0.000015243709,0.00034160115,0.05120581,0.00008850788,0.9458824],"study_design_scores_gemma":[0.0015934433,0.001301531,0.009187208,0.00052360236,0.000028647239,0.007668755,0.000008259784,0.033128753,0.000049718634,0.9462198,0.000089326015,0.00020094776],"about_ca_topic_score_codex":0.000014809785,"about_ca_topic_score_gemma":0.0000041587214,"teacher_disagreement_score":0.94568145,"about_ca_system_score_codex":0.00003259136,"about_ca_system_score_gemma":0.000027948257,"threshold_uncertainty_score":0.5934078},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5714294779352754,"score_gpt":0.5466511481811501,"score_spread":0.024778329754125306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2330570680","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009491453,0.0001526475,0.98667306,0.0007723316,0.00025100756,0.00033933023,0.00012852561,0.000021928665,0.0021697222],"genre_scores_gemma":[0.02671371,0.0000795563,0.97255015,0.00020261222,0.0003021199,0.000028298009,4.2340193e-7,0.0000306228,0.00009252826],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971574,0.00044851683,0.0014431108,0.00034385614,0.00025892718,0.00034816653],"domain_scores_gemma":[0.934677,0.06414041,0.00041965683,0.0001357024,0.000288462,0.00033879033],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002797637,0.00018508312,0.0009287995,0.000064833774,0.00009877985,0.00008291579,0.00016153873,0.00017901123,0.0003003588],"category_scores_gemma":[0.10235773,0.00012844571,0.00008885696,0.000084700296,0.00059261714,0.00009926138,0.00006856401,0.00031234053,0.0000049808455],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004346688,0.00074299023,0.000119964076,0.0005769439,0.00014202484,0.00013543178,0.000041589792,2.2715852e-7,0.00040485096,0.5404044,0.012080784,0.44491613],"study_design_scores_gemma":[0.0026160234,0.0009522566,0.0011032443,0.000581523,0.00014993237,0.006122453,0.00004476522,0.00034560284,0.000016137752,0.98751426,0.00037647935,0.00017733869],"about_ca_topic_score_codex":0.0000012427779,"about_ca_topic_score_gemma":6.433167e-7,"teacher_disagreement_score":0.44710985,"about_ca_system_score_codex":0.000020243433,"about_ca_system_score_gemma":0.000026682459,"threshold_uncertainty_score":0.9052035},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12336615640232285,"score_gpt":0.48009945331021286,"score_spread":0.35673329690789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2584362917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04493261,0.00012865616,0.9532382,0.0005228575,0.0001511561,0.00017637793,0.00003472865,0.000004017625,0.00081143074],"genre_scores_gemma":[0.5588543,0.000035435532,0.44100568,0.000046799127,0.000038223294,0.0000014388675,3.2323794e-7,0.000007629784,0.000010164501],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998059,0.0006921523,0.0007725478,0.0001490541,0.00017480194,0.00015246528],"domain_scores_gemma":[0.99312645,0.005682028,0.000661852,0.00026606297,0.00016438802,0.000099205005],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021001294,0.00011214858,0.0004350121,0.000028765122,0.00039651804,0.00010946441,0.00020410359,0.000105688,0.00010112251],"category_scores_gemma":[0.009084335,0.000068976784,0.000061877625,0.000038918384,0.00078812736,0.00015044858,0.000083447914,0.00035163623,6.8176064e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000447727,0.00007383878,0.000107190644,0.00009607445,0.000027945527,0.00014459126,0.00016143674,0.000012833043,0.0000144186415,0.6872796,0.00014251583,0.3118948],"study_design_scores_gemma":[0.0004895097,0.00008499023,0.018251207,0.00016250189,0.00012979262,0.0073459563,0.00006607652,0.0847298,0.0000034180105,0.88865244,0.0000125503275,0.00007178138],"about_ca_topic_score_codex":0.000038761907,"about_ca_topic_score_gemma":0.000015577814,"teacher_disagreement_score":0.5139217,"about_ca_system_score_codex":0.00000814121,"about_ca_system_score_gemma":0.000011733563,"threshold_uncertainty_score":0.9992626},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.4557394537833383,"score_gpt":0.5102854334071317,"score_spread":0.05454597962379343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620799017","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14614898,0.0005507852,0.84445906,0.0035035328,0.0007243465,0.0003628835,0.00009386559,0.000023410938,0.004133147],"genre_scores_gemma":[0.12042548,0.001467063,0.8758939,0.0010985973,0.0008085318,0.000044824912,5.447311e-7,0.00004908578,0.0002120119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959061,0.0011371337,0.0015917497,0.00040619227,0.0005006839,0.0004581281],"domain_scores_gemma":[0.9511646,0.04692145,0.0008096529,0.0005083604,0.00023204797,0.00036387658],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.007023971,0.00025080223,0.0012925473,0.000047924666,0.0005870883,0.00042027206,0.0005672998,0.0002235423,0.00043796934],"category_scores_gemma":[0.14463721,0.00018096923,0.00015735583,0.000050762326,0.0028913228,0.0002111681,0.0002459436,0.00094207196,0.00003019243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019794193,0.00035880628,0.00035019874,0.00027785898,0.00024583968,0.0008252288,0.00018074691,8.320208e-8,0.000045003417,0.8660449,0.008514993,0.12295843],"study_design_scores_gemma":[0.0040667127,0.00020618149,0.022372559,0.00031996437,0.0002523027,0.004559471,0.00004850178,0.0001393582,0.000013174567,0.9669433,0.0009742418,0.00010419202],"about_ca_topic_score_codex":0.0000069976054,"about_ca_topic_score_gemma":0.0000035697133,"teacher_disagreement_score":0.13761324,"about_ca_system_score_codex":0.000013585396,"about_ca_system_score_gemma":0.000025159274,"threshold_uncertainty_score":0.99982226},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.13750207654009666,"score_gpt":0.50524852138227,"score_spread":0.3677464448421734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782608753","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1880275,0.00016311517,0.81063956,0.00061503355,0.00007476724,0.00017135669,0.00003928446,0.0000031746533,0.00026617735],"genre_scores_gemma":[0.80711615,0.00005389182,0.19261298,0.00015366105,0.000046746954,0.0000028831948,1.2062986e-7,0.000007642574,0.0000059481217],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99788016,0.00079417584,0.00072772877,0.0001568345,0.0002444014,0.0001966932],"domain_scores_gemma":[0.98479885,0.014464153,0.0002890029,0.00011858324,0.0002480071,0.00008141245],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021294565,0.00012276508,0.0005015659,0.000047987716,0.00011130906,0.000024903258,0.00014386844,0.00008930782,0.00015958658],"category_scores_gemma":[0.019969989,0.00006760047,0.00005891853,0.00012853519,0.0005901477,0.000046903308,0.00006411057,0.00035323418,0.0000019858599],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016529567,0.00028389474,0.00013841123,0.00014408365,0.000072741685,0.000026087406,0.00043224683,0.0000021170672,0.00027156586,0.9149533,0.0007605542,0.08274968],"study_design_scores_gemma":[0.0005108787,0.0004960934,0.026034588,0.00038879196,0.000049244412,0.00043124013,0.00005813025,0.012012602,0.000067613524,0.9598728,0.000005429235,0.000072609735],"about_ca_topic_score_codex":0.000005169339,"about_ca_topic_score_gemma":0.000011622426,"teacher_disagreement_score":0.61908865,"about_ca_system_score_codex":0.000018988856,"about_ca_system_score_gemma":0.000017221768,"threshold_uncertainty_score":0.98828524},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0576921882517152,"score_gpt":0.41720794336886785,"score_spread":0.35951575511715267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942651266","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06421437,0.00022915888,0.9331979,0.00022140324,0.00015845773,0.00017502898,0.000116773284,0.000016343727,0.001670571],"genre_scores_gemma":[0.32638684,0.00008708128,0.6730499,0.0002534867,0.00005499025,0.000002773465,0.0000052158493,0.000020463202,0.00013924505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973703,0.0003995725,0.0011381733,0.0003206944,0.00040034996,0.00037092523],"domain_scores_gemma":[0.9964494,0.0024192282,0.0003545098,0.0002197742,0.00018039749,0.0003766739],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009310232,0.00020474942,0.0012119018,0.00015259445,0.00006854827,0.00006277856,0.0002035965,0.0001506436,0.0032351455],"category_scores_gemma":[0.0014382724,0.0001770343,0.0001971559,0.00021971036,0.00025099254,0.00008478045,0.00005283467,0.00045431816,0.000014514667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019701067,0.000362774,0.00016522483,0.0001967384,0.0006717607,0.0004906046,0.00009102751,0.000020672564,0.00042034435,0.9432666,0.0018945003,0.052222777],"study_design_scores_gemma":[0.0014330043,0.0002878605,0.0031357477,0.000065889275,0.0006000849,0.0020187588,0.000042890802,0.005331385,0.000012083889,0.98652214,0.00033906865,0.00021106607],"about_ca_topic_score_codex":0.0000036905162,"about_ca_topic_score_gemma":0.0000055604314,"teacher_disagreement_score":0.26217246,"about_ca_system_score_codex":0.000015653563,"about_ca_system_score_gemma":0.000019731495,"threshold_uncertainty_score":0.997676},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0946494624905834,"score_gpt":0.3728073056028315,"score_spread":0.2781578431122481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995591168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24508308,0.0013477345,0.75057316,0.00017615265,0.00018568957,0.0005992572,0.000061029965,0.000016108555,0.0019578058],"genre_scores_gemma":[0.8198214,0.0003071079,0.17961766,0.000097947406,0.000037441438,0.000013369056,0.0000013606509,0.00002621757,0.0000775019],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99751294,0.0004115092,0.0013015794,0.00018898622,0.00028388933,0.00030107476],"domain_scores_gemma":[0.9803374,0.018528147,0.000617507,0.0002062128,0.00021328108,0.00009747048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013515154,0.00018054536,0.0010396453,0.00009086921,0.000038353686,0.000033077704,0.0002819761,0.00016066621,0.000093910414],"category_scores_gemma":[0.0045233136,0.00013711648,0.00008190862,0.00008160687,0.0005658722,0.00011040391,0.00007150819,0.0005222717,0.0000037333568],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034782675,0.0006039984,0.00049879286,0.0029505307,0.00014843392,0.00029669618,0.00039229996,6.829562e-7,0.013759762,0.8922089,0.002383933,0.086408146],"study_design_scores_gemma":[0.0020557626,0.00083272986,0.0110242525,0.0023903248,0.00005654746,0.00075175596,0.00006212022,0.00006425487,0.0010620115,0.98141754,0.00013496322,0.00014774792],"about_ca_topic_score_codex":0.0000050560843,"about_ca_topic_score_gemma":0.000007836086,"teacher_disagreement_score":0.5747383,"about_ca_system_score_codex":0.000026718737,"about_ca_system_score_gemma":0.000031981555,"threshold_uncertainty_score":0.5591448},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16531862255891705,"score_gpt":0.426819047784887,"score_spread":0.26150042522596995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005846352","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02607851,0.0002652103,0.9693604,0.00343314,0.000029664496,0.0004122155,0.00026429302,0.0000108736285,0.0001456993],"genre_scores_gemma":[0.13926834,0.000118240656,0.8598099,0.0006580291,0.00006566436,0.000021753565,0.0000026995992,0.000029698509,0.000025691737],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976405,0.00024373202,0.001096801,0.00035769408,0.00022451182,0.00043679375],"domain_scores_gemma":[0.9939352,0.0052392613,0.00022553917,0.00012820217,0.0001523738,0.0003194236],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012577927,0.00022046066,0.00085967383,0.000052430114,0.00011026948,0.00005656452,0.00018890183,0.00016789365,0.000023932824],"category_scores_gemma":[0.011976989,0.00016387553,0.000048412472,0.00018074046,0.00034180732,0.000101594764,0.00009194956,0.0007532911,8.784371e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002902598,0.0034149853,0.0013289361,0.0052307947,0.00016964105,0.002812699,0.00646618,0.0052380757,0.0027125627,0.57082605,0.0072115404,0.3916859],"study_design_scores_gemma":[0.001751832,0.00025347184,0.00023336642,0.0004599893,0.00003285424,0.0005217418,0.00015209058,0.3989171,0.0000045232528,0.5974704,0.000071845796,0.0001307998],"about_ca_topic_score_codex":0.000008406578,"about_ca_topic_score_gemma":0.000019055013,"teacher_disagreement_score":0.39367902,"about_ca_system_score_codex":0.000018847157,"about_ca_system_score_gemma":0.000055826604,"threshold_uncertainty_score":0.9963455},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.42078208780786935,"score_gpt":0.49142747486818933,"score_spread":0.07064538706031998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047129708","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11332132,0.00034531535,0.88384926,0.0014086826,0.00015871668,0.0002022232,0.00012562977,0.000010840639,0.0005779823],"genre_scores_gemma":[0.8197263,0.00009780025,0.1782214,0.0018262859,0.0001100666,0.0000028821996,0.0000030641968,0.0000071404156,0.000005045849],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99728036,0.0003556787,0.0012733367,0.00025132022,0.00058815855,0.000251155],"domain_scores_gemma":[0.92699105,0.07170064,0.0004933927,0.00007191662,0.00043290804,0.0003101235],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0036395448,0.00012772247,0.0006104057,0.00013301907,0.000145674,0.00041597622,0.0002556983,0.000105535546,0.000095196374],"category_scores_gemma":[0.2360558,0.00010479221,0.00007812697,0.00032291716,0.00023465196,0.0004985028,0.000092309,0.00033202468,0.000017489494],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005252109,0.00019406242,0.0007469518,0.00018440216,0.00005940609,0.00019709925,0.0007724484,0.000065849395,0.000014373895,0.1337892,0.00565555,0.8577954],"study_design_scores_gemma":[0.0018868494,0.0010594608,0.03649589,0.00021831694,0.000060655817,0.0012011804,0.00035704495,0.045299932,0.0000018735241,0.91305155,0.00022312229,0.00014413676],"about_ca_topic_score_codex":0.0000026460534,"about_ca_topic_score_gemma":7.102096e-7,"teacher_disagreement_score":0.8576513,"about_ca_system_score_codex":0.000006843668,"about_ca_system_score_gemma":0.000020776954,"threshold_uncertainty_score":0.77037925},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02750667536499382,"score_gpt":0.324438908424291,"score_spread":0.29693223305929717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3147659269","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5075119,0.00005675423,0.49192166,0.0002207969,0.000008327047,0.00005671725,0.00009315005,0.0000043813357,0.00012629294],"genre_scores_gemma":[0.77286536,0.000026470529,0.22681446,0.00021170505,0.000030033054,0.0000058538058,0.000032022912,0.0000015713516,0.0000125385895],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979915,0.0003775009,0.00072260917,0.00034689315,0.00033346863,0.00022800626],"domain_scores_gemma":[0.99778664,0.0009510708,0.00028428054,0.00008783316,0.0005276961,0.00036245427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059242017,0.0001253562,0.00062399067,0.000038574835,0.000103153376,0.000055563643,0.0001471133,0.00009354018,0.0005439626],"category_scores_gemma":[0.00093209115,0.00006625415,0.00010518992,0.00057822646,0.00023282458,0.00008854661,0.000021551832,0.0002117539,0.0000019502972],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025773142,0.0043905345,0.013822216,0.00021280414,0.001018871,0.0011941337,0.0002923136,0.0033039595,0.025547486,0.10474058,0.00029247883,0.8426073],"study_design_scores_gemma":[0.0010765465,0.0030315267,0.6467252,0.0004138086,0.0012897004,0.0009928105,0.0004051517,0.115796626,0.00107808,0.22869912,0.000041923093,0.0004495137],"about_ca_topic_score_codex":0.000034212302,"about_ca_topic_score_gemma":0.0005061214,"teacher_disagreement_score":0.8421578,"about_ca_system_score_codex":0.000009057609,"about_ca_system_score_gemma":0.0000166939,"threshold_uncertainty_score":0.5956009},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.8016671738027995,"score_gpt":0.5424559714075778,"score_spread":0.25921120239522166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205145300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4819427,0.000559792,0.5167004,0.0001368813,0.00008295537,0.00007078569,0.000024242354,0.0000016847538,0.00048059772],"genre_scores_gemma":[0.81859535,0.000024847928,0.18131734,0.00003400674,0.000015926118,0.0000018898857,0.0000035529274,0.000003200308,0.000003862127],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959045,0.0015809541,0.0011965373,0.00028583824,0.00087679754,0.00015534692],"domain_scores_gemma":[0.9784634,0.02019897,0.00047807983,0.00012464666,0.0006270996,0.00010777052],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004137191,0.00009592115,0.0006229411,0.00021448323,0.00006907243,0.00010196002,0.0001263294,0.00007680793,0.0003773958],"category_scores_gemma":[0.018861314,0.00008066414,0.000052919542,0.0004265096,0.00038692742,0.00012504359,0.000036553967,0.00025122342,9.838326e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004694892,0.00091321184,0.037147656,0.00018432169,0.0002469002,0.0002906278,0.002496109,0.040748127,0.0011397259,0.17251946,0.00043906464,0.74340534],"study_design_scores_gemma":[0.0009392886,0.00006656194,0.11886338,0.00006412327,0.000031353644,0.00094802503,0.00095239736,0.37955266,0.000030520754,0.49849164,0.0000016921293,0.000058351172],"about_ca_topic_score_codex":0.000009927747,"about_ca_topic_score_gemma":0.000008598924,"teacher_disagreement_score":0.743347,"about_ca_system_score_codex":0.000016616696,"about_ca_system_score_gemma":0.000079806385,"threshold_uncertainty_score":0.98940325},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Item response theory; Group (periodic table); Mathematics; Statistics; Econometrics; Reliability engineering; Psychology; Psychometrics; Engineering; Physics","score_opus":0.3057821453871747,"score_gpt":0.4634622157514617,"score_spread":0.157680070364287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214686438","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2135176,0.00038323313,0.7843809,0.00036482624,0.00046003293,0.00019110089,0.0002330067,0.000010888753,0.00045838725],"genre_scores_gemma":[0.8021678,0.000020071773,0.19700241,0.00054297334,0.00005502924,0.000021363327,0.0000020086245,0.000012876235,0.00017550636],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99334204,0.0033905245,0.0014929107,0.00043557666,0.0009813923,0.0003575357],"domain_scores_gemma":[0.84884316,0.14996025,0.00043221036,0.00023944183,0.0003045209,0.00022041921],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03522916,0.00012649049,0.0006549987,0.00024110403,0.00039083336,0.00012597411,0.00064894906,0.000075280375,0.00076648255],"category_scores_gemma":[0.27608702,0.000103200386,0.00015354066,0.00048387217,0.00038628452,0.000117615156,0.00020818877,0.00048042386,0.0000049516325],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009728293,0.0019163209,0.0010379304,0.000060449096,0.00006645095,0.0005000552,0.00041956434,0.00059089396,0.00024918068,0.22586343,0.029725691,0.72984177],"study_design_scores_gemma":[0.0015550669,0.001125391,0.018578133,0.000019862506,0.000021085072,0.0032603375,0.00064686564,0.018622233,9.072709e-7,0.9520822,0.0039681834,0.000119739714],"about_ca_topic_score_codex":0.0000018670484,"about_ca_topic_score_gemma":3.976097e-7,"teacher_disagreement_score":0.729722,"about_ca_system_score_codex":0.000030047388,"about_ca_system_score_gemma":0.000034402878,"threshold_uncertainty_score":0.9934346},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11198058467526725,"score_gpt":0.39204246552775257,"score_spread":0.2800618808524853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281689061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018907942,0.00042796225,0.96339875,0.0049884613,0.00007478095,0.00021682693,0.010732264,0.000016354801,0.0012366676],"genre_scores_gemma":[0.88903135,0.000048176178,0.109859884,0.0008197756,0.00004825668,0.000014580408,0.00016064975,0.000011979587,0.0000053490735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976533,0.00046673525,0.0010433006,0.00024638278,0.00039519946,0.00019510317],"domain_scores_gemma":[0.9858381,0.013151917,0.00033535372,0.0003318133,0.00017489653,0.00016787798],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011956488,0.00012275924,0.0004321793,0.000024910523,0.00047868607,0.00006810682,0.00032738486,0.00005449867,0.0047251172],"category_scores_gemma":[0.007914994,0.000102595506,0.000047357797,0.00010103201,0.001190084,0.00007709351,0.00032973127,0.00051454327,0.0000041873955],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025934163,0.00033335297,0.000026486992,0.000020053118,0.00005150273,0.000035832094,0.00010178977,0.0000019601591,0.000072623414,0.9631267,0.031826217,0.0043774983],"study_design_scores_gemma":[0.00069898384,0.000104341125,0.0031882813,0.000044165467,0.00016691079,0.0012760074,0.00029941622,0.007196748,0.000003031525,0.98610413,0.0008142773,0.00010368854],"about_ca_topic_score_codex":0.000012067132,"about_ca_topic_score_gemma":0.0000036959,"teacher_disagreement_score":0.8701234,"about_ca_system_score_codex":0.000015679663,"about_ca_system_score_gemma":0.000062145664,"threshold_uncertainty_score":0.9961847},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1287896801544608,"score_gpt":0.44059646563512533,"score_spread":0.31180678548066454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283316432","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.816598,0.0007651,0.18141694,0.00024181727,0.00020572354,0.00019024068,0.000094213116,0.000012824744,0.00047512254],"genre_scores_gemma":[0.95555973,0.0001893653,0.043639734,0.00036029826,0.00007018318,0.00003175458,0.0000060940197,0.000014653617,0.00012816374],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944699,0.0038900748,0.0006165725,0.00027141548,0.00039278535,0.00035925262],"domain_scores_gemma":[0.9897746,0.009550526,0.00018850475,0.00008604365,0.00012315363,0.00027718864],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024127686,0.00010741769,0.00044255407,0.00020494497,0.00045656037,0.00004856128,0.0002011069,0.00015242648,0.000046573194],"category_scores_gemma":[0.011957936,0.000113324684,0.00004869821,0.00016638167,0.00040941147,0.0000945298,0.000043402746,0.0005260912,4.1098505e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008691396,0.006784,0.01697302,0.00046737838,0.00040119686,0.023690738,0.10596891,0.00056729256,0.0013425372,0.7215223,0.022779567,0.09081167],"study_design_scores_gemma":[0.0055287806,0.002534785,0.17612499,0.0001893552,0.00021075604,0.028323058,0.023477554,0.013929927,0.000023494551,0.73278046,0.016423823,0.00045303488],"about_ca_topic_score_codex":0.00002158054,"about_ca_topic_score_gemma":0.00010866817,"teacher_disagreement_score":0.15915197,"about_ca_system_score_codex":0.000047555743,"about_ca_system_score_gemma":0.00016741936,"threshold_uncertainty_score":0.9963648},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2205900365319809,"score_gpt":0.5017560123301307,"score_spread":0.2811659757981498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295077327","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22598939,0.0053767385,0.73899305,0.010232858,0.003049611,0.0015965693,0.007553411,0.000038486396,0.007169859],"genre_scores_gemma":[0.8791481,0.00039794715,0.10898107,0.0051736482,0.0008456846,0.0002009894,0.000385075,0.00012346402,0.0047439835],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99712795,0.000535579,0.00090615323,0.00041927327,0.0004798265,0.00053124217],"domain_scores_gemma":[0.99715173,0.0015535445,0.0002889748,0.0003269267,0.00027691358,0.0004018845],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021513016,0.00014264535,0.0005320127,0.00010881832,0.0003127472,0.000045034318,0.00060078246,0.00007135988,0.008000513],"category_scores_gemma":[0.0013886724,0.00013329048,0.000059176004,0.00011187524,0.00039154422,0.00009191438,0.0003768691,0.0009031639,0.00002124766],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030544654,0.0015358255,0.00046252063,0.00037799243,0.000221331,0.005458528,0.00063995784,8.338421e-7,0.000065090535,0.10541774,0.4301212,0.4526445],"study_design_scores_gemma":[0.008875254,0.008685227,0.058851525,0.0003491791,0.00017214956,0.10307544,0.0028252052,0.0010863983,0.0000050146114,0.7106175,0.10492129,0.00053582614],"about_ca_topic_score_codex":0.000024501682,"about_ca_topic_score_gemma":0.000008269028,"teacher_disagreement_score":0.6531587,"about_ca_system_score_codex":0.000046180918,"about_ca_system_score_gemma":0.0000700634,"threshold_uncertainty_score":0.99290633},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.8160285585535664,"score_gpt":0.5966260124549783,"score_spread":0.2194025460985881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384277172","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.644032,0.00021428449,0.35523757,0.00022268762,0.00008612178,0.00009201142,0.000016770631,0.000003392664,0.00009516274],"genre_scores_gemma":[0.7977203,0.000085217966,0.20207407,0.000051384675,0.00004143378,0.000003857413,5.578423e-7,0.0000048469838,0.000018335253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975231,0.0002505213,0.0011916792,0.00022488457,0.0005697307,0.00024003332],"domain_scores_gemma":[0.9502944,0.048759904,0.00053611153,0.00009832848,0.00024272596,0.00006857844],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012167774,0.00008411139,0.00040608548,0.00021813103,0.00013624478,0.00009453848,0.00028299575,0.00006407997,0.000032799184],"category_scores_gemma":[0.0734489,0.00005670528,0.000036529604,0.00058013585,0.00029459113,0.00013815046,0.000076994584,0.00023944692,0.0000010977437],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023394471,0.00007821571,0.010221301,0.0002664848,0.000025239999,0.000029459201,0.0006891447,0.005330279,0.00079794537,0.04399235,0.00019563577,0.93814],"study_design_scores_gemma":[0.00050202385,0.0003964854,0.07313863,0.00018145717,0.000010366991,0.0005097189,0.00019881556,0.57613105,0.0000040955915,0.34887016,0.0000063256293,0.000050848896],"about_ca_topic_score_codex":0.0000050317667,"about_ca_topic_score_gemma":0.0000014171909,"teacher_disagreement_score":0.93808913,"about_ca_system_score_codex":0.0000062995186,"about_ca_system_score_gemma":0.000021461858,"threshold_uncertainty_score":0.93435585},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.17965977955819226,"score_gpt":0.4642400169581189,"score_spread":0.28458023739992666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406715877","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067792633,0.0003127509,0.990706,0.0007119462,0.00014531506,0.00028486951,0.0005765618,0.0000069032153,0.0004763585],"genre_scores_gemma":[0.26577315,0.00008013138,0.7338138,0.00024307691,0.000037381484,0.00001503357,0.000008341598,0.000010674993,0.000018391534],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979059,0.00016379,0.0010056521,0.00039682759,0.00022016681,0.00030763354],"domain_scores_gemma":[0.9892571,0.009638645,0.00025928297,0.00020828855,0.0004762316,0.00016045361],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013014779,0.00017884267,0.0007071114,0.00013199038,0.00008720872,0.00009430272,0.00030102974,0.0001490789,0.0000807877],"category_scores_gemma":[0.016483987,0.00015614697,0.000036170182,0.000090175774,0.0004543497,0.000094931645,0.00019257855,0.0004233374,9.404592e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001920574,0.0002983576,0.00010419693,0.00028061005,0.00006038354,0.00021329444,0.00011680458,0.0000100568295,0.000014558939,0.93979824,0.0015236527,0.057387803],"study_design_scores_gemma":[0.0012550432,0.00012109956,0.010141313,0.00058938796,0.000072903604,0.0006662227,0.000058652327,0.2443217,0.0000014465259,0.74264526,0.000012845811,0.000114120245],"about_ca_topic_score_codex":0.0000060177263,"about_ca_topic_score_gemma":0.000008873111,"teacher_disagreement_score":0.2589939,"about_ca_system_score_codex":0.000020630045,"about_ca_system_score_gemma":0.00009050523,"threshold_uncertainty_score":0.9918006},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.07205106244704894,"score_gpt":0.3891975518028085,"score_spread":0.31714648935575956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117121226","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012534901,0.00024757732,0.99407977,0.00086236873,0.00026380748,0.0002774176,0.00024561543,0.000018245692,0.0027517295],"genre_scores_gemma":[0.019739045,0.000105872736,0.97932714,0.00065470365,0.000053121516,0.00001993727,0.000004919064,0.000018734456,0.00007653271],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979483,0.00021667396,0.0010221516,0.00025600137,0.00021027029,0.00034658817],"domain_scores_gemma":[0.9867535,0.012294146,0.00023842472,0.00013739642,0.0003763793,0.00020015649],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013066226,0.00017059065,0.00069391966,0.00009287399,0.00011242262,0.00009542493,0.00018604845,0.00018712123,0.00062769104],"category_scores_gemma":[0.010334864,0.00015101938,0.00009542099,0.00013832531,0.0002585037,0.00008080862,0.00004592323,0.0003186958,0.0000024595859],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012541405,0.00035258368,0.000012157828,0.00026703675,0.00010821818,0.000026793154,0.00005031504,0.0000016893695,0.000053360145,0.944262,0.0048303837,0.04991001],"study_design_scores_gemma":[0.001240967,0.00032252673,0.00082545966,0.0002857805,0.00014181664,0.00036515354,0.000054074684,0.003372921,0.0000070677615,0.9929204,0.000311416,0.00015239014],"about_ca_topic_score_codex":0.000005381235,"about_ca_topic_score_gemma":0.0000038106973,"teacher_disagreement_score":0.04975762,"about_ca_system_score_codex":0.00002620123,"about_ca_system_score_gemma":0.00008473868,"threshold_uncertainty_score":0.9980015},"labels":[],"label_agreement":null}]}