{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010669489,0.00010708132,0.9975217,0.00009190221,0.000014056357,0.00013051403,0.00009611431,0.0004930967,0.00047849328],"genre_scores_gemma":[0.021992525,0.00012584128,0.9745598,0.000103989754,0.000032942633,0.00113678,0.0005505414,0.00025428983,0.0012433245],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9870651,0.010070035,0.00048593187,0.0010507415,0.0011025907,0.00022568535],"domain_scores_gemma":[0.97932076,0.015460997,0.00065354287,0.0024516121,0.001959237,0.00015394787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019501602,0.001749702,0.0036037879,0.0031151727,0.0010710066,0.002250154,0.0057914048,0.0030237972,0.012046967],"category_scores_gemma":[0.06602999,0.0017398306,0.0028142838,0.004551479,0.0013481408,0.0031206894,0.0036699278,0.0047112713,0.0057395482],"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":[0.00043370936,0.00024543554,0.0020161388,0.00045514226,0.0006036349,0.00013703493,0.00042072948,0.27629188,0.0010520634,0.09867163,0.014284701,0.6053879],"study_design_scores_gemma":[0.00013313252,0.00008507619,0.0011398239,0.00010386304,0.000079309415,0.00014326224,0.00008607872,0.856423,0.0011949075,0.13153504,0.009004856,0.00007155325],"about_ca_topic_score_codex":0.0028900758,"about_ca_topic_score_gemma":0.0028126945,"teacher_disagreement_score":0.019501602,"about_ca_system_score_codex":0.0013348769,"about_ca_system_score_gemma":0.0025305396,"threshold_uncertainty_score":0.103135526},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042233948,0.0002517975,0.93709195,0.0019517468,0.00042592155,0.0051748925,0.0028324167,0.0011650074,0.008872296],"genre_scores_gemma":[0.4567814,0.00065369654,0.47968167,0.0013259138,0.0003850942,0.019326515,0.004809695,0.00034963552,0.036686525],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9280175,0.051935617,0.0032454326,0.008397638,0.0059695723,0.0024343033],"domain_scores_gemma":[0.9165291,0.064407475,0.0051724366,0.0070517617,0.0056937975,0.0011454651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07903546,0.0040366147,0.0040846253,0.003727707,0.0018313733,0.0059169927,0.010312115,0.005959656,0.035118144],"category_scores_gemma":[0.106844455,0.0021581468,0.005476612,0.0042530983,0.0037267138,0.006336994,0.0031469306,0.007896593,0.01406138],"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":[0.004754398,0.0027775152,0.031043025,0.0013336499,0.0011936111,0.0010687661,0.005061826,0.18246016,0.002387007,0.5967607,0.017384594,0.1537747],"study_design_scores_gemma":[0.0008317665,0.0012690075,0.005186636,0.00015772182,0.00021907617,0.000509973,0.00047392852,0.7621812,0.00074368744,0.2168553,0.011327926,0.00024367357],"about_ca_topic_score_codex":0.005502418,"about_ca_topic_score_gemma":0.0047008055,"teacher_disagreement_score":0.07903546,"about_ca_system_score_codex":0.004472696,"about_ca_system_score_gemma":0.0037247636,"threshold_uncertainty_score":0.4179845},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022687479,0.98197144,0.0064379047,0.004947853,0.0023475408,0.00013571417,0.00046583818,0.00019573187,0.0032711125],"genre_scores_gemma":[0.0013377614,0.9837337,0.0074059675,0.0037259543,0.0014523306,0.00033291336,0.0005129966,0.000091999915,0.0014063743],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99078137,0.002808318,0.002155339,0.0006275773,0.00344197,0.0001853192],"domain_scores_gemma":[0.96287584,0.025911786,0.002354263,0.0005204412,0.007931942,0.0004057728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008417669,0.0011563033,0.00211762,0.011557201,0.00060481083,0.0020935605,0.0018449578,0.0014855673,0.0070225475],"category_scores_gemma":[0.025758538,0.00085043564,0.002174181,0.014914216,0.0015746295,0.0034317055,0.0011193762,0.0027694127,0.005406169],"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":[0.000043580447,0.00006170353,0.00060127286,0.05658716,0.0001836563,0.00014475771,0.0004870633,0.000353054,0.00076749735,0.0050733946,0.21993007,0.7157668],"study_design_scores_gemma":[0.000009462178,0.00010329531,0.004357127,0.035277374,0.00015130031,0.00043062476,0.00025594665,0.00019574785,0.0003598229,0.002523433,0.9562827,0.00005323874],"about_ca_topic_score_codex":0.0050575193,"about_ca_topic_score_gemma":0.00720306,"teacher_disagreement_score":0.011557201,"about_ca_system_score_codex":0.0025444974,"about_ca_system_score_gemma":0.0069462815,"threshold_uncertainty_score":0.044517398},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013277782,0.00077998714,0.99541986,0.00049573067,0.00010898776,0.001274565,0.000064178595,0.0001848704,0.0003439629],"genre_scores_gemma":[0.046786215,0.00077626103,0.9432451,0.0006357772,0.00023674694,0.0076875435,0.00015636874,0.00009665392,0.0003793122],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.70711136,0.2725939,0.0061044325,0.006005429,0.007532097,0.0006527388],"domain_scores_gemma":[0.4853451,0.49092302,0.006569588,0.011562249,0.0047733234,0.00082682865],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23238614,0.0024863333,0.00945213,0.005913597,0.0013537904,0.0032596006,0.0066126045,0.005829132,0.004191216],"category_scores_gemma":[0.4642672,0.0021016852,0.0043287906,0.0041865674,0.0042220885,0.0038084793,0.0030971253,0.007025414,0.00087242323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050512613,0.0006249609,0.0050513935,0.00515365,0.005032888,0.0004529592,0.0013528618,0.20811112,0.0008937987,0.3569687,0.012419473,0.39888695],"study_design_scores_gemma":[0.0021026435,0.00089136156,0.00094869424,0.0013591778,0.0010133258,0.000236837,0.00008255611,0.48694366,0.0010209993,0.49990848,0.00534665,0.00014563886],"about_ca_topic_score_codex":0.0027655435,"about_ca_topic_score_gemma":0.0021563978,"teacher_disagreement_score":0.7676139,"about_ca_system_score_codex":0.0025587135,"about_ca_system_score_gemma":0.005226885,"threshold_uncertainty_score":0.94660455},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008676873,0.013287659,0.97414,0.00053930486,0.00026626838,0.000100704936,0.00034004386,0.00043242096,0.0022167366],"genre_scores_gemma":[0.45793518,0.014412662,0.5204049,0.00048962905,0.0015867627,0.0011862523,0.0018466024,0.0006977693,0.0014402024],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9037481,0.07285565,0.0034340143,0.00540918,0.013790962,0.0007620077],"domain_scores_gemma":[0.3562389,0.6088876,0.012675598,0.012603279,0.009004243,0.0005903803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07495872,0.0015902936,0.002788023,0.007605434,0.0007629839,0.003755733,0.00519698,0.0035184163,0.004078543],"category_scores_gemma":[0.54239416,0.0008657075,0.002264155,0.008394957,0.0034082653,0.0052652056,0.0035480373,0.006080374,0.0011134063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007811586,0.00016214796,0.016037708,0.0030917544,0.0013298788,0.0005310364,0.0011331602,0.11219167,0.0009386392,0.44592446,0.009297959,0.40858042],"study_design_scores_gemma":[0.00015374467,0.0004538293,0.013978754,0.0024338018,0.00060473045,0.0011519293,0.0003909432,0.26595885,0.0024764575,0.6989138,0.013206204,0.00027694184],"about_ca_topic_score_codex":0.0014779676,"about_ca_topic_score_gemma":0.00060725876,"teacher_disagreement_score":0.07495872,"about_ca_system_score_codex":0.0013632404,"about_ca_system_score_gemma":0.0009546171,"threshold_uncertainty_score":0.39642435},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008071425,0.0006852314,0.9799565,0.0012154337,0.00018687024,0.00014841177,0.0002264343,0.00018243802,0.0093272645],"genre_scores_gemma":[0.42919055,0.0019957626,0.5564993,0.0020031622,0.0013777934,0.002803,0.0009638516,0.00033589854,0.0048306976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9454123,0.025814168,0.0036260244,0.008717971,0.0152747845,0.0011547116],"domain_scores_gemma":[0.7803366,0.17759596,0.0069361622,0.021028407,0.013261014,0.00084174244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053156987,0.0010017873,0.0025752943,0.003622723,0.0017896148,0.004700808,0.0044698673,0.0024844736,0.0037773058],"category_scores_gemma":[0.2204103,0.0009779917,0.0021964451,0.0029545226,0.013548639,0.006757646,0.0054875407,0.006206825,0.001098517],"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":[0.000042283373,0.00003965172,0.0032279708,0.00017998517,0.0001002532,0.00012574329,0.00062329025,0.013055149,0.0002898854,0.9496275,0.0015595646,0.031128693],"study_design_scores_gemma":[0.000034924265,0.000042738684,0.00165175,0.0001081217,0.000025744175,0.00020026318,0.000068418,0.03201616,0.00036945983,0.96150136,0.0039439183,0.00003709803],"about_ca_topic_score_codex":0.003161281,"about_ca_topic_score_gemma":0.0014039249,"teacher_disagreement_score":0.053156987,"about_ca_system_score_codex":0.0028446838,"about_ca_system_score_gemma":0.0027949214,"threshold_uncertainty_score":0.28112435},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006436783,0.015702724,0.7301543,0.03648999,0.044417888,0.0020900303,0.0059323367,0.0071464134,0.15162961],"genre_scores_gemma":[0.057624724,0.02165396,0.5773421,0.026411213,0.027263125,0.0046481784,0.007135786,0.00539857,0.27252236],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99903786,0.0004347351,0.00008385306,0.000103992315,0.00026739945,0.00007216841],"domain_scores_gemma":[0.9956008,0.0031368742,0.00015771156,0.00018355434,0.0007301862,0.0001908938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028528192,0.0019054773,0.0009796853,0.0024444703,0.0005872955,0.0017424154,0.0011307283,0.0016165513,0.09426639],"category_scores_gemma":[0.011097103,0.00047138167,0.00096819416,0.0018719736,0.0009877152,0.0022808372,0.0017936161,0.0035699236,0.034035336],"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":[0.0000858095,0.00012843567,0.00035102028,0.00042866837,0.000014379838,0.00025728822,0.00029270205,0.0011283916,0.0024000113,0.02847487,0.8064011,0.1600375],"study_design_scores_gemma":[0.000048932932,0.00023663243,0.0016604734,0.00040809132,0.000010698464,0.00093294884,0.0002716269,0.0039251936,0.0018922095,0.043541096,0.946999,0.000073052186],"about_ca_topic_score_codex":0.0008216156,"about_ca_topic_score_gemma":0.0010876397,"teacher_disagreement_score":0.09426639,"about_ca_system_score_codex":0.0011397798,"about_ca_system_score_gemma":0.0007098341,"threshold_uncertainty_score":0.3153525},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028261289,0.000444679,0.9898032,0.0015509549,0.00012687535,0.00027564337,0.00034829503,0.00016693985,0.004457254],"genre_scores_gemma":[0.30399114,0.0026627125,0.67595255,0.0012065938,0.00056130555,0.0047147344,0.0008111545,0.00016994316,0.0099299885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9741587,0.02094092,0.00065797794,0.0018577422,0.0017347127,0.00064991263],"domain_scores_gemma":[0.9719686,0.024042001,0.0011943444,0.0013036216,0.0012191634,0.0002723118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021991225,0.0018888426,0.0025147423,0.0035360593,0.0019352022,0.0035961918,0.0045066085,0.0027282697,0.017273128],"category_scores_gemma":[0.042080414,0.0008357617,0.0041344687,0.0048202886,0.0025097798,0.003965222,0.003962656,0.0060590412,0.0014056861],"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":[0.000064507054,0.00014558004,0.002885143,0.0002528592,0.00065303955,0.00017669851,0.0010246547,0.023088135,0.00021556328,0.93713224,0.0026509238,0.031710632],"study_design_scores_gemma":[0.00008039114,0.00019260056,0.0011167299,0.00012850107,0.0002853728,0.00013431396,0.00037326306,0.16973357,0.00031214653,0.8154033,0.012174142,0.00006570708],"about_ca_topic_score_codex":0.007519131,"about_ca_topic_score_gemma":0.005909486,"teacher_disagreement_score":0.021991225,"about_ca_system_score_codex":0.002779241,"about_ca_system_score_gemma":0.005693382,"threshold_uncertainty_score":0.11630207},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024238849,0.083992876,0.043189153,0.7449782,0.019133067,0.000040042716,0.00010851509,0.0005930976,0.083726235],"genre_scores_gemma":[0.58982843,0.07514531,0.04078512,0.14688993,0.017345801,0.00013222525,0.00015410302,0.0017012055,0.12801798],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927994,0.003636511,0.00016180324,0.001003903,0.0021157612,0.00028262695],"domain_scores_gemma":[0.9892046,0.0048022848,0.00029148682,0.0006749217,0.0035409993,0.0014857572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077788904,0.00054467615,0.0004914824,0.0019203502,0.0037173461,0.010893338,0.0009921272,0.0026917027,0.002084845],"category_scores_gemma":[0.017885882,0.00044562537,0.00030622352,0.0015181828,0.020335378,0.008637617,0.0026818847,0.010796824,0.0009145509],"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":[0.000071383096,0.000031700056,0.0010550927,0.00010648798,0.000018095508,0.00016848919,0.015282031,0.00060281216,0.0005962305,0.66434044,0.26113507,0.05659218],"study_design_scores_gemma":[0.0000063083185,0.000018614812,0.00044797763,0.000117232026,0.0000052694304,0.00023500681,0.0030490365,0.0006395676,0.0004850475,0.08290281,0.9120478,0.0000453059],"about_ca_topic_score_codex":0.015265973,"about_ca_topic_score_gemma":0.010402511,"teacher_disagreement_score":0.015265973,"about_ca_system_score_codex":0.0047343397,"about_ca_system_score_gemma":0.0031627466,"threshold_uncertainty_score":0.041139245},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045422096,0.0005993607,0.9411324,0.0008609215,0.000081403174,0.00009745322,0.0011779888,0.007209174,0.003419185],"genre_scores_gemma":[0.476968,0.0003972104,0.51800996,0.00018966074,0.000086858774,0.00056636846,0.0014193594,0.0016535271,0.0007090417],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934227,0.004398646,0.00045496316,0.0006134483,0.0009082674,0.00020194626],"domain_scores_gemma":[0.7544731,0.22388642,0.0066142725,0.00941151,0.0049574412,0.00065729907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029350163,0.0014967303,0.0009907278,0.0064689913,0.00063807116,0.004023313,0.0018815644,0.0023276352,0.01476543],"category_scores_gemma":[0.19890663,0.000833546,0.0012455775,0.0027322099,0.0013178745,0.0038812049,0.0035388814,0.0030863008,0.0010846979],"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":[0.001673808,0.0003431661,0.03081997,0.002134844,0.00047028039,0.00088384683,0.011039797,0.16350593,0.0082697505,0.24456997,0.027955964,0.5083327],"study_design_scores_gemma":[0.00022041149,0.00025018255,0.01793371,0.0010572983,0.00015915313,0.0007301744,0.002012985,0.7340534,0.00976091,0.21692,0.016654545,0.00024733163],"about_ca_topic_score_codex":0.0026883243,"about_ca_topic_score_gemma":0.0014957978,"teacher_disagreement_score":0.029350163,"about_ca_system_score_codex":0.0008420997,"about_ca_system_score_gemma":0.0007889753,"threshold_uncertainty_score":0.15522033},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004347945,0.018476756,0.9604444,0.0021842304,0.00034937332,0.00032922786,0.00054053724,0.0010710444,0.012256424],"genre_scores_gemma":[0.077667885,0.024662415,0.888955,0.0005629061,0.0008259509,0.0008835557,0.0007666175,0.00061626325,0.005059389],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99268097,0.0036390575,0.00046680612,0.0010713818,0.001987218,0.00015449106],"domain_scores_gemma":[0.9843008,0.0105586955,0.00068713917,0.0015919353,0.0025843703,0.000277141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009481243,0.0022749722,0.0019426959,0.005548128,0.0013607416,0.003312462,0.0018870769,0.0021988824,0.0066000936],"category_scores_gemma":[0.036321595,0.0010516469,0.0021533496,0.014185689,0.0026160134,0.0027529267,0.0027596096,0.003035407,0.0026126155],"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":[0.000105312196,0.00011459812,0.003751042,0.0012143841,0.0005227643,0.00027819327,0.00090134714,0.0207899,0.0016857667,0.1997559,0.021454925,0.7494259],"study_design_scores_gemma":[0.00006702314,0.00009704051,0.008079606,0.00092098716,0.00018734933,0.00078239525,0.0005961031,0.13596225,0.0028908057,0.69490236,0.1552554,0.00025872234],"about_ca_topic_score_codex":0.0045851823,"about_ca_topic_score_gemma":0.0038165206,"teacher_disagreement_score":0.009481243,"about_ca_system_score_codex":0.0011704554,"about_ca_system_score_gemma":0.0023529385,"threshold_uncertainty_score":0.05014217},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015271396,0.0006198671,0.9755401,0.0029743847,0.00035035354,0.00088344666,0.0004293776,0.0003470318,0.0035840345],"genre_scores_gemma":[0.5496599,0.0012213666,0.4304256,0.0028819789,0.0007323166,0.0059966263,0.000924338,0.00014314365,0.008014728],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8490179,0.11867663,0.004138808,0.015832707,0.009528828,0.0028051408],"domain_scores_gemma":[0.2989704,0.6427408,0.018288147,0.03437829,0.0043442794,0.0012781394],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.16117488,0.0022657975,0.0050900006,0.0061609927,0.0032406405,0.005192946,0.007568586,0.006844993,0.01879952],"category_scores_gemma":[0.4561103,0.0026512812,0.008715903,0.0056766276,0.008048142,0.008796516,0.0074172285,0.011591155,0.00094330194],"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":[0.0007705242,0.0008460152,0.020394096,0.00070870953,0.004217661,0.0007455058,0.0015120894,0.037631743,0.00038929022,0.86069924,0.0031282376,0.06895687],"study_design_scores_gemma":[0.0005887452,0.0003070641,0.0037664392,0.00018351483,0.0012148233,0.00017084384,0.00032237908,0.14704902,0.0007898217,0.8415756,0.003939868,0.00009178651],"about_ca_topic_score_codex":0.01279165,"about_ca_topic_score_gemma":0.008609131,"teacher_disagreement_score":0.8388251,"about_ca_system_score_codex":0.005432348,"about_ca_system_score_gemma":0.0052339435,"threshold_uncertainty_score":0.85238445},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018380639,0.021312786,0.8132481,0.011794422,0.006452147,0.00021570834,0.05632377,0.02984296,0.058972143],"genre_scores_gemma":[0.066427335,0.029389605,0.7104236,0.0090976,0.004897903,0.0022100983,0.060709544,0.041162364,0.075682014],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951266,0.001903741,0.0004260753,0.001370261,0.0009852861,0.0001879865],"domain_scores_gemma":[0.972514,0.018349815,0.0019339925,0.004783027,0.002052185,0.0003669098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004546951,0.0020765944,0.001617466,0.0041247597,0.0009857847,0.0032204906,0.0026172616,0.0013742684,0.19391346],"category_scores_gemma":[0.049013715,0.0018819924,0.0018653583,0.007719184,0.0025222928,0.0048684427,0.0023895258,0.0033545818,0.10320996],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006236671,0.00002554584,0.0005030205,0.0016987526,0.0001285346,0.0001605347,0.00029441877,0.0012670542,0.0011255312,0.056798648,0.776827,0.16110855],"study_design_scores_gemma":[0.000026476766,0.000028978155,0.0008741133,0.0005413236,0.000097448705,0.00064590626,0.00011730301,0.0037952755,0.0017116192,0.15641756,0.8356753,0.00006873801],"about_ca_topic_score_codex":0.0035121895,"about_ca_topic_score_gemma":0.006092787,"teacher_disagreement_score":0.19391346,"about_ca_system_score_codex":0.0009720983,"about_ca_system_score_gemma":0.0021002835,"threshold_uncertainty_score":0.6487051},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042714545,0.90177435,0.088705346,0.004190369,0.001380106,0.000069554706,0.00036279514,0.00023785222,0.0028525097],"genre_scores_gemma":[0.009102348,0.88241297,0.09941091,0.0023542107,0.0040846053,0.00029506558,0.00057067524,0.00021344303,0.0015557178],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944042,0.0029782816,0.0006509211,0.0006582084,0.0011994969,0.00010887209],"domain_scores_gemma":[0.9620807,0.03275604,0.0009433,0.0011134385,0.0028585556,0.0002479794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013357229,0.0016360064,0.0034557676,0.005047064,0.0005738135,0.0026861401,0.0035191535,0.0028573165,0.0054786876],"category_scores_gemma":[0.043147206,0.000776138,0.0017483342,0.009561797,0.001931791,0.0033066107,0.0014815136,0.0029053797,0.0025391502],"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":[0.00006191229,0.00009493366,0.0009842925,0.0119635165,0.00040986828,0.00005711754,0.00015079598,0.006148567,0.00026916977,0.064689085,0.050560385,0.86461025],"study_design_scores_gemma":[0.00009130361,0.00022348907,0.0034496768,0.012267887,0.0007464599,0.00059384725,0.00014903833,0.028642887,0.0011040698,0.19284914,0.7596238,0.000258317],"about_ca_topic_score_codex":0.008697914,"about_ca_topic_score_gemma":0.009047463,"teacher_disagreement_score":0.013357229,"about_ca_system_score_codex":0.0020129748,"about_ca_system_score_gemma":0.0044593974,"threshold_uncertainty_score":0.070640564},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005215624,0.0003380952,0.97236055,0.0034290338,0.0016140839,0.00017807042,0.00020242434,0.0014035741,0.015258596],"genre_scores_gemma":[0.050226778,0.00036372634,0.9291699,0.0022523971,0.0005779189,0.00054389203,0.00020293731,0.0009847139,0.01567776],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.982139,0.0075884038,0.0011706854,0.0028667424,0.005739508,0.0004956961],"domain_scores_gemma":[0.97600126,0.007075582,0.0011432203,0.010936955,0.004311268,0.0005316912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013685287,0.0017717715,0.0018022234,0.0023710309,0.0020588846,0.0035447548,0.004011787,0.0024235316,0.016111156],"category_scores_gemma":[0.06521629,0.0008339519,0.0015607398,0.003568006,0.0037616682,0.0060215066,0.0056478265,0.0063064885,0.013279367],"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":[0.00017326839,0.00015540316,0.002082339,0.00020488798,0.000094056544,0.00021335397,0.0011395776,0.0021570523,0.004331016,0.4847489,0.029835025,0.47486517],"study_design_scores_gemma":[0.000097805154,0.0004954731,0.0017713208,0.00038411064,0.00012838565,0.0020606553,0.0006682329,0.029566737,0.011647803,0.6267201,0.3262393,0.00022005323],"about_ca_topic_score_codex":0.0014434556,"about_ca_topic_score_gemma":0.0018976253,"teacher_disagreement_score":0.016111156,"about_ca_system_score_codex":0.0008813047,"about_ca_system_score_gemma":0.0025948503,"threshold_uncertainty_score":0.072375596},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019140613,0.00018769426,0.9958961,0.00020006375,0.00005970052,0.0001345929,0.00016697771,0.0003547847,0.0010860811],"genre_scores_gemma":[0.14630787,0.00062573317,0.84332246,0.0006569746,0.00028992162,0.0020156791,0.0013921941,0.00045375383,0.0049354318],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9810091,0.013195972,0.00079935056,0.002517763,0.0020759334,0.00040187777],"domain_scores_gemma":[0.95101696,0.03762055,0.0020335903,0.0055203224,0.00350185,0.00030665722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018418102,0.0014778213,0.0024571735,0.0019160412,0.00085642765,0.0025270514,0.0043689148,0.0019123883,0.013154818],"category_scores_gemma":[0.11934724,0.0011062472,0.001740258,0.0027057878,0.0018971241,0.00445031,0.0031738502,0.004076978,0.0040656268],"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":[0.00050740567,0.00027096004,0.023714554,0.001245891,0.0010710031,0.00039716993,0.001200187,0.06920498,0.00220298,0.2860189,0.023161221,0.5910047],"study_design_scores_gemma":[0.00024205096,0.0003528495,0.0063188574,0.00036973518,0.0003339411,0.0006685191,0.00036761645,0.6173984,0.0030687342,0.3422989,0.028455295,0.00012514],"about_ca_topic_score_codex":0.003332593,"about_ca_topic_score_gemma":0.0032068626,"teacher_disagreement_score":0.018418102,"about_ca_system_score_codex":0.001208666,"about_ca_system_score_gemma":0.0032401446,"threshold_uncertainty_score":0.09740543},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.113961376,0.00024185363,0.8730437,0.00094714446,0.00015611044,0.0016234218,0.0014893244,0.0007975931,0.0077395146],"genre_scores_gemma":[0.6432201,0.00014795153,0.34912395,0.00037548863,0.00012279072,0.004400617,0.0015067427,0.00016584457,0.0009365577],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9122729,0.058526523,0.005013337,0.00737509,0.015773756,0.0010384535],"domain_scores_gemma":[0.57165706,0.38544247,0.012623166,0.017628541,0.011196595,0.0014522187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05811315,0.0014334578,0.0021065169,0.0061134654,0.0019368645,0.0021657743,0.0032129714,0.0022733957,0.010277887],"category_scores_gemma":[0.37201667,0.00059993943,0.0030528812,0.005725828,0.004417795,0.005729861,0.0032292397,0.003965284,0.0010757606],"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":[0.0033976038,0.0010412353,0.1917419,0.0016906956,0.005430215,0.0014483983,0.006066375,0.03718402,0.005414763,0.23921773,0.018357484,0.48900962],"study_design_scores_gemma":[0.0006875629,0.0050855163,0.110577546,0.00074656354,0.0010647983,0.0018402928,0.0028965306,0.4848767,0.008692978,0.36785692,0.015202809,0.00047185074],"about_ca_topic_score_codex":0.0014080798,"about_ca_topic_score_gemma":0.0009767867,"teacher_disagreement_score":0.05811315,"about_ca_system_score_codex":0.0015550465,"about_ca_system_score_gemma":0.0029558407,"threshold_uncertainty_score":0.30733538},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004680337,0.0018195737,0.9646783,0.013049362,0.0013241252,0.0001226561,0.00013362749,0.0003072402,0.013884788],"genre_scores_gemma":[0.11179204,0.0025198888,0.8665367,0.0043564797,0.0020033747,0.0009977042,0.00026049017,0.00082267745,0.010710585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98158365,0.011550152,0.0008983054,0.0019894722,0.0033559238,0.0006224597],"domain_scores_gemma":[0.832273,0.14861715,0.0035952711,0.006602287,0.007841838,0.0010704083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026263947,0.001409681,0.0019271261,0.001918107,0.001909378,0.0038909083,0.003455032,0.00394844,0.012664878],"category_scores_gemma":[0.2144321,0.0009877415,0.0033119882,0.001652428,0.0042793322,0.0063380566,0.0053239167,0.013345564,0.0023844785],"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":[0.0001749624,0.00005738802,0.0027896871,0.00023729146,0.00008477033,0.00053507515,0.00066375796,0.02564754,0.0011583011,0.8814385,0.027893187,0.05931959],"study_design_scores_gemma":[0.000115141156,0.000100914855,0.00069175934,0.00036494833,0.000065261185,0.0005055419,0.00013084784,0.24669413,0.0020888867,0.70501083,0.044105195,0.00012655821],"about_ca_topic_score_codex":0.0037387311,"about_ca_topic_score_gemma":0.0027552983,"teacher_disagreement_score":0.026263947,"about_ca_system_score_codex":0.0022197478,"about_ca_system_score_gemma":0.003698148,"threshold_uncertainty_score":0.13889873},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01673786,0.00075862586,0.97392184,0.000400008,0.00013119192,0.0002541391,0.00044970805,0.0008231261,0.0065236334],"genre_scores_gemma":[0.24187031,0.0005096319,0.752017,0.00038767312,0.00014721627,0.000469653,0.0011533697,0.00028626062,0.0031588573],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9652968,0.02029377,0.0024608597,0.0034394413,0.007267433,0.0012417862],"domain_scores_gemma":[0.9579268,0.020642584,0.0017733691,0.0125167845,0.0065827006,0.0005577871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017101845,0.0016851167,0.0028130768,0.003399915,0.00067750795,0.0030399864,0.00262526,0.0019288274,0.007401206],"category_scores_gemma":[0.08574058,0.0012577369,0.0017100697,0.00326302,0.0021258844,0.004608592,0.005312946,0.0025284835,0.0026428644],"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":[0.0010346423,0.00029460137,0.0051100347,0.0003187716,0.00035886286,0.00015249444,0.00024515207,0.060256533,0.0032226215,0.07308504,0.012330278,0.843591],"study_design_scores_gemma":[0.0003189293,0.0005077505,0.00534604,0.00019568115,0.00020751868,0.00063190685,0.000095576965,0.6658161,0.0079523,0.30887842,0.009813498,0.00023616079],"about_ca_topic_score_codex":0.001229944,"about_ca_topic_score_gemma":0.0012233439,"teacher_disagreement_score":0.017101845,"about_ca_system_score_codex":0.0011860806,"about_ca_system_score_gemma":0.0019943034,"threshold_uncertainty_score":0.09044427},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014606046,0.028059352,0.62173665,0.16139059,0.0149116125,0.00015297963,0.00093755184,0.0021720324,0.1560332],"genre_scores_gemma":[0.49128962,0.02564791,0.38053882,0.033106178,0.013479241,0.0006860345,0.00077941216,0.0048967106,0.04957599],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97622174,0.01678538,0.0011221062,0.0014175853,0.0039876797,0.0004655734],"domain_scores_gemma":[0.9071105,0.07603705,0.0024724808,0.005217673,0.008090166,0.0010720544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022867283,0.00081643846,0.00084471965,0.0047551207,0.0044705337,0.013573012,0.0018737682,0.003241984,0.0053199613],"category_scores_gemma":[0.1627503,0.0006267175,0.0005617901,0.006441672,0.024601242,0.0135918455,0.0033964782,0.007020762,0.0014325898],"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":[0.000038845592,0.0000043190753,0.00034233465,0.000057181933,0.000005506987,0.00006054685,0.0035839947,0.00027603042,0.000062352876,0.93566173,0.025672195,0.034234945],"study_design_scores_gemma":[0.000011726277,0.000023582537,0.00056120136,0.00050717435,0.000010572423,0.00022366403,0.0018310145,0.0018762993,0.00041603527,0.64866996,0.34579447,0.00007437781],"about_ca_topic_score_codex":0.0065643424,"about_ca_topic_score_gemma":0.006607598,"teacher_disagreement_score":0.022867283,"about_ca_system_score_codex":0.0031351026,"about_ca_system_score_gemma":0.004699576,"threshold_uncertainty_score":0.12093514},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11371331,0.0010034799,0.8789225,0.0018855943,0.00008104289,0.00035507255,0.00063125574,0.0006039861,0.0028037247],"genre_scores_gemma":[0.7795544,0.0007486405,0.21343723,0.00079952565,0.00020000827,0.0009446088,0.0019148379,0.0003331674,0.002067592],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9712602,0.022627445,0.0007140627,0.0025297718,0.0024053925,0.00046320516],"domain_scores_gemma":[0.80242217,0.16763605,0.006324875,0.017628253,0.005020687,0.00096797996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044644922,0.001527421,0.002679079,0.003378359,0.00061465875,0.0033542153,0.0049562664,0.002458462,0.0030599134],"category_scores_gemma":[0.16413186,0.0006520514,0.0025641639,0.0049345186,0.00372733,0.006465808,0.0023780162,0.003794333,0.0008178997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011049462,0.00041794594,0.042959593,0.00062124874,0.0011700921,0.0003772958,0.001325476,0.58489835,0.0005742207,0.17575763,0.003993157,0.18680006],"study_design_scores_gemma":[0.00008228224,0.00020227025,0.005854757,0.000069850685,0.00009238995,0.00013791239,0.0001582688,0.89071995,0.00019639848,0.101383165,0.0010420935,0.000060612885],"about_ca_topic_score_codex":0.0065431944,"about_ca_topic_score_gemma":0.0046897666,"teacher_disagreement_score":0.044644922,"about_ca_system_score_codex":0.0024614974,"about_ca_system_score_gemma":0.0025032882,"threshold_uncertainty_score":0.2361077},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011137136,0.00043911472,0.9840528,0.00045822983,0.00009330142,0.0002699465,0.00043199677,0.00028720064,0.002830205],"genre_scores_gemma":[0.33457717,0.0005482316,0.6603304,0.00036427018,0.00028229385,0.0014584286,0.001131764,0.00026091686,0.0010464117],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95480096,0.02688146,0.003901229,0.0027043635,0.011268665,0.0004433709],"domain_scores_gemma":[0.8152895,0.14828481,0.011781442,0.010851327,0.012912103,0.0008807812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036445055,0.0012057992,0.0013551668,0.009503247,0.00074979186,0.004079932,0.0014353264,0.001290756,0.0032220506],"category_scores_gemma":[0.22853899,0.00043701686,0.001498742,0.007772556,0.0029181617,0.0044313157,0.002610361,0.0026147172,0.00077122345],"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":[0.0003739272,0.00020906536,0.0397396,0.0010394923,0.00077025685,0.00061608147,0.002791192,0.08574845,0.0038980332,0.37667963,0.011095944,0.47703832],"study_design_scores_gemma":[0.000066017376,0.0006320915,0.021648495,0.0003352006,0.00014636498,0.0008917175,0.000920725,0.42073593,0.0029163992,0.5337713,0.017714262,0.00022155743],"about_ca_topic_score_codex":0.0012593475,"about_ca_topic_score_gemma":0.0007355437,"teacher_disagreement_score":0.036445055,"about_ca_system_score_codex":0.001918244,"about_ca_system_score_gemma":0.0016018144,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028117797,0.0004435461,0.9931297,0.00029620173,0.00025162322,0.0001320526,0.00064900797,0.0008448527,0.0014411904],"genre_scores_gemma":[0.14163673,0.0007392753,0.84641343,0.0006730799,0.00037830215,0.0022873078,0.0025151004,0.0022428082,0.003114006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9565806,0.024219332,0.0035390456,0.0057944995,0.009026025,0.0008405149],"domain_scores_gemma":[0.8116549,0.12770726,0.010749993,0.037171956,0.012067279,0.00064852886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053176068,0.0013013509,0.0020027338,0.0038764074,0.0011703833,0.002895397,0.0058164764,0.0029263953,0.010972299],"category_scores_gemma":[0.39095286,0.0012024312,0.002859199,0.0055541424,0.0021525524,0.0038770335,0.0028839263,0.0058898735,0.003888691],"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":[0.0001941081,0.00021377575,0.01591968,0.00096739543,0.0012514497,0.00032435238,0.0011448201,0.075396106,0.0013314144,0.56248987,0.041567065,0.2991999],"study_design_scores_gemma":[0.00012941676,0.00013707097,0.009859416,0.000921212,0.00031918712,0.00036346784,0.00030070523,0.17319387,0.0047430354,0.761743,0.04811629,0.00017326765],"about_ca_topic_score_codex":0.0046221167,"about_ca_topic_score_gemma":0.004356858,"teacher_disagreement_score":0.053176068,"about_ca_system_score_codex":0.0019463855,"about_ca_system_score_gemma":0.0023777788,"threshold_uncertainty_score":0.28122526},"labels":[],"label_agreement":null}]}