{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":23,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":23,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"4243585afc1b","filters":{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04016072169252984,"gpt":0.3276923298278803,"spread":0.2875316081353504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002367016,0.0001017052,0.0001256791,0.0001164896,0.0001545596,0.0001375177,0.0002475368,0.00002822946,0.00005153548],"category_scores_gemma":[0.0002468632,0.00006138431,0.00001939996,0.0002857575,0.00008718952,0.0002781533,0.00003744834,0.0001950296,0.000004482206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004993348,"about_ca_system_score_gemma":0.00006483467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004804062,"about_ca_topic_score_gemma":0.000001930778,"domain_scores_codex":[0.9991051,0.00005468952,0.000253175,0.000119785,0.0003385851,0.0001286958],"domain_scores_gemma":[0.9976794,0.00143979,0.0002343457,0.0001281518,0.0004210392,0.00009724648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002066617,0.0009289916,0.00283719,0.00001468891,0.00003723162,0.00005592685,0.000888517,0.000295309,0.0001995173,0.08028142,0.02910387,0.8851507],"study_design_scores_gemma":[0.001356673,0.008359618,0.2068509,0.0001618665,0.000410806,0.002340511,0.0003867111,0.3803353,0.0002387858,0.3923741,0.006299386,0.0008853262],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0230548,0.0002626267,0.9742236,0.00220577,0.0001382485,0.00006186457,0.0000332768,0.00001227181,0.000007508635],"genre_scores_gemma":[0.2300448,0.00002357164,0.7696162,0.0001092655,0.00005559497,0.000004657418,0.000001910967,0.000005596242,0.000138416],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8842654,"threshold_uncertainty_score":0.2503179,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08936654137525234,"gpt":0.4135590799087178,"spread":0.3241925385334655,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001147589,0.00005715784,0.00009722733,0.00005447289,0.0004758042,0.00002842076,0.00006788928,0.00003600422,0.0004669715],"category_scores_gemma":[0.0001371019,0.00004974733,0.00002725883,0.00006926066,0.0001399727,0.0002684446,0.000006154937,0.00007773375,0.000008491247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006963133,"about_ca_system_score_gemma":0.0007239177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001885744,"about_ca_topic_score_gemma":0.00005884775,"domain_scores_codex":[0.9993528,0.00002122459,0.0002052804,0.00005884902,0.0002486323,0.0001131771],"domain_scores_gemma":[0.9990662,0.0002701001,0.0001650904,0.00002578422,0.0003573429,0.0001154823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001604055,0.0007930362,0.8915326,0.00001864141,0.00005920235,0.00001016738,0.0054138,0.00003018878,0.0003642583,0.02561071,0.04111246,0.03489453],"study_design_scores_gemma":[0.001338692,0.0006704963,0.9266776,0.00005183799,0.0001738916,0.0002144054,0.0004947408,0.00007052416,0.00006835662,0.02067322,0.04928864,0.0002776191],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974995,0.000101049,0.0004716234,0.0009482193,0.0004917372,0.0000673259,0.0001372322,0.000002177413,0.0002811809],"genre_scores_gemma":[0.9389415,0.0004097764,0.05440943,0.00008838187,0.001690017,0.000009202104,0.00004983905,0.000006673122,0.004395146],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05855792,"threshold_uncertainty_score":0.511301,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5866905625763341,"gpt":0.5681326453150991,"spread":0.01855791726123501,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001934876,0.00009649088,0.0002472943,0.0004270692,0.0001393793,0.0002575074,0.0003133421,0.0000373992,0.0003475581],"category_scores_gemma":[0.04071126,0.00006302931,0.000053574,0.0005408177,0.00004361416,0.0002244372,0.00005324061,0.0001052036,0.00002547736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003261423,"about_ca_system_score_gemma":0.0002488319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000560406,"about_ca_topic_score_gemma":0.000007992173,"domain_scores_codex":[0.9981045,0.00008530316,0.0007773568,0.0001748197,0.0006935392,0.0001645255],"domain_scores_gemma":[0.9742002,0.02290869,0.0004387491,0.0001403594,0.002069937,0.0002420754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000438651,0.0004316139,0.09845335,0.000005633981,0.00001238768,0.00000236154,0.0006875027,0.0011398,0.001945021,0.007118654,0.3012902,0.5884748],"study_design_scores_gemma":[0.0006175372,0.001086615,0.3184436,0.00004082298,0.00004457899,0.0001053425,0.000719419,0.02278476,0.00003125965,0.649464,0.006450237,0.0002118728],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6887818,0.000143496,0.3083389,0.001527975,0.000952607,0.0001394314,0.00007961978,0.000001830438,0.00003435371],"genre_scores_gemma":[0.4096995,0.00001250356,0.5879563,0.0001780831,0.0001755857,0.00000654931,0.00000212361,0.000005373647,0.001963997],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6423453,"threshold_uncertainty_score":0.9673693,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06888977604375794,"gpt":0.3729042043720761,"spread":0.3040144283283181,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009755178,0.00006921097,0.0001403988,0.0001182454,0.00009147979,0.00007694174,0.0001784561,0.00002604932,0.0002667736],"category_scores_gemma":[0.00007609087,0.00005617724,0.00002552921,0.0001469912,0.00008156075,0.000263158,0.00006370763,0.00007892119,0.000003631731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001105435,"about_ca_system_score_gemma":0.00005603484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008974054,"about_ca_topic_score_gemma":0.0000053901,"domain_scores_codex":[0.999222,0.00001821729,0.0003489978,0.00008905803,0.0002405681,0.00008119502],"domain_scores_gemma":[0.9990724,0.0001290873,0.0002659838,0.00009524896,0.0003024783,0.0001348124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0000122593,0.00284658,0.07390199,0.0000800736,0.00005304833,0.00002759508,0.003795961,0.00002361616,0.0009665581,0.5637032,0.2210629,0.1335262],"study_design_scores_gemma":[0.003173342,0.003832192,0.7084348,0.0007523475,0.0006972188,0.00116622,0.002540349,0.06330652,0.0006713095,0.09306519,0.1210089,0.001351617],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6499212,0.003300931,0.327627,0.0159912,0.00140103,0.0002038451,0.0009950394,0.00001617664,0.0005435069],"genre_scores_gemma":[0.8592998,0.001152139,0.1385315,0.0001457922,0.0000993404,7.226973e-7,0.00001874996,0.00000551214,0.0007464438],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6345327,"threshold_uncertainty_score":0.2920984,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08203732621707842,"gpt":0.3446977867055444,"spread":0.2626604604884659,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001874744,0.00009801033,0.0002607673,0.0000420293,0.0001633481,0.00006111307,0.0001100138,0.00004242636,0.003826611],"category_scores_gemma":[0.00006556771,0.00004225666,0.000101506,0.0003757098,0.0001122754,0.00005438188,0.00001551868,0.0001289742,0.00001111402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002148518,"about_ca_system_score_gemma":0.0000105997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000459571,"about_ca_topic_score_gemma":0.00006447414,"domain_scores_codex":[0.9989632,0.00008658745,0.0004482068,0.0001259866,0.0002460927,0.0001299639],"domain_scores_gemma":[0.9985175,0.0007093039,0.0002775878,0.00003362952,0.0002734144,0.000188573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006484741,0.004525874,0.1691168,0.00002358176,0.0008559708,0.00003915994,0.000373687,0.0001307621,0.01595696,0.1399865,0.004371933,0.6645539],"study_design_scores_gemma":[0.0002860299,0.0006175996,0.9573621,0.00001059229,0.002241771,0.0001431977,0.0003368361,0.002385731,0.00004730365,0.01445324,0.02179396,0.0003216828],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9783139,0.0005643898,0.0171824,0.002428138,0.0001403864,0.0001504188,0.0008423462,0.000006830764,0.0003712463],"genre_scores_gemma":[0.9563794,0.00007717999,0.04275373,0.00009180018,0.0002349911,0.000006188271,0.00007354093,6.823794e-7,0.0003824835],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7882453,"threshold_uncertainty_score":0.997084,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2097672163","doi":"10.3102/1076998610396894","title":"A Didactic Presentation of Snijders’s <i> l <sub>z</sub> * </i> 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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4831390672638221,"gpt":0.4779579214191477,"spread":0.00518114584467444,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001912685,0.0000902153,0.0002359421,0.0003616071,0.00007528978,0.00003189465,0.00009640965,0.00004749421,0.00004064321],"category_scores_gemma":[0.00794147,0.00006276628,0.0000316253,0.0004680487,0.000130071,0.0002598595,0.00001292955,0.0001231834,3.122416e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003807558,"about_ca_system_score_gemma":0.0002256672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007048729,"about_ca_topic_score_gemma":0.00001534288,"domain_scores_codex":[0.9982486,0.0002572879,0.0005771857,0.0001544537,0.0006749631,0.00008753399],"domain_scores_gemma":[0.9922888,0.005593052,0.001035506,0.00009161624,0.0009087942,0.00008227542],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004490989,0.001311969,0.7651072,0.00004792082,0.00003472242,0.000002079413,0.004529926,0.003126194,0.01367515,0.0008443357,0.000767326,0.2060622],"study_design_scores_gemma":[0.0004317582,0.001378456,0.9642962,0.00004059769,0.00007357756,0.00005593544,0.001051772,0.01342932,0.002922245,0.01624481,0.000002096101,0.00007328355],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9279968,0.00003815647,0.07156754,0.0001564422,0.0000835257,0.00008466758,0.00004824292,0.000001423417,0.00002320798],"genre_scores_gemma":[0.8923694,0.00001445079,0.1075672,0.00001045536,0.00001579887,0.000002236904,0.00000171685,0.000004144072,0.00001466922],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2059889,"threshold_uncertainty_score":0.9507254,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1729810713784575,"gpt":0.5008700679701498,"spread":0.3278889965916923,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003895621,0.0001901313,0.0008974773,0.0001620226,0.00008771911,0.0001163238,0.0001447197,0.00009910558,0.0007176536],"category_scores_gemma":[0.03629625,0.0001381327,0.0001043404,0.0001642589,0.0001496936,0.0002576782,0.00001338348,0.000289427,0.000001573367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008680132,"about_ca_system_score_gemma":0.0004442604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003785476,"about_ca_topic_score_gemma":0.00000763428,"domain_scores_codex":[0.9965768,0.00112841,0.001483476,0.0001887146,0.0004289934,0.0001935829],"domain_scores_gemma":[0.9657921,0.03277214,0.0007370248,0.0001107503,0.0003790366,0.0002089551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.004225777,0.003734387,0.00489328,0.00005767674,0.00003181391,0.000003347029,0.001031524,0.0000174705,0.00003614176,0.901612,0.006107036,0.07824957],"study_design_scores_gemma":[0.009489111,0.0002699079,0.0362646,0.0000519108,0.0001977629,0.0000725278,0.0001199077,0.005787979,0.000005416309,0.9475526,0.00002378435,0.0001645075],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04597751,0.00007950643,0.9493408,0.003626605,0.0002781013,0.0003505469,0.0002261972,0.0000041186,0.0001166008],"genre_scores_gemma":[0.1487234,0.0000241859,0.8506695,0.0001845002,0.0002764476,0.0000162071,0.00004315593,0.000009277629,0.00005333277],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1027459,"threshold_uncertainty_score":0.9718214,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1748694814327777,"gpt":0.4944659832462644,"spread":0.3195965018134866,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007967484,0.0001027087,0.0002529829,0.00006660094,0.0000621572,0.00001916958,0.00005436083,0.00004650242,0.0000422146],"category_scores_gemma":[0.002706924,0.00007761563,0.00001943041,0.00005187037,0.00008305946,0.0001285519,0.00002037101,0.0001369442,1.491073e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003800383,"about_ca_system_score_gemma":0.00007833148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001819803,"about_ca_topic_score_gemma":0.00004139711,"domain_scores_codex":[0.9989948,0.00002047279,0.0005780677,0.0001135026,0.0001382318,0.0001549488],"domain_scores_gemma":[0.9952446,0.003934735,0.0003426659,0.00005441358,0.0003009662,0.0001226704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003937422,0.0007853694,0.06852656,0.0002819002,0.00001675581,0.00002642021,0.0006217715,0.00001720805,0.003194511,0.9002407,0.001755427,0.02413962],"study_design_scores_gemma":[0.0005794617,0.0002809691,0.01774818,0.0002215912,0.00005284359,0.0000878406,0.0001952749,0.001609433,0.0003258209,0.9786341,0.0001538317,0.0001107006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1719817,0.0002051817,0.8272146,0.0001736276,0.0001369964,0.0001280908,0.0001450683,0.000001744607,0.0000129655],"genre_scores_gemma":[0.154816,0.00004033953,0.84492,0.00003420478,0.00007335059,0.000003808509,0.000007928929,0.000009037948,0.00009525457],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07839334,"threshold_uncertainty_score":0.3240637,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1615246983656391,"gpt":0.4451226269014738,"spread":0.2835979285358347,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003794623,0.0001021512,0.0002522347,0.0002457022,0.0000567986,0.00004133884,0.00009493441,0.00003330309,0.00003528204],"category_scores_gemma":[0.0004446432,0.00008502286,0.00004551387,0.0002631126,0.00002540679,0.0001380543,0.00002231591,0.0001364888,0.000001522266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000659276,"about_ca_system_score_gemma":0.00007618762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002039993,"about_ca_topic_score_gemma":0.0000212168,"domain_scores_codex":[0.9990017,0.00004687535,0.0004197669,0.0001044809,0.000306608,0.0001206083],"domain_scores_gemma":[0.9986261,0.0003345402,0.0002963583,0.00009181009,0.0004952031,0.0001559687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001005905,0.002024011,0.03263852,0.0001150686,0.0002939318,0.000002623728,0.003657773,0.01584639,0.001472838,0.9140487,0.008299534,0.02150003],"study_design_scores_gemma":[0.0001949556,0.0003128326,0.005949169,0.0000222191,0.0005848201,0.00002379441,0.0002294692,0.03842658,0.0001255133,0.9536723,0.0002250572,0.0002333182],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2702491,0.00001248078,0.7292265,0.0002632409,0.00004876325,0.00005840522,0.00003758644,0.000005893806,0.00009810682],"genre_scores_gemma":[0.509676,0.000008209725,0.4900783,0.00002735756,0.00007263616,0.000004422542,0.00001313098,0.000006509674,0.0001134167],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2394269,"threshold_uncertainty_score":0.3467132,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2861209535314837,"gpt":0.5117877317198253,"spread":0.2256667781883416,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003050969,0.00009020817,0.0001982246,0.00004934924,0.0000791214,0.0000232803,0.00006045552,0.00003239746,0.0000941392],"category_scores_gemma":[0.001096,0.0000561545,0.00003799162,0.00003180806,0.00006013473,0.0001346363,0.00001288558,0.00006859325,6.586623e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004605396,"about_ca_system_score_gemma":0.0001347526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003346115,"about_ca_topic_score_gemma":0.000004562254,"domain_scores_codex":[0.9991446,0.0000278637,0.0004229404,0.0001013553,0.0001578416,0.0001454533],"domain_scores_gemma":[0.9967743,0.002361616,0.0002989515,0.00006359549,0.0003760473,0.0001255385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008514308,0.0002236495,0.0013418,0.00005768725,0.00001577011,0.000004098167,0.00008033679,0.00000263759,0.002621901,0.8660821,0.0033197,0.1261652],"study_design_scores_gemma":[0.0004996526,0.0003923635,0.001825306,0.0001112458,0.00009067053,0.00007141211,0.00007253138,0.00003452009,0.0002189147,0.9957091,0.0008708021,0.0001034363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07047995,0.00006405911,0.9282666,0.0005076578,0.0002554755,0.00009171769,0.0002950734,0.000002571596,0.00003691714],"genre_scores_gemma":[0.1816692,0.00003399862,0.8171772,0.00001701627,0.0002388127,0.000007060858,0.000002289534,0.00001204673,0.0008423235],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1296271,"threshold_uncertainty_score":0.2289914,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3522251289511596,"gpt":0.4970637307263445,"spread":0.1448386017751849,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001482524,0.00006296616,0.0001679122,0.0003058969,0.00006239818,0.0001926305,0.0002050938,0.00002996433,0.0009874334],"category_scores_gemma":[0.006850415,0.00004303836,0.00003525378,0.00035272,0.0000329606,0.0006183441,0.00003942931,0.0001346941,0.00006516065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002636938,"about_ca_system_score_gemma":0.0001379572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001174042,"about_ca_topic_score_gemma":7.03016e-7,"domain_scores_codex":[0.9984284,0.0000589162,0.0006568306,0.00007357603,0.0006786294,0.0001036249],"domain_scores_gemma":[0.9938056,0.00464723,0.0006488668,0.00009040745,0.0007133248,0.00009459937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001039729,0.0001451039,0.6293312,0.00001106185,0.00001023501,0.000002287975,0.0004819318,0.000257636,0.0003654795,0.01443818,0.01468206,0.3401709],"study_design_scores_gemma":[0.0004812711,0.0008236184,0.925817,0.00003096451,0.0000295298,0.0002689587,0.00156399,0.0005898121,0.00002612257,0.05162895,0.01859435,0.0001454925],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9616501,0.0001009398,0.03583035,0.0004817569,0.001431284,0.00004471975,0.00003647953,0.000001578022,0.0004228394],"genre_scores_gemma":[0.6829764,0.00002265435,0.3163696,0.00006559618,0.0001662133,6.429426e-7,0.000004977717,0.000002517397,0.0003913261],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3400254,"threshold_uncertainty_score":0.9999258,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7867101434106125,"gpt":0.5828149761437459,"spread":0.2038951672668666,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005565708,0.0001185874,0.0002555589,0.0001228403,0.001262842,0.0008040674,0.001619268,0.00003795007,0.001314061],"category_scores_gemma":[0.0567458,0.00006534572,0.00004421634,0.0001030479,0.0003319244,0.0005333728,0.0005340251,0.0002366546,0.00001392699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004106189,"about_ca_system_score_gemma":0.0002494512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009462033,"about_ca_topic_score_gemma":0.00006990803,"domain_scores_codex":[0.9977374,0.0002595057,0.0006867747,0.0002283853,0.0009053007,0.0001826396],"domain_scores_gemma":[0.9781928,0.01846187,0.001855678,0.0007521543,0.0005722467,0.000165235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006372855,0.0001502232,0.6626335,0.000006302434,0.000017348,0.00002390427,0.0002359354,0.000012935,0.00008602172,0.006202013,0.07050186,0.2600662],"study_design_scores_gemma":[0.0002900617,0.00005913587,0.9014047,0.00003437593,0.00006231626,0.0002022872,0.0007572678,0.0004356699,0.00001549665,0.08568881,0.01094288,0.0001069849],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9081619,0.00110258,0.07265793,0.01153454,0.002992709,0.0001225413,0.00256438,0.000004346618,0.0008590728],"genre_scores_gemma":[0.5998151,0.00004100451,0.3873932,0.000231631,0.0008218321,0.000001675414,0.00003350991,0.00001462729,0.01164737],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3147353,"threshold_uncertainty_score":0.9995989,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.168753698670039,"gpt":0.4417865701940591,"spread":0.2730328715240201,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004755092,0.00008632024,0.0001343561,0.00003978832,0.0002062908,0.0000211893,0.0001392489,0.000047007,0.0001574104],"category_scores_gemma":[0.001653029,0.00004745016,0.00004921501,0.0001285389,0.0002862814,0.00004998369,0.00002816161,0.0001939377,0.000005324941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004978918,"about_ca_system_score_gemma":0.0001093351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002523703,"about_ca_topic_score_gemma":0.00002303079,"domain_scores_codex":[0.9989187,0.0001275719,0.0004674125,0.00008104039,0.0003141643,0.00009111879],"domain_scores_gemma":[0.9959522,0.002699942,0.000627863,0.000131284,0.0005381011,0.00005058694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007434497,0.000750124,0.00815862,0.00002789151,0.00002069065,2.368769e-7,0.001118994,0.000008454947,0.002535399,0.9513599,0.009790992,0.02615437],"study_design_scores_gemma":[0.0002854002,0.0004437468,0.1863519,0.0001095154,0.0002113886,0.00001598402,0.0001369116,0.004978956,0.001188373,0.8058475,0.0003324264,0.00009788911],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4359844,0.00001480253,0.560054,0.002867281,0.0005632939,0.0002147935,0.0001936681,0.00000237125,0.0001053909],"genre_scores_gemma":[0.8723993,0.000009987665,0.1270665,0.00007744852,0.0002868055,0.000007842535,0.000005369884,0.000007315264,0.0001393662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.436415,"threshold_uncertainty_score":0.1978949,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4011186254261651,"gpt":0.5242410804061896,"spread":0.1231224549800244,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002283059,0.00006016031,0.000131881,0.0001052111,0.0003402999,0.0002058125,0.0003167895,0.00002883639,0.00007550743],"category_scores_gemma":[0.009459394,0.00002797211,0.00003434663,0.0003234859,0.0002691525,0.0003657986,0.0000240904,0.00007930985,0.000001174817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001734176,"about_ca_system_score_gemma":0.0003007875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003446872,"about_ca_topic_score_gemma":0.00001121609,"domain_scores_codex":[0.9986148,0.00006084661,0.0006374978,0.00005933132,0.000530905,0.00009659091],"domain_scores_gemma":[0.9813334,0.01600912,0.0007910629,0.0001267684,0.001686683,0.0000529485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005549354,0.001075881,0.2204792,0.00003523054,0.00007442202,7.20317e-7,0.009509777,0.01146487,0.001500406,0.2452073,0.16602,0.3440773],"study_design_scores_gemma":[0.0006583107,0.001702499,0.3072648,0.00002110649,0.000229865,0.0001217293,0.01414184,0.1149724,0.0002866904,0.554245,0.006178271,0.0001775061],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3788146,0.0001253122,0.6167855,0.00265301,0.00118386,0.0001191179,0.0002759333,0.000001480405,0.0000411636],"genre_scores_gemma":[0.8819512,0.00001397959,0.117408,0.00007478469,0.0004351317,0.000003061088,0.000004712933,0.000002414576,0.0001067224],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5031366,"threshold_uncertainty_score":0.9988843,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2731813646370473,"gpt":0.5297634161063589,"spread":0.2565820514693116,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005935362,0.00008674968,0.0001745869,0.0001512973,0.0001123841,0.00005110158,0.0001032826,0.00007339477,0.0005017541],"category_scores_gemma":[0.00067273,0.0000747062,0.00002751748,0.0001733154,0.0001038323,0.0001200738,0.00002004554,0.0002128273,0.00001295526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001327922,"about_ca_system_score_gemma":0.000509786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002343954,"about_ca_topic_score_gemma":0.00001844691,"domain_scores_codex":[0.9987724,0.00007338533,0.0005153537,0.000112609,0.0003217761,0.0002044666],"domain_scores_gemma":[0.9975708,0.0008137246,0.0003152793,0.00007255322,0.0008534049,0.000374298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003927602,0.002160468,0.7577465,0.00008115738,0.00007332009,0.00003071629,0.001954125,0.0001176244,0.0000801558,0.1282034,0.09518259,0.01397727],"study_design_scores_gemma":[0.002948018,0.003049001,0.9302776,0.0002117652,0.0002747612,0.0003284062,0.001231921,0.005585371,0.00004374005,0.0458858,0.009816487,0.000347152],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9559684,0.0007844426,0.03900947,0.001533488,0.001462854,0.000386582,0.0005018702,0.000006958695,0.0003458867],"genre_scores_gemma":[0.7202668,0.00003901999,0.2744989,0.0001129701,0.0004404301,0.00003345889,0.0001685162,0.00001987766,0.004420076],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2357017,"threshold_uncertainty_score":0.5493856,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2060741340","doi":"10.3102/10769986028001083","title":"A Review of <i>Data Analysis for the Behavioral Sciences Using SPSS</i>","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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8292002256135855,"gpt":0.6501527572032614,"spread":0.1790474684103242,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002763523,0.0002758351,0.001646671,0.000297475,0.000211179,0.00006350576,0.000727515,0.0001006579,0.0002926585],"category_scores_gemma":[0.002281334,0.0001660301,0.00036118,0.0007300343,0.0003891691,0.0001126399,0.00008758251,0.0002594065,5.635528e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007524156,"about_ca_system_score_gemma":0.002214418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002963939,"about_ca_topic_score_gemma":0.00001167945,"domain_scores_codex":[0.997158,0.0003393195,0.001618754,0.000254179,0.0004364045,0.0001933571],"domain_scores_gemma":[0.9875517,0.00821037,0.002899604,0.0003949625,0.0008450942,0.00009827797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001221549,0.00156356,0.0003131078,0.0714172,0.001277516,0.000002608419,0.0001600681,0.000001746894,5.765597e-7,0.06473834,0.1560057,0.7045074],"study_design_scores_gemma":[0.0001580359,0.0002569287,0.00003665494,0.0176092,0.06287169,0.0002621597,0.0002413844,0.00002331386,3.863927e-7,0.02731093,0.8908709,0.0003583905],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000006156411,0.9340894,0.05875843,0.0001149086,0.0008504468,0.0004784889,0.005693285,0.000001554415,0.000007358397],"genre_scores_gemma":[4.568578e-7,0.5916219,0.4079234,0.00003999392,0.0001161394,0.00001239521,0.0001560096,0.00001270449,0.0001169865],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7348652,"threshold_uncertainty_score":0.6770511,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Chart; Pie chart; Appeal; Brother; Plot (graphics); History; Mathematics; Law; Statistics; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.04239665616900781,"gpt":0.3786457753845167,"spread":0.3362491192155089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002124589,0.00006773652,0.0001248794,0.00005284706,0.00008584269,0.00009665866,0.0001992416,0.00001971048,0.0001688413],"category_scores_gemma":[0.0000923306,0.00004545771,0.00001560217,0.00009847408,0.0001183355,0.0002447669,0.00005299633,0.00009534305,0.000006868682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000232624,"about_ca_system_score_gemma":0.0001970305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002224932,"about_ca_topic_score_gemma":0.00001231396,"domain_scores_codex":[0.9992064,0.00003201464,0.0003304651,0.00008136932,0.0002594373,0.00009036337],"domain_scores_gemma":[0.9990416,0.0002258981,0.0002237011,0.00008927791,0.0003179106,0.0001016071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000898395,0.0004928145,0.01162444,0.00002136917,0.00001598067,0.000003734779,0.000438415,0.000009272621,0.0002240103,0.9259768,0.03355467,0.02762958],"study_design_scores_gemma":[0.002174054,0.001828487,0.398238,0.0001721536,0.0004148942,0.0008141297,0.000451645,0.04315269,0.000418746,0.05154087,0.5000622,0.0007320956],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1384301,0.000504657,0.8519927,0.007001874,0.000709263,0.0001411426,0.0008370791,0.000007090242,0.0003760933],"genre_scores_gemma":[0.6892441,0.0003219557,0.3081972,0.0004770753,0.0003750171,0.000001649226,0.00003802744,0.000007319032,0.00133773],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8744358,"threshold_uncertainty_score":0.1853712,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6043028112079372,"gpt":0.5189607433140067,"spread":0.0853420678939305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004355172,0.00006953646,0.0002456592,0.0001682485,0.00007028341,0.00003915594,0.0001786681,0.00004153554,0.0005616203],"category_scores_gemma":[0.04670079,0.00004466158,0.00003397727,0.0002836991,0.0002512774,0.0001131022,0.00005154096,0.0001429809,9.951376e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001291803,"about_ca_system_score_gemma":0.0001274627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001617141,"about_ca_topic_score_gemma":0.000001400932,"domain_scores_codex":[0.9984322,0.0002049899,0.0007058194,0.0001284912,0.0004336511,0.00009480095],"domain_scores_gemma":[0.9658836,0.03264575,0.0006189219,0.0001047011,0.00062398,0.0001230188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004533863,0.0004824345,0.7875258,0.00000712709,0.000006870458,0.00000166419,0.0005504552,6.608278e-7,0.0002734412,0.05980727,0.0005136216,0.1507853],"study_design_scores_gemma":[0.00009113545,0.0002106534,0.6393028,0.000008906598,0.00002549536,0.00005158123,0.0003786742,0.00001970947,0.00002083385,0.3597346,0.0001186911,0.00003693275],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9081597,0.0001541333,0.09057342,0.0001906162,0.0004411321,0.00003691058,0.0000921003,0.000001218826,0.0003507238],"genre_scores_gemma":[0.746702,0.00001991147,0.2530872,0.00001526549,0.0000731183,4.574646e-7,7.615803e-7,0.000002302063,0.00009900756],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2999273,"threshold_uncertainty_score":0.9613293,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2461458402","doi":"10.3102/1076998615625963","title":"A Review of <i>Monte Carlo Simulation and Resampling Methods for Social Science</i>","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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Monte Carlo method; Resampling; Computer science; Statistics; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1585917114809376,"gpt":0.5628150157069903,"spread":0.4042233042260527,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006629977,0.0001338321,0.0006962584,0.00008069215,0.0001735232,0.00004060751,0.0001134272,0.00004292418,0.00003393629],"category_scores_gemma":[0.00008794942,0.00009539153,0.0001435459,0.0001197185,0.0002193867,0.0001117175,0.00003285985,0.0001213662,1.613509e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004578364,"about_ca_system_score_gemma":0.0008456578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001302811,"about_ca_topic_score_gemma":1.659368e-7,"domain_scores_codex":[0.9988597,0.00005768401,0.0007026113,0.0001198937,0.0001475505,0.0001125606],"domain_scores_gemma":[0.9972484,0.0006789878,0.001155431,0.00004865017,0.0007903955,0.00007810816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002296166,0.00005263941,0.0000674092,0.004832378,0.00002337836,3.372646e-8,0.00005154991,6.71717e-7,7.84139e-7,0.02153975,0.0002329399,0.9731961],"study_design_scores_gemma":[0.0002521209,0.0001602731,0.0001453535,0.03675246,0.001158771,0.000006346376,0.00005616979,0.00009068365,2.918116e-7,0.01720465,0.943877,0.0002958919],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00003334718,0.9820653,0.01610481,0.00007534108,0.0003081547,0.0002535687,0.00113427,5.421489e-7,0.00002469075],"genre_scores_gemma":[0.0001180245,0.9552128,0.04403109,0.00002041994,0.0005157783,0.00001284133,0.00002525516,0.00001146328,0.00005226418],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9729003,"threshold_uncertainty_score":0.3889953,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5966527320784061,"gpt":0.5378534698798701,"spread":0.05879926219853593,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004303536,0.0001150652,0.0003632914,0.0003820959,0.0003173557,0.000450837,0.0005658611,0.00004895252,0.00002994244],"category_scores_gemma":[0.01494621,0.00006826322,0.00003691281,0.0007032066,0.000200781,0.0007144128,0.0001264252,0.0002131745,0.000003554537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002056512,"about_ca_system_score_gemma":0.000384652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007898918,"about_ca_topic_score_gemma":0.00001486394,"domain_scores_codex":[0.9975981,0.0001797381,0.00105133,0.0001656096,0.00082778,0.0001774273],"domain_scores_gemma":[0.9839212,0.01417947,0.0008547694,0.0002795494,0.0005794357,0.0001855418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001527695,0.000214813,0.8015459,0.00001047315,0.00002563644,0.000002130889,0.0009728634,0.06562241,0.00003485489,0.003985468,0.03709242,0.09034031],"study_design_scores_gemma":[0.0007622006,0.00009302018,0.1330009,0.000007692512,0.00009696215,0.000008909387,0.0003397471,0.8326971,0.000002434804,0.03272827,0.0001760481,0.00008671821],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7339148,0.0001081173,0.2621889,0.002308846,0.0002527032,0.00008576706,0.001116574,0.000007282948,0.00001707875],"genre_scores_gemma":[0.8247029,0.00002844968,0.174674,0.00009375162,0.0002629872,0.000002956566,0.0001623115,0.000004866929,0.00006782503],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7670747,"threshold_uncertainty_score":0.9933513,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2290377455","doi":"10.3102/1076998615606114","title":"Graphs ′ <i>R</i> Us UnwinAntony. Graphical Data Analysis With R. Boca Raton, FL: Taylor &amp; 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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Computer science; Mathematics education; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.08435273792904979,"gpt":0.3799160870258571,"spread":0.2955633490968073,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001093659,0.0002695304,0.0004931251,0.0005198148,0.0002278741,0.0002897069,0.001486562,0.0000893221,0.00008303398],"category_scores_gemma":[0.0002309847,0.000201146,0.00009300755,0.001607747,0.0004065737,0.001094449,0.0003207565,0.0005531017,0.0000127445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006466575,"about_ca_system_score_gemma":0.0006278447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001041745,"about_ca_topic_score_gemma":0.0003873728,"domain_scores_codex":[0.9969203,0.0002039765,0.0006801568,0.0004886988,0.00127931,0.000427491],"domain_scores_gemma":[0.9960694,0.0004117827,0.0005152423,0.0008534075,0.001417732,0.0007323843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007088342,0.003647161,0.5591015,0.00006447837,0.0009633091,0.0003364506,0.001229871,0.0005451861,0.0004112448,0.1846525,0.220176,0.02816353],"study_design_scores_gemma":[0.005399324,0.003902796,0.3927632,0.0001409853,0.003201174,0.001758323,0.0006160155,0.007288387,0.0001480431,0.462555,0.1199575,0.002269306],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1517853,0.005185648,0.8352062,0.005575457,0.0008487187,0.0002792746,0.001033946,0.00002592331,0.00005946765],"genre_scores_gemma":[0.4669513,0.0005846673,0.530808,0.0003310018,0.0002989186,0.00001315701,0.0005105421,0.00003438141,0.0004680536],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3151659,"threshold_uncertainty_score":0.8202494,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4986897028064809,"gpt":0.5681965655826773,"spread":0.06950686277619639,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006545846,0.0000808586,0.0003917511,0.0004038088,0.0002145503,0.0001341236,0.0001491837,0.00005301057,0.0001172389],"category_scores_gemma":[0.004419304,0.00007183726,0.00006172382,0.0003323689,0.00006012637,0.0004193679,0.00003241048,0.0001714825,0.00004145177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002035183,"about_ca_system_score_gemma":0.000356725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002103465,"about_ca_topic_score_gemma":0.00004132719,"domain_scores_codex":[0.9963011,0.0001457809,0.003234408,0.00009722773,0.00009543337,0.0001260399],"domain_scores_gemma":[0.9960326,0.001593832,0.001842987,0.0001080844,0.0003062389,0.0001162685],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002148489,0.000207004,0.6661284,0.0000810518,0.00006178994,3.120941e-7,0.000768404,0.0004539726,0.00000215293,0.2540155,0.07274819,0.005511687],"study_design_scores_gemma":[0.0005732139,0.000176201,0.9102278,0.0001096783,0.00007547694,0.00002309127,0.002167178,0.003910767,0.000002062404,0.04766378,0.03486928,0.0002014538],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7871441,0.001201507,0.1640036,0.04461309,0.0019636,0.0003119374,0.0004180362,0.000003328634,0.0003408355],"genre_scores_gemma":[0.8548202,0.00009516462,0.1366356,0.007537296,0.0005678709,0.000008666315,0.00002594625,0.000007193496,0.0003020895],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2440994,"threshold_uncertainty_score":0.5290639,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs","keywords":"Jackknife resampling; Frequentist inference; Markov chain Monte Carlo; Estimator; Quantile; Quantile regression; Standard error; Bayesian probability; Point estimation; Outlier","retraction":null,"screen_n_in":null,"score":{"opus":0.06763164808331662,"gpt":0.405548800795139,"spread":0.3379171527118224,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004023688,0.00009852087,0.0001890416,0.00009743737,0.0001305601,0.0001347155,0.0003203017,0.00004157278,0.000008681649],"category_scores_gemma":[0.00005649014,0.00006587434,0.00001552743,0.00009218474,0.0000549912,0.0003031636,0.0001240461,0.0001206807,5.139442e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002585938,"about_ca_system_score_gemma":0.0003819695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001334723,"about_ca_topic_score_gemma":0.00002739528,"domain_scores_codex":[0.9991559,0.00004877114,0.0002791131,0.0001889254,0.0002147822,0.0001125007],"domain_scores_gemma":[0.9989792,0.00022486,0.0002243144,0.0002010117,0.0002678439,0.000102832],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005405924,0.0006437496,0.0250993,0.0002110056,0.00009065693,0.00002620586,0.001116701,0.00001040005,0.0003735079,0.4212784,0.04488628,0.5057232],"study_design_scores_gemma":[0.006531212,0.003986557,0.1061385,0.001335162,0.0008764592,0.000959446,0.0005800169,0.04707867,0.0007036491,0.8089248,0.02188293,0.001002588],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01393226,0.0003490741,0.9823108,0.00269298,0.0003413962,0.0001151766,0.0002344049,0.000002517276,0.00002142175],"genre_scores_gemma":[0.1383692,0.00005364655,0.8610973,0.0001009365,0.00005822071,0.00000285106,0.000022851,0.0000042856,0.0002906648],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5047206,"threshold_uncertainty_score":0.2686278,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}