{"meta":{"query_hash":"4243585afc1b","filters":{"venue":"Journal of Educational and Behavioral Statistics"},"cohort_total":23,"direct_labels_cover":1,"predictions_cover":23,"exported":23,"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/4243585afc1b","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Educational+and+Behavioral+Statistics"},"results":[{"id":"W1999688181","doi":"10.3102/10769986027003291","title":"Nonparametric Item Response Function Estimates with the EM Algorithm","year":2002,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":83,"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":"Nonparametric statistics; Mathematics; Item response theory; Functional data analysis; Differential item functioning; Algorithm; Latent variable; Latent variable model; Smoothness; Statistics; Function (biology); Mathematical optimization; Psychometrics","score_opus":0.04016072169252984,"score_gpt":0.32769232982788027,"score_spread":0.28753160813535045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999688181","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":[0.023054805,0.0002626267,0.9742236,0.0022057702,0.0001382485,0.00006186457,0.000033276803,0.000012271807,0.0000075086355],"genre_scores_gemma":[0.23004475,0.000023571643,0.76961625,0.00010926546,0.00005559497,0.0000046574182,0.0000019109666,0.0000055962423,0.000138416],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991051,0.000054689517,0.00025317498,0.00011978502,0.0003385851,0.00012869576],"domain_scores_gemma":[0.9976794,0.0014397898,0.00023434567,0.00012815183,0.00042103918,0.00009724648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023670164,0.0001017052,0.00012567909,0.00011648959,0.00015455965,0.00013751765,0.0002475368,0.000028229462,0.000051535484],"category_scores_gemma":[0.00024686323,0.00006138431,0.000019399959,0.00028575747,0.000087189524,0.00027815334,0.000037448335,0.00019502957,0.0000044822064],"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":[0.00020666169,0.0009289916,0.0028371904,0.000014688914,0.000037231624,0.000055926852,0.000888517,0.000295309,0.00019951734,0.08028142,0.029103868,0.8851507],"study_design_scores_gemma":[0.0013566733,0.008359618,0.20685089,0.00016186648,0.00041080598,0.0023405112,0.00038671112,0.38033533,0.00023878577,0.3923741,0.006299386,0.0008853262],"about_ca_topic_score_codex":0.0000048040615,"about_ca_topic_score_gemma":0.0000019307781,"teacher_disagreement_score":0.88426536,"about_ca_system_score_codex":0.000049933482,"about_ca_system_score_gemma":0.00006483467,"threshold_uncertainty_score":0.25031793},"labels":[],"label_agreement":null},{"id":"W2033872871","doi":"10.3102/1076998613481500","title":"A Two-Decision Model for Responses to Likert-Type Items","year":2013,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kronos (Canada)","funders":"","keywords":"Likert scale; Item response theory; Set (abstract data type); Decision model; Econometrics; Functional response; Model selection; Response time; Statistics; Computer science; Mathematics; Machine learning; Psychometrics","score_opus":0.5866905625763341,"score_gpt":0.5681326453150991,"score_spread":0.018557917261235013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033872871","genre_codex":"empirical","genre_gemma":"methods","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":[0.6887818,0.00014349598,0.30833888,0.001527975,0.00095260696,0.0001394314,0.00007961978,0.000001830438,0.00003435371],"genre_scores_gemma":[0.40969947,0.000012503562,0.5879563,0.0001780831,0.00017558566,0.00000654931,0.0000021236103,0.000005373647,0.0019639966],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99810445,0.00008530316,0.0007773568,0.00017481974,0.00069353916,0.0001645255],"domain_scores_gemma":[0.9742002,0.022908691,0.00043874906,0.00014035939,0.0020699366,0.00024207536],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019348762,0.000096490876,0.00024729426,0.0004270692,0.0001393793,0.0002575074,0.0003133421,0.0000373992,0.00034755812],"category_scores_gemma":[0.040711258,0.00006302931,0.000053574004,0.0005408177,0.000043614156,0.00022443724,0.00005324061,0.000105203624,0.00002547736],"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":[0.00043865104,0.0004316139,0.09845335,0.000005633981,0.000012387683,0.00000236154,0.0006875027,0.0011398002,0.0019450206,0.007118654,0.30129024,0.5884748],"study_design_scores_gemma":[0.00061753724,0.001086615,0.3184436,0.000040822983,0.00004457899,0.0001053425,0.00071941904,0.022784762,0.000031259653,0.64946395,0.0064502372,0.00021187283],"about_ca_topic_score_codex":0.0000560406,"about_ca_topic_score_gemma":0.000007992173,"teacher_disagreement_score":0.6423453,"about_ca_system_score_codex":0.000032614225,"about_ca_system_score_gemma":0.00024883187,"threshold_uncertainty_score":0.96736926},"labels":[],"label_agreement":null},{"id":"W2060741340","doi":"10.3102/10769986028001083","title":"A Review of Data Analysis for the Behavioral Sciences Using SPSS","year":2003,"lang":"en","type":"review","venue":"Journal of Educational and Behavioral Statistics","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":3,"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":"Statistics education; Mathematics education; Readability; Computer science; Competence (human resources); Statistics; Psychology; Mathematics; Social psychology","score_opus":0.8292002256135855,"score_gpt":0.6501527572032614,"score_spread":0.17904746841032415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060741340","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000061564106,0.93408936,0.058758434,0.00011490855,0.0008504468,0.00047848892,0.005693285,0.0000015544152,0.0000073583974],"genre_scores_gemma":[4.568578e-7,0.5916219,0.40792343,0.000039993916,0.00011613935,0.000012395207,0.00015600964,0.000012704492,0.00011698649],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997158,0.00033931946,0.001618754,0.00025417897,0.00043640446,0.0001933571],"domain_scores_gemma":[0.9875517,0.00821037,0.0028996044,0.00039496252,0.0008450942,0.00009827797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027635226,0.00027583507,0.0016466712,0.00029747497,0.00021117898,0.00006350576,0.000727515,0.00010065786,0.0002926585],"category_scores_gemma":[0.0022813336,0.0001660301,0.00036117996,0.0007300343,0.00038916906,0.000112639915,0.000087582506,0.00025940646,5.6355276e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012215494,0.0015635601,0.00031310777,0.0714172,0.0012775164,0.0000026084194,0.00016006807,0.0000017468944,5.7655967e-7,0.06473834,0.15600571,0.70450735],"study_design_scores_gemma":[0.00015803591,0.00025692873,0.000036654943,0.017609203,0.06287169,0.0002621597,0.00024138445,0.00002331386,3.8639266e-7,0.02731093,0.8908709,0.0003583905],"about_ca_topic_score_codex":0.000029639386,"about_ca_topic_score_gemma":0.0000116794545,"teacher_disagreement_score":0.73486525,"about_ca_system_score_codex":0.00007524156,"about_ca_system_score_gemma":0.0022144183,"threshold_uncertainty_score":0.6770511},"labels":[],"label_agreement":null},{"id":"W2071849850","doi":"10.3102/1076998609332756","title":"Sample Size Estimation in Cluster Randomized Educational Trials: An Empirical Bayes Approach","year":2009,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Intraclass correlation; Bayes' theorem; Computer science; Cluster (spacecraft); Statistics; Sample size determination; Estimation; Sample (material); Data mining; Task (project management); Field (mathematics); Econometrics; Bayesian probability; Mathematics; Artificial intelligence; Psychometrics","score_opus":0.17298107137845747,"score_gpt":0.5008700679701498,"score_spread":0.3278889965916923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071849850","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":[0.045977507,0.00007950643,0.9493408,0.003626605,0.00027810133,0.00035054694,0.00022619718,0.0000041186004,0.00011660076],"genre_scores_gemma":[0.14872341,0.000024185903,0.8506695,0.00018450024,0.0002764476,0.000016207097,0.000043155927,0.000009277629,0.00005333277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99657685,0.0011284095,0.0014834761,0.00018871458,0.00042899337,0.00019358295],"domain_scores_gemma":[0.9657921,0.032772142,0.00073702476,0.00011075031,0.00037903665,0.00020895505],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003895621,0.00019013128,0.00089747726,0.00016202255,0.00008771911,0.00011632385,0.00014471968,0.00009910558,0.0007176536],"category_scores_gemma":[0.03629625,0.00013813272,0.000104340426,0.00016425889,0.00014969359,0.00025767818,0.0000133834765,0.00028942703,0.0000015733668],"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":[0.0042257775,0.003734387,0.00489328,0.00005767674,0.000031813914,0.000003347029,0.0010315237,0.0000174705,0.000036141762,0.901612,0.006107036,0.078249566],"study_design_scores_gemma":[0.009489111,0.00026990793,0.036264602,0.000051910796,0.00019776294,0.0000725278,0.00011990765,0.0057879793,0.000005416309,0.94755256,0.000023784347,0.00016450754],"about_ca_topic_score_codex":0.000037854756,"about_ca_topic_score_gemma":0.00000763428,"teacher_disagreement_score":0.1027459,"about_ca_system_score_codex":0.00008680132,"about_ca_system_score_gemma":0.00044426037,"threshold_uncertainty_score":0.9718214},"labels":[],"label_agreement":null},{"id":"W2072546393","doi":"10.3102/1076998606298037","title":"Point Estimates and Confidence Intervals for Variable Importance in Multiple Linear Regression","year":2007,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada; Carleton University","funders":"","keywords":"Statistics; Confidence interval; Linear regression; Variable (mathematics); Regression analysis; Mathematics; Measure (data warehouse); Variance (accounting); Regression; Linear model; Regression diagnostic; Econometrics; Bayesian multivariate linear regression; Computer science; Data mining","score_opus":0.17486948143277772,"score_gpt":0.4944659832462644,"score_spread":0.31959650181348664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072546393","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":[0.17198174,0.0002051817,0.8272146,0.00017362763,0.00013699639,0.00012809079,0.00014506829,0.0000017446073,0.000012965502],"genre_scores_gemma":[0.15481603,0.00004033953,0.84492004,0.000034204782,0.00007335059,0.0000038085088,0.000007928929,0.000009037948,0.000095254574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99899477,0.000020472791,0.0005780677,0.00011350262,0.00013823176,0.00015494878],"domain_scores_gemma":[0.99524456,0.0039347354,0.00034266594,0.000054413576,0.00030096623,0.00012267036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079674844,0.00010270875,0.00025298292,0.000066600944,0.000062157196,0.000019169584,0.00005436083,0.000046502424,0.000042214597],"category_scores_gemma":[0.0027069245,0.00007761563,0.000019430412,0.000051870367,0.00008305946,0.0001285519,0.000020371006,0.0001369442,1.4910734e-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":[0.00039374223,0.0007853694,0.06852656,0.0002819002,0.00001675581,0.000026420214,0.0006217715,0.000017208053,0.0031945112,0.9002407,0.0017554265,0.02413962],"study_design_scores_gemma":[0.0005794617,0.00028096908,0.017748175,0.00022159122,0.000052843592,0.0000878406,0.00019527492,0.0016094326,0.00032582093,0.97863406,0.00015383174,0.00011070057],"about_ca_topic_score_codex":0.000018198027,"about_ca_topic_score_gemma":0.000041397107,"teacher_disagreement_score":0.07839334,"about_ca_system_score_codex":0.00003800383,"about_ca_system_score_gemma":0.00007833148,"threshold_uncertainty_score":0.3240637},"labels":[],"label_agreement":null},{"id":"W2095820822","doi":"10.3102/1076998610397052","title":"Sampling Variability and Axioms of Classical Test Theory","year":2011,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Carleton University","funders":"","keywords":"Mathematics; Statistics; Sampling (signal processing); Sample size determination; Statistical hypothesis testing; Test theory; Sample (material); Test (biology); Axiom; Reliability (semiconductor); Population; Applied mathematics; Psychometrics; Computer science; Geometry","score_opus":0.6043028112079372,"score_gpt":0.5189607433140067,"score_spread":0.0853420678939305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095820822","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":[0.90815973,0.0001541333,0.09057342,0.0001906162,0.00044113206,0.000036910576,0.0000921003,0.0000012188265,0.00035072383],"genre_scores_gemma":[0.74670196,0.00001991147,0.25308722,0.000015265494,0.0000731183,4.5746455e-7,7.6158034e-7,0.0000023020634,0.000099007564],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984322,0.00020498995,0.0007058194,0.00012849116,0.0004336511,0.00009480095],"domain_scores_gemma":[0.9658836,0.03264575,0.00061892194,0.00010470113,0.00062398,0.00012301879],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0043551717,0.00006953646,0.0002456592,0.00016824855,0.000070283415,0.00003915594,0.00017866811,0.000041535535,0.0005616203],"category_scores_gemma":[0.04670079,0.000044661585,0.000033977274,0.0002836991,0.00025127738,0.0001131022,0.000051540963,0.00014298095,9.951376e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004533863,0.00048243452,0.78752583,0.0000071270897,0.0000068704576,0.0000016641899,0.0005504552,6.6082777e-7,0.0002734412,0.059807274,0.0005136216,0.15078527],"study_design_scores_gemma":[0.00009113545,0.00021065338,0.6393028,0.000008906598,0.000025495363,0.00005158123,0.00037867416,0.000019709467,0.000020833852,0.3597346,0.00011869108,0.000036932746],"about_ca_topic_score_codex":0.000016171414,"about_ca_topic_score_gemma":0.000001400932,"teacher_disagreement_score":0.29992732,"about_ca_system_score_codex":0.000012918025,"about_ca_system_score_gemma":0.00012746271,"threshold_uncertainty_score":0.9613293},"labels":[],"label_agreement":null},{"id":"W2097672163","doi":"10.3102/1076998610396894","title":"A Didactic Presentation of Snijders’s l z * Index of Person Fit With Emphasis on Response Model Selection and Ability Estimation","year":2011,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":52,"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 du Québec à Montréal","funders":"","keywords":"Ambiguity; Estimator; Item response theory; Index (typography); Generalization; Statistics; Set (abstract data type); Mathematics; Sample (material); Computer science; Type (biology); Psychology; Artificial intelligence; Psychometrics","score_opus":0.4831390672638221,"score_gpt":0.47795792141914767,"score_spread":0.00518114584467444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097672163","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":[0.9279968,0.00003815647,0.071567535,0.00015644224,0.0000835257,0.00008466758,0.000048242917,0.0000014234174,0.000023207976],"genre_scores_gemma":[0.8923694,0.00001445079,0.10756717,0.000010455364,0.000015798867,0.0000022369043,0.0000017168503,0.0000041440717,0.000014669223],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982486,0.00025728793,0.0005771857,0.0001544537,0.0006749631,0.00008753399],"domain_scores_gemma":[0.99228877,0.005593052,0.0010355064,0.00009161624,0.0009087942,0.000082275415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019126848,0.000090215304,0.00023594213,0.0003616071,0.00007528978,0.000031894655,0.00009640965,0.000047494206,0.000040643212],"category_scores_gemma":[0.00794147,0.00006276628,0.000031625295,0.00046804867,0.000130071,0.00025985946,0.000012929553,0.00012318336,3.1224158e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004490989,0.0013119689,0.76510715,0.000047920817,0.00003472242,0.000002079413,0.0045299265,0.0031261935,0.0136751495,0.0008443357,0.00076732604,0.20606223],"study_design_scores_gemma":[0.0004317582,0.001378456,0.96429616,0.000040597686,0.00007357756,0.00005593544,0.0010517716,0.013429319,0.0029222446,0.01624481,0.0000020961006,0.00007328355],"about_ca_topic_score_codex":0.00007048729,"about_ca_topic_score_gemma":0.000015342885,"teacher_disagreement_score":0.20598894,"about_ca_system_score_codex":0.000038075577,"about_ca_system_score_gemma":0.00022566725,"threshold_uncertainty_score":0.95072544},"labels":[],"label_agreement":null},{"id":"W2127843972","doi":"10.3102/1076998614524823","title":"A State Space Modeling Approach to Mediation Analysis","year":2014,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mediation; Computer science; Process (computing); Population; State space; Data science; Econometrics; Mathematics; Statistics; Sociology; Social science","score_opus":0.1615246983656391,"score_gpt":0.44512262690147375,"score_spread":0.28359792853583465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127843972","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":[0.27024907,0.000012480784,0.72922647,0.0002632409,0.000048763253,0.00005840522,0.000037586437,0.0000058938062,0.00009810682],"genre_scores_gemma":[0.509676,0.000008209725,0.49007833,0.000027357555,0.00007263616,0.000004422542,0.000013130976,0.0000065096738,0.00011341675],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990017,0.00004687535,0.0004197669,0.00010448086,0.00030660804,0.00012060827],"domain_scores_gemma":[0.9986261,0.0003345402,0.00029635828,0.00009181009,0.00049520313,0.00015596866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037946226,0.000102151236,0.00025223475,0.00024570216,0.0000567986,0.000041338837,0.00009493441,0.00003330309,0.000035282043],"category_scores_gemma":[0.00044464317,0.00008502286,0.000045513865,0.00026311263,0.000025406787,0.00013805427,0.000022315911,0.00013648879,0.0000015222663],"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":[0.000100590485,0.002024011,0.032638524,0.00011506861,0.0002939318,0.000002623728,0.0036577727,0.01584639,0.001472838,0.9140487,0.008299534,0.021500027],"study_design_scores_gemma":[0.00019495556,0.00031283265,0.0059491694,0.000022219105,0.00058482005,0.000023794413,0.00022946921,0.038426578,0.00012551327,0.9536723,0.00022505719,0.00023331825],"about_ca_topic_score_codex":0.000020399928,"about_ca_topic_score_gemma":0.000021216796,"teacher_disagreement_score":0.23942691,"about_ca_system_score_codex":0.0000659276,"about_ca_system_score_gemma":0.00007618762,"threshold_uncertainty_score":0.34671316},"labels":[],"label_agreement":null},{"id":"W2133414959","doi":"10.3102/10769986027001031","title":"Visions and Re-Visions of Charles Joseph Minard","year":2002,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":75,"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":"Vision; Depiction; Graphics; Visualization; Computer science; Thematic map; Data science; Computer graphics (images); Visual arts; Cartography; Artificial intelligence; Sociology; Art; Geography","score_opus":0.06888977604375794,"score_gpt":0.37290420437207605,"score_spread":0.3040144283283181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133414959","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":[0.64992124,0.0033009308,0.32762703,0.015991203,0.0014010298,0.00020384506,0.0009950394,0.000016176637,0.0005435069],"genre_scores_gemma":[0.85929984,0.0011521387,0.13853149,0.00014579218,0.000099340396,7.226973e-7,0.000018749963,0.0000055121404,0.00074644375],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.999222,0.000018217293,0.00034899783,0.00008905803,0.0002405681,0.00008119502],"domain_scores_gemma":[0.9990724,0.00012908735,0.00026598384,0.000095248964,0.00030247832,0.00013481244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000097551776,0.00006921097,0.00014039881,0.00011824543,0.000091479786,0.00007694174,0.00017845609,0.000026049323,0.00026677363],"category_scores_gemma":[0.00007609087,0.000056177236,0.00002552921,0.00014699118,0.00008156075,0.000263158,0.00006370763,0.00007892119,0.0000036317315],"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":[0.000012259299,0.00284658,0.07390199,0.0000800736,0.000053048327,0.000027595084,0.0037959612,0.000023616161,0.0009665581,0.56370324,0.22106285,0.13352624],"study_design_scores_gemma":[0.0031733424,0.0038321924,0.70843476,0.00075234746,0.0006972188,0.0011662198,0.0025403495,0.06330652,0.00067130954,0.093065195,0.121008925,0.0013516172],"about_ca_topic_score_codex":0.000008974054,"about_ca_topic_score_gemma":0.0000053901,"teacher_disagreement_score":0.63453275,"about_ca_system_score_codex":0.000011054348,"about_ca_system_score_gemma":0.00005603484,"threshold_uncertainty_score":0.29209843},"labels":[],"label_agreement":null},{"id":"W2157756920","doi":"10.3102/1076998615589129","title":"Visualizing Confidence Bands for Semiparametrically Estimated Nonlinear Relations Among Latent Variables","year":2015,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Mental Health Research Topics","field":"Psychology","cited_by":3,"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":"American Educational Research Association","keywords":"Latent variable; Structural equation modeling; Inference; Computer science; Latent variable model; Statistical inference; Visualization; Exploratory data analysis; Econometrics; Regression analysis; Latent class model; Empirical research; Nonlinear system; Data mining; Artificial intelligence; Machine learning; Statistics; Mathematics","score_opus":0.27318136463704734,"score_gpt":0.5297634161063589,"score_spread":0.25658205146931157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157756920","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":[0.95596844,0.0007844426,0.039009474,0.0015334884,0.0014628542,0.00038658205,0.00050187024,0.0000069586954,0.00034588666],"genre_scores_gemma":[0.72026676,0.000039019986,0.27449888,0.000112970134,0.00044043007,0.000033458888,0.00016851623,0.000019877662,0.004420076],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987724,0.00007338533,0.00051535375,0.00011260901,0.00032177614,0.00020446656],"domain_scores_gemma":[0.99757075,0.0008137246,0.0003152793,0.000072553215,0.00085340487,0.00037429802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059353624,0.00008674968,0.00017458691,0.00015129728,0.00011238413,0.00005110158,0.000103282604,0.000073394775,0.0005017541],"category_scores_gemma":[0.00067273,0.0000747062,0.00002751748,0.00017331539,0.00010383231,0.00012007382,0.000020045536,0.0002128273,0.0000129552645],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039276015,0.0021604677,0.75774646,0.00008115738,0.00007332009,0.00003071629,0.0019541252,0.00011762444,0.0000801558,0.12820336,0.09518259,0.013977274],"study_design_scores_gemma":[0.002948018,0.0030490013,0.9302776,0.00021176517,0.00027476117,0.00032840623,0.0012319214,0.0055853706,0.000043740052,0.045885798,0.009816487,0.00034715197],"about_ca_topic_score_codex":0.00023439538,"about_ca_topic_score_gemma":0.000018446908,"teacher_disagreement_score":0.23570165,"about_ca_system_score_codex":0.0001327922,"about_ca_system_score_gemma":0.000509786,"threshold_uncertainty_score":0.5493856},"labels":[],"label_agreement":null},{"id":"W2158157835","doi":"10.3102/10769986027002105","title":"Constrained Principal Component Analysis: Various Applications","year":2002,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":62,"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":"Principal component analysis; Contingency table; Set (abstract data type); Computer science; Multivariate statistics; Reliability (semiconductor); Component (thermodynamics); Regression analysis; Variety (cybernetics); Statistics; Data mining; Econometrics; Mathematics; Machine learning","score_opus":0.08203732621707842,"score_gpt":0.34469778670554435,"score_spread":0.2626604604884659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158157835","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":[0.97831386,0.0005643898,0.0171824,0.0024281377,0.00014038643,0.00015041878,0.0008423462,0.000006830764,0.0003712463],"genre_scores_gemma":[0.9563794,0.00007717999,0.042753726,0.000091800175,0.00023499105,0.0000061882706,0.000073540934,6.8237944e-7,0.00038248347],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989632,0.00008658745,0.00044820676,0.00012598664,0.0002460927,0.00012996388],"domain_scores_gemma":[0.9985175,0.00070930395,0.00027758782,0.000033629516,0.00027341436,0.00018857296],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018747445,0.00009801033,0.00026076732,0.0000420293,0.00016334812,0.000061113074,0.00011001378,0.00004242636,0.0038266107],"category_scores_gemma":[0.00006556771,0.00004225666,0.00010150604,0.00037570982,0.000112275404,0.000054381875,0.00001551868,0.00012897416,0.000011114016],"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":[0.00006484741,0.004525874,0.1691168,0.000023581759,0.0008559708,0.00003915994,0.000373687,0.0001307621,0.015956957,0.13998653,0.0043719327,0.6645539],"study_design_scores_gemma":[0.00028602994,0.0006175996,0.95736206,0.00001059229,0.0022417707,0.00014319773,0.0003368361,0.0023857306,0.000047303645,0.014453242,0.02179396,0.00032168278],"about_ca_topic_score_codex":0.000045957102,"about_ca_topic_score_gemma":0.000064474145,"teacher_disagreement_score":0.78824526,"about_ca_system_score_codex":0.000021485183,"about_ca_system_score_gemma":0.000010599702,"threshold_uncertainty_score":0.997084},"labels":[],"label_agreement":null},{"id":"W2163829751","doi":"10.3102/1076998607307355","title":"Causal Inference for Time-Varying Instructional Treatments","year":2008,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"School Choice and Performance","field":"Social Sciences","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 Toronto","funders":"","keywords":"Causal inference; Endogeneity; Weighting; Mathematics education; Value (mathematics); Inverse probability weighting; Multilevel model; Causal model; Econometrics; Inference; Outcome (game theory); Average treatment effect; Academic achievement; Computer science; Psychology; Propensity score matching; Statistics; Mathematics; Machine learning; Medicine; Artificial intelligence","score_opus":0.08936654137525234,"score_gpt":0.4135590799087178,"score_spread":0.32419253853346547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163829751","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":[0.99749947,0.00010104897,0.00047162344,0.0009482193,0.00049173716,0.0000673259,0.00013723217,0.000002177413,0.0002811809],"genre_scores_gemma":[0.93894154,0.0004097764,0.05440943,0.00008838187,0.0016900173,0.000009202104,0.000049839047,0.0000066731222,0.0043951464],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993528,0.000021224594,0.00020528036,0.000058849022,0.00024863228,0.00011317706],"domain_scores_gemma":[0.9990662,0.0002701001,0.00016509039,0.000025784224,0.00035734285,0.00011548233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011475888,0.00005715784,0.00009722733,0.000054472894,0.00047580423,0.000028420756,0.000067889276,0.000036004225,0.00046697148],"category_scores_gemma":[0.0001371019,0.000049747327,0.00002725883,0.000069260655,0.00013997273,0.0002684446,0.0000061549367,0.00007773375,0.000008491247],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016040551,0.00079303625,0.8915326,0.00001864141,0.00005920235,0.000010167377,0.0054138,0.000030188781,0.00036425833,0.025610706,0.04111246,0.03489453],"study_design_scores_gemma":[0.0013386921,0.0006704963,0.9266776,0.000051837993,0.00017389163,0.0002144054,0.00049474085,0.00007052416,0.00006835662,0.020673215,0.04928864,0.00027761914],"about_ca_topic_score_codex":0.00018857443,"about_ca_topic_score_gemma":0.000058847752,"teacher_disagreement_score":0.05855792,"about_ca_system_score_codex":0.00006963133,"about_ca_system_score_gemma":0.00072391774,"threshold_uncertainty_score":0.51130104},"labels":[],"label_agreement":null},{"id":"W2290377455","doi":"10.3102/1076998615606114","title":"Graphs ′ R Us UnwinAntony. Graphical Data Analysis With R. Boca Raton, FL: Taylor & Francis, 2015; 310 pages, $69.95, ISBN 9781498715232.","year":2015,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Advanced Graph Theory Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Mathematics education; Mathematics","score_opus":0.08435273792904979,"score_gpt":0.3799160870258571,"score_spread":0.2955633490968073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2290377455","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":[0.15178534,0.005185648,0.8352062,0.005575457,0.00084871874,0.0002792746,0.0010339456,0.000025923315,0.00005946765],"genre_scores_gemma":[0.4669513,0.0005846673,0.530808,0.00033100182,0.00029891857,0.000013157008,0.0005105421,0.000034381414,0.0004680536],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99692035,0.00020397654,0.00068015675,0.00048869883,0.0012793099,0.00042749097],"domain_scores_gemma":[0.99606943,0.0004117827,0.00051524234,0.00085340755,0.0014177316,0.00073238433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010936587,0.00026953043,0.00049312506,0.00051981484,0.00022787406,0.0002897069,0.0014865624,0.0000893221,0.000083033985],"category_scores_gemma":[0.00023098473,0.00020114596,0.00009300755,0.0016077469,0.0004065737,0.0010944491,0.0003207565,0.0005531017,0.000012744502],"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":[0.00070883415,0.0036471607,0.55910146,0.00006447837,0.00096330914,0.00033645055,0.0012298714,0.0005451861,0.00041124478,0.18465252,0.22017598,0.02816353],"study_design_scores_gemma":[0.0053993245,0.003902796,0.39276317,0.00014098534,0.0032011743,0.0017583227,0.00061601546,0.007288387,0.0001480431,0.46255502,0.11995747,0.0022693065],"about_ca_topic_score_codex":0.000104174454,"about_ca_topic_score_gemma":0.0003873728,"teacher_disagreement_score":0.31516594,"about_ca_system_score_codex":0.00006466575,"about_ca_system_score_gemma":0.0006278447,"threshold_uncertainty_score":0.82024944},"labels":[],"label_agreement":null},{"id":"W2461458402","doi":"10.3102/1076998615625963","title":"A Review of Monte Carlo Simulation and Resampling Methods for Social Science","year":2016,"lang":"en","type":"review","venue":"Journal of Educational and Behavioral Statistics","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Monte Carlo method; Resampling; Computer science; Statistics; Mathematics; Artificial intelligence","score_opus":0.15859171148093765,"score_gpt":0.5628150157069903,"score_spread":0.4042233042260527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2461458402","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003334718,0.98206526,0.016104814,0.00007534108,0.0003081547,0.0002535687,0.0011342698,5.421489e-7,0.00002469075],"genre_scores_gemma":[0.00011802445,0.95521283,0.044031095,0.000020419937,0.0005157783,0.00001284133,0.000025255162,0.000011463283,0.00005226418],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988597,0.000057684014,0.00070261135,0.00011989373,0.00014755047,0.000112560556],"domain_scores_gemma":[0.9972484,0.00067898777,0.0011554311,0.000048650167,0.00079039554,0.00007810816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066299766,0.00013383212,0.0006962584,0.00008069215,0.00017352318,0.000040607512,0.00011342723,0.000042924177,0.000033936285],"category_scores_gemma":[0.00008794942,0.00009539153,0.00014354593,0.000119718534,0.0002193867,0.000111717534,0.000032859854,0.00012136622,1.6135094e-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":[0.000002296166,0.000052639414,0.0000674092,0.0048323777,0.000023378356,3.372646e-8,0.000051549905,6.71717e-7,7.84139e-7,0.021539751,0.00023293987,0.97319615],"study_design_scores_gemma":[0.0002521209,0.00016027315,0.00014535354,0.03675246,0.0011587705,0.000006346376,0.000056169793,0.00009068365,2.9181163e-7,0.017204648,0.943877,0.0002958919],"about_ca_topic_score_codex":0.000013028107,"about_ca_topic_score_gemma":1.6593681e-7,"teacher_disagreement_score":0.9729003,"about_ca_system_score_codex":0.000045783636,"about_ca_system_score_gemma":0.00084565784,"threshold_uncertainty_score":0.38899535},"labels":[],"label_agreement":null},{"id":"W2663249513","doi":"10.3102/1076998616680841","title":"A Strategy for Replacing Sum Scoring","year":2016,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","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":"McGill University","funders":"","keywords":"Univariate; Mathematics; Parametric statistics; Statistics; Odds; Function (biology); Statistical hypothesis testing; Test (biology); Binary number; Applied mathematics; Binary data; Algorithm; Computer science; Multivariate statistics; Logistic regression; Arithmetic","score_opus":0.2861209535314837,"score_gpt":0.5117877317198253,"score_spread":0.22566677818834158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2663249513","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":[0.07047995,0.00006405911,0.9282666,0.0005076578,0.00025547555,0.00009171769,0.0002950734,0.0000025715965,0.000036917143],"genre_scores_gemma":[0.1816692,0.000033998618,0.81717724,0.000017016271,0.00023881267,0.0000070608585,0.0000022895345,0.000012046727,0.00084232347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99914455,0.000027863704,0.00042294041,0.00010135527,0.00015784155,0.00014545329],"domain_scores_gemma":[0.99677426,0.0023616161,0.0002989515,0.000063595486,0.0003760473,0.00012553851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030509688,0.00009020817,0.00019822462,0.000049349237,0.000079121404,0.0000232803,0.00006045552,0.000032397456,0.0000941392],"category_scores_gemma":[0.001096,0.000056154502,0.000037991616,0.000031808057,0.000060134727,0.00013463633,0.000012885578,0.00006859325,6.586623e-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":[0.00008514308,0.00022364953,0.0013418003,0.000057687248,0.000015770107,0.000004098167,0.00008033679,0.00000263759,0.0026219008,0.8660821,0.0033196998,0.12616521],"study_design_scores_gemma":[0.00049965264,0.0003923635,0.0018253059,0.00011124584,0.00009067053,0.00007141211,0.00007253138,0.000034520086,0.00021891473,0.9957091,0.00087080215,0.00010343633],"about_ca_topic_score_codex":0.0000033461147,"about_ca_topic_score_gemma":0.000004562254,"teacher_disagreement_score":0.12962708,"about_ca_system_score_codex":0.000046053963,"about_ca_system_score_gemma":0.00013475263,"threshold_uncertainty_score":0.22899142},"labels":[],"label_agreement":null},{"id":"W2753556883","doi":"10.3102/1076998617694880","title":"Normal Theory Two-Stage ML Estimator When Data Are Missing at the Item Level","year":2017,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","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":"University of British Columbia","funders":"","keywords":"Missing data; Imputation (statistics); Computer science; Estimator; Item response theory; Statistics; Structural equation modeling; Scale (ratio); Data mining; Mathematics; Psychometrics","score_opus":0.7867101434106125,"score_gpt":0.5828149761437459,"score_spread":0.20389516726686663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753556883","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":[0.9081619,0.0011025803,0.07265793,0.011534536,0.0029927094,0.0001225413,0.0025643804,0.000004346618,0.00085907284],"genre_scores_gemma":[0.59981513,0.00004100451,0.38739324,0.00023163095,0.0008218321,0.0000016754138,0.00003350991,0.0000146272905,0.011647366],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977374,0.00025950573,0.00068677467,0.00022838534,0.00090530067,0.00018263965],"domain_scores_gemma":[0.9781928,0.018461866,0.0018556779,0.00075215433,0.0005722467,0.000165235],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0055657076,0.000118587435,0.00025555887,0.00012284034,0.0012628421,0.0008040674,0.0016192683,0.00003795007,0.0013140609],"category_scores_gemma":[0.0567458,0.00006534572,0.000044216336,0.00010304786,0.00033192438,0.0005333728,0.0005340251,0.0002366546,0.000013926992],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006372855,0.00015022316,0.66263354,0.0000063024336,0.000017347998,0.000023904273,0.00023593535,0.000012935005,0.00008602172,0.0062020128,0.070501864,0.26006615],"study_design_scores_gemma":[0.00029006167,0.000059135866,0.90140474,0.000034375927,0.00006231626,0.00020228724,0.00075726776,0.00043566988,0.00001549665,0.08568881,0.01094288,0.000106984895],"about_ca_topic_score_codex":0.00009462033,"about_ca_topic_score_gemma":0.00006990803,"teacher_disagreement_score":0.3147353,"about_ca_system_score_codex":0.000041061892,"about_ca_system_score_gemma":0.00024945123,"threshold_uncertainty_score":0.99959886},"labels":[],"label_agreement":null},{"id":"W2883355895","doi":"10.3102/1076998618787478","title":"An Information Matrix Test for the Collapsing of Categories Under the Partial Credit Model","year":2018,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"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":"Goodness of fit; Econometrics; Test statistic; Set (abstract data type); Statistic; Test (biology); Polytomous Rasch model; Computer science; Statistics; Data set; Ordinal data; Mathematics; Data mining; Statistical hypothesis testing; Item response theory; Psychometrics","score_opus":0.4011186254261651,"score_gpt":0.5242410804061896,"score_spread":0.12312245498002444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883355895","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":[0.37881464,0.00012531219,0.61678547,0.0026530102,0.0011838598,0.000119117925,0.00027593327,0.0000014804052,0.000041163603],"genre_scores_gemma":[0.8819512,0.000013979592,0.117407955,0.000074784686,0.00043513166,0.0000030610877,0.0000047129333,0.0000024145756,0.0001067224],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861485,0.000060846607,0.00063749775,0.00005933132,0.000530905,0.000096590906],"domain_scores_gemma":[0.98133343,0.01600912,0.0007910629,0.00012676837,0.0016866832,0.000052948504],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022830588,0.00006016031,0.00013188098,0.00010521112,0.00034029988,0.00020581254,0.00031678955,0.000028836388,0.00007550743],"category_scores_gemma":[0.009459394,0.000027972112,0.000034346634,0.00032348593,0.00026915254,0.00036579857,0.000024090397,0.00007930985,0.0000011748167],"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":[0.0005549354,0.0010758808,0.22047916,0.000035230543,0.000074422016,7.20317e-7,0.009509777,0.0114648715,0.0015004064,0.24520731,0.16602002,0.34407726],"study_design_scores_gemma":[0.00065831066,0.001702499,0.3072648,0.00002110649,0.00022986504,0.00012172928,0.014141835,0.1149724,0.00028669037,0.554245,0.0061782715,0.00017750611],"about_ca_topic_score_codex":0.000034468718,"about_ca_topic_score_gemma":0.000011216085,"teacher_disagreement_score":0.50313663,"about_ca_system_score_codex":0.00001734176,"about_ca_system_score_gemma":0.00030078753,"threshold_uncertainty_score":0.9988843},"labels":[],"label_agreement":null},{"id":"W2897288930","doi":"10.3102/1076998618803381","title":"A Note on the Solution Multiplicity of the Vale–Maurelli Intermediate Correlation Equation","year":2018,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Statistical Methods and Applications","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Kurtosis; Skewness; Correlation; Mathematics; Range (aeronautics); Corollary; Applied mathematics; Multiplicity (mathematics); Monte Carlo method; Correlation coefficient; Statistics; Mathematical analysis; Combinatorics; Geometry","score_opus":0.16875369867003903,"score_gpt":0.44178657019405915,"score_spread":0.2730328715240201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897288930","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":[0.43598437,0.0000148025265,0.560054,0.0028672807,0.0005632939,0.00021479346,0.00019366814,0.0000023712503,0.000105390944],"genre_scores_gemma":[0.87239933,0.000009987665,0.12706651,0.000077448516,0.00028680553,0.000007842535,0.0000053698836,0.000007315264,0.00013936617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989187,0.00012757187,0.00046741252,0.00008104039,0.00031416427,0.00009111879],"domain_scores_gemma":[0.99595225,0.0026999419,0.00062786305,0.00013128399,0.00053810107,0.000050586936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047550924,0.000086320244,0.00013435613,0.000039788323,0.00020629085,0.0000211893,0.00013924894,0.000047007004,0.00015741037],"category_scores_gemma":[0.001653029,0.00004745016,0.000049215007,0.00012853893,0.00028628137,0.000049983686,0.000028161614,0.0001939377,0.0000053249405],"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":[0.00007434497,0.00075012405,0.00815862,0.000027891507,0.000020690648,2.3687686e-7,0.0011189943,0.000008454947,0.0025353988,0.95135987,0.009790992,0.026154375],"study_design_scores_gemma":[0.0002854002,0.00044374677,0.1863519,0.0001095154,0.00021138857,0.00001598402,0.00013691159,0.0049789557,0.0011883727,0.8058475,0.0003324264,0.00009788911],"about_ca_topic_score_codex":0.000025237032,"about_ca_topic_score_gemma":0.000023030794,"teacher_disagreement_score":0.436415,"about_ca_system_score_codex":0.000049789178,"about_ca_system_score_gemma":0.00010933508,"threshold_uncertainty_score":0.19789495},"labels":[],"label_agreement":null},{"id":"W2984476219","doi":"10.3102/1076998619885636","title":"Full Information Optimal Scoring","year":2019,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; McGill University","funders":"","keywords":"Statistics; Binary number; Scoring rule; Mathematics; Binary data; Scoring system; Computer science; Point (geometry); Test (biology); Mean squared error; Arithmetic; Medicine","score_opus":0.35222512895115965,"score_gpt":0.4970637307263445,"score_spread":0.14483860177518487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2984476219","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":[0.9616501,0.00010093979,0.03583035,0.00048175693,0.0014312841,0.00004471975,0.000036479527,0.000001578022,0.00042283937],"genre_scores_gemma":[0.6829764,0.00002265435,0.31636962,0.00006559618,0.00016621327,6.4294255e-7,0.000004977717,0.0000025173974,0.00039132615],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984284,0.000058916197,0.0006568306,0.000073576026,0.00067862944,0.00010362489],"domain_scores_gemma":[0.9938056,0.0046472303,0.00064886676,0.000090407455,0.00071332476,0.00009459937],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014825235,0.00006296616,0.00016791219,0.00030589695,0.00006239818,0.00019263054,0.00020509385,0.00002996433,0.0009874334],"category_scores_gemma":[0.006850415,0.000043038362,0.000035253775,0.00035271997,0.000032960605,0.00061834406,0.000039429313,0.00013469407,0.000065160646],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010397286,0.00014510387,0.6293312,0.000011061851,0.0000102350095,0.000002287975,0.00048193184,0.00025763598,0.00036547953,0.0144381765,0.014682062,0.34017086],"study_design_scores_gemma":[0.00048127113,0.00082361844,0.92581695,0.000030964515,0.000029529798,0.00026895865,0.0015639905,0.0005898121,0.000026122569,0.051628947,0.01859435,0.00014549248],"about_ca_topic_score_codex":0.000011740422,"about_ca_topic_score_gemma":7.0301604e-7,"teacher_disagreement_score":0.34002537,"about_ca_system_score_codex":0.000026369384,"about_ca_system_score_gemma":0.0001379572,"threshold_uncertainty_score":0.9999258},"labels":[],"label_agreement":null},{"id":"W346574303","doi":"10.3102/10769986030004353","title":"No Humble Pie: The Origins and Usage of a Statistical Chart","year":2005,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Data Visualization and Analytics","field":"Computer Science","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 Toronto","funders":"","keywords":"Chart; Pie chart; Appeal; Brother; Plot (graphics); History; Mathematics; Law; Statistics; Political science","score_opus":0.042396656169007806,"score_gpt":0.37864577538451666,"score_spread":0.3362491192155089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W346574303","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":[0.13843012,0.00050465704,0.85199267,0.007001874,0.00070926297,0.00014114258,0.0008370791,0.0000070902424,0.00037609335],"genre_scores_gemma":[0.6892441,0.0003219557,0.30819717,0.00047707531,0.00037501715,0.0000016492262,0.00003802744,0.000007319032,0.0013377296],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920636,0.00003201464,0.0003304651,0.00008136932,0.0002594373,0.00009036337],"domain_scores_gemma":[0.9990416,0.00022589814,0.00022370114,0.000089277906,0.0003179106,0.000101607104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002124589,0.000067736524,0.00012487943,0.00005284706,0.000085842694,0.00009665866,0.0001992416,0.000019710484,0.00016884135],"category_scores_gemma":[0.0000923306,0.000045457713,0.000015602165,0.000098474084,0.000118335454,0.0002447669,0.000052996325,0.00009534305,0.000006868682],"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":[0.0000089839505,0.0004928145,0.011624444,0.00002136917,0.00001598067,0.0000037347786,0.00043841504,0.000009272621,0.0002240103,0.92597675,0.03355467,0.027629577],"study_design_scores_gemma":[0.0021740538,0.0018284871,0.39823803,0.00017215364,0.0004148942,0.00081412966,0.00045164503,0.043152686,0.00041874597,0.051540874,0.5000622,0.0007320956],"about_ca_topic_score_codex":0.000022249322,"about_ca_topic_score_gemma":0.0000123139625,"teacher_disagreement_score":0.87443584,"about_ca_system_score_codex":0.000023262399,"about_ca_system_score_gemma":0.00019703055,"threshold_uncertainty_score":0.18537118},"labels":[],"label_agreement":null},{"id":"W4388459609","doi":"10.3102/10769986231207879","title":"Analyzing Polytomous Test Data: A Comparison Between an Information-Based IRT Model and the Generalized Partial Credit Model","year":2023,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Ottawa Hospital; McGill University","funders":"","keywords":"Polytomous Rasch model; Item response theory; Measure (data warehouse); Econometrics; Computer science; Statistics; Metric (unit); Parametric statistics; Nonparametric statistics; Scale (ratio); Psychometrics; Mathematics; Data mining","score_opus":0.5966527320784061,"score_gpt":0.5378534698798701,"score_spread":0.05879926219853593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388459609","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":[0.7339148,0.00010811729,0.26218885,0.0023088455,0.00025270323,0.00008576706,0.001116574,0.0000072829475,0.000017078748],"genre_scores_gemma":[0.82470286,0.00002844968,0.174674,0.000093751616,0.00026298722,0.0000029565656,0.00016231152,0.0000048669285,0.00006782503],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975981,0.00017973808,0.0010513297,0.00016560956,0.00082778,0.00017742728],"domain_scores_gemma":[0.98392123,0.01417947,0.00085476943,0.00027954942,0.00057943567,0.0001855418],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0043035364,0.00011506517,0.00036329142,0.00038209592,0.0003173557,0.00045083705,0.0005658611,0.00004895252,0.000029942436],"category_scores_gemma":[0.014946214,0.00006826322,0.000036912807,0.0007032066,0.00020078097,0.00071441283,0.00012642525,0.00021317448,0.0000035545374],"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":[0.00015276954,0.00021481296,0.80154586,0.00001047315,0.00002563644,0.0000021308892,0.0009728634,0.06562241,0.000034854893,0.0039854683,0.03709242,0.09034031],"study_design_scores_gemma":[0.0007622006,0.00009302018,0.13300088,0.000007692512,0.00009696215,0.000008909387,0.00033974712,0.8326971,0.0000024348037,0.032728266,0.00017604808,0.00008671821],"about_ca_topic_score_codex":0.00007898918,"about_ca_topic_score_gemma":0.000014863936,"teacher_disagreement_score":0.7670747,"about_ca_system_score_codex":0.00002056512,"about_ca_system_score_gemma":0.00038465197,"threshold_uncertainty_score":0.99335134},"labels":[],"label_agreement":null},{"id":"W4407927480","doi":"10.3102/10769986251314833","title":"Using the Information Metric to Analyze Clinical Rating Scales","year":2025,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Manitoba; Ottawa Hospital; McGill University","funders":"Vetenskapsrådet","keywords":"Rating scale; Metric (unit); Item response theory; Statistics; Computer science; Econometrics; Mathematics; Psychology; Psychometrics","score_opus":0.4986897028064809,"score_gpt":0.5681965655826773,"score_spread":0.06950686277619639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407927480","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":[0.78714406,0.0012015073,0.16400358,0.04461309,0.0019636003,0.00031193736,0.0004180362,0.0000033286344,0.0003408355],"genre_scores_gemma":[0.8548202,0.00009516462,0.1366356,0.0075372956,0.0005678709,0.000008666315,0.000025946249,0.0000071934955,0.0003020895],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963011,0.00014578087,0.0032344079,0.000097227734,0.00009543337,0.00012603994],"domain_scores_gemma":[0.9960326,0.0015938323,0.0018429869,0.000108084394,0.0003062389,0.0001162685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006545846,0.000080858605,0.00039175112,0.00040380884,0.00021455032,0.00013412365,0.00014918366,0.00005301057,0.000117238895],"category_scores_gemma":[0.004419304,0.00007183726,0.00006172382,0.00033236892,0.000060126375,0.0004193679,0.000032410484,0.00017148249,0.000041451767],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002148489,0.00020700399,0.6661284,0.000081051796,0.00006178994,3.1209407e-7,0.000768404,0.00045397264,0.0000021529297,0.25401554,0.07274819,0.005511687],"study_design_scores_gemma":[0.00057321385,0.000176201,0.91022784,0.00010967827,0.00007547694,0.000023091274,0.0021671779,0.0039107674,0.0000020624038,0.04766378,0.034869276,0.00020145382],"about_ca_topic_score_codex":0.00021034651,"about_ca_topic_score_gemma":0.00004132719,"teacher_disagreement_score":0.24409942,"about_ca_system_score_codex":0.00020351826,"about_ca_system_score_gemma":0.00035672504,"threshold_uncertainty_score":0.5290639},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4415958133","doi":"10.3102/10769986251379738","title":"Valid Standard Errors for Bayesian Quantile Regression With Clustered and Independent Data","year":2025,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","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 Toronto","funders":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs","keywords":"Jackknife resampling; Frequentist inference; Markov chain Monte Carlo; Estimator; Quantile; Quantile regression; Standard error; Bayesian probability; Point estimation; Outlier","score_opus":0.06763164808331662,"score_gpt":0.405548800795139,"score_spread":0.3379171527118224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415958133","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":[0.013932263,0.00034907408,0.9823108,0.0026929795,0.00034139623,0.0001151766,0.00023440491,0.0000025172758,0.000021421749],"genre_scores_gemma":[0.13836925,0.00005364655,0.8610973,0.0001009365,0.000058220707,0.0000028510597,0.000022851003,0.0000042856004,0.00029066482],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991559,0.000048771137,0.00027911313,0.00018892542,0.00021478215,0.000112500704],"domain_scores_gemma":[0.99897915,0.00022486002,0.00022431441,0.00020101175,0.00026784392,0.000102832026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040236878,0.00009852087,0.00018904163,0.00009743737,0.00013056013,0.00013471546,0.00032030165,0.000041572777,0.000008681649],"category_scores_gemma":[0.000056490142,0.00006587434,0.000015527427,0.00009218474,0.000054991204,0.00030316363,0.00012404606,0.000120680656,5.1394416e-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":[0.00054059236,0.0006437496,0.025099302,0.00021100558,0.000090656926,0.000026205858,0.001116701,0.000010400049,0.00037350794,0.42127842,0.04488628,0.5057232],"study_design_scores_gemma":[0.0065312125,0.003986557,0.1061385,0.0013351621,0.00087645923,0.000959446,0.00058001693,0.047078673,0.0007036491,0.8089248,0.021882929,0.0010025884],"about_ca_topic_score_codex":0.0000133472295,"about_ca_topic_score_gemma":0.000027395276,"teacher_disagreement_score":0.50472057,"about_ca_system_score_codex":0.000025859381,"about_ca_system_score_gemma":0.00038196947,"threshold_uncertainty_score":0.26862776},"labels":[],"label_agreement":null}]}