{"meta":{"query_hash":"e5913b510d38","filters":{"venue":"Applied Psychological Measurement"},"cohort_total":34,"direct_labels_cover":1,"predictions_cover":34,"exported":34,"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/e5913b510d38","api":"https://metacan.xera.ac/api/v1/cohort?venue=Applied+Psychological+Measurement"},"results":[{"id":"W1942728350","doi":"10.1177/0146621608316603","title":"Computer Software Review: Conducting Automated Test Assembly Using the Premium Solver Platform Version 7.0 With Microsoft Excel and the Large-Scale LP/QP Solver Engine Add-In","year":2008,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Manufacturing Process and Optimization","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Solver; Computer science; Microsoft excel; Scale (ratio); Software; Test (biology); Programming language; Computational science; Software engineering; Operating system; Cartography","score_opus":0.04766665868336487,"score_gpt":0.24687560586079704,"score_spread":0.19920894717743218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1942728350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60837096,0.01020459,0.37224984,0.00050117297,0.00063005177,0.0038965282,0.000020665582,0.001918468,0.0022077383],"genre_scores_gemma":[0.9838617,0.0007737836,0.014426143,0.0007260716,0.0000803884,0.000079073594,0.000012299394,0.000033516542,0.0000070351175],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852127,0.000026960874,0.00033387484,0.00034216477,0.00040642626,0.0003693152],"domain_scores_gemma":[0.9993691,0.00012231333,0.00008875538,0.00028366852,0.00007527856,0.00006089099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007516431,0.00026873668,0.00031646108,0.000036278503,0.00027549945,0.000041865478,0.00020056753,0.00011528349,0.000048673406],"category_scores_gemma":[0.000031346997,0.00014219165,0.00004457185,0.00019164498,0.00010548842,0.00008457083,0.000056110657,0.00034478705,0.000007667098],"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":[0.0012814819,0.001810364,0.009953039,0.0041811266,0.00059451064,0.0000932158,0.006645859,0.8700805,0.02265288,0.00024313523,0.057644952,0.024818951],"study_design_scores_gemma":[0.029771706,0.0006257815,0.06209342,0.004920056,0.0005830848,0.00052249664,0.00059092615,0.8518792,0.028651383,0.00020441848,0.016861077,0.003296477],"about_ca_topic_score_codex":0.0000051809357,"about_ca_topic_score_gemma":0.0000072548855,"teacher_disagreement_score":0.37549073,"about_ca_system_score_codex":0.00008482989,"about_ca_system_score_gemma":0.000010116715,"threshold_uncertainty_score":0.5798407},"labels":[],"label_agreement":null},{"id":"W1975836040","doi":"10.1177/0146621602239476","title":"Determining the Significance of Correlations Corrected for Unreliability and Range Restriction","year":2003,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Statistics; Mathematics; Sampling (signal processing); Variance (accounting); Range (aeronautics); Sample size determination; Monte Carlo method; Population; Correlation coefficient; Correlation; Population variance; Sample (material); Demography; Physics","score_opus":0.32356157863681795,"score_gpt":0.4344033213096365,"score_spread":0.11084174267281854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975836040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045991637,0.00002402427,0.94835263,0.00005920341,0.0001545834,0.0013018843,0.000013268366,0.00003182859,0.004070915],"genre_scores_gemma":[0.7610411,0.0000070602164,0.23853545,0.000057514233,0.000012650666,0.00032943863,8.338178e-7,0.000007435387,0.000008508897],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988279,0.00015585829,0.00033684153,0.0002747623,0.00024021068,0.0001644439],"domain_scores_gemma":[0.9974588,0.0019221554,0.00014627111,0.00023544765,0.00018525086,0.00005203857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014327563,0.00011170211,0.00020688011,0.000016518903,0.00013198829,0.0000076230913,0.00007176911,0.00007455173,0.00001507379],"category_scores_gemma":[0.00315715,0.0000704214,0.000039940605,0.00011287524,0.00012654354,0.000015932965,0.000009278722,0.00012368312,6.634935e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018449093,0.00052489777,0.001300551,0.000065022716,0.000024993475,1.7331108e-7,0.00015404666,0.000039442537,0.004320947,0.9529929,0.0006619478,0.039730586],"study_design_scores_gemma":[0.0011360117,0.0002425376,0.02398126,0.000015937667,0.00006706152,8.1524763e-7,0.000092731025,0.00023140898,0.0006265713,0.97243494,0.0010341114,0.00013663995],"about_ca_topic_score_codex":6.795488e-7,"about_ca_topic_score_gemma":0.0000016794589,"teacher_disagreement_score":0.71504945,"about_ca_system_score_codex":0.000034006178,"about_ca_system_score_gemma":0.000009387863,"threshold_uncertainty_score":0.37796316},"labels":[],"label_agreement":null},{"id":"W2019817087","doi":"10.1177/01466216045280142","title":"SIMCAT 1.0: A SAS Computer Program for Simulating Computer Adaptive Testing","year":2006,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Computerized adaptive testing; Computer science; Computer program; Programming language; Statistics; Psychometrics; Mathematics","score_opus":0.13975375466909867,"score_gpt":0.3452510035012429,"score_spread":0.2054972488321442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019817087","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013610403,0.00004292583,0.98130655,0.00029482672,0.00016117349,0.001588768,0.0000017954849,0.00072425016,0.0022692985],"genre_scores_gemma":[0.54592633,3.8834847e-7,0.45310724,0.0002808103,0.00033609295,0.0003301705,0.0000036490073,0.000009504896,0.0000058099877],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99633354,0.00012463718,0.00056951575,0.0011281433,0.0010945606,0.0007496279],"domain_scores_gemma":[0.997682,0.0007764028,0.00015757441,0.0006643397,0.00056333654,0.00015637297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017032363,0.00029835204,0.00039808362,0.000107365064,0.0003276842,0.00030422083,0.00094036676,0.00015279495,0.0000104249575],"category_scores_gemma":[0.00008879098,0.00023440535,0.00020321355,0.0007968162,0.00011826622,0.000104488056,0.0002649583,0.00029008716,0.000056438512],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042322525,0.0013087069,0.0008178631,0.000026920443,0.000051608462,0.0000056573144,0.000041427902,0.0138803655,0.0007395647,0.013170947,0.0013898385,0.96852475],"study_design_scores_gemma":[0.0018368769,0.0021524641,0.020721387,0.000062103754,0.000028292738,0.0000070773804,0.000010182962,0.9399897,0.00038301543,0.02971858,0.004445454,0.0006448523],"about_ca_topic_score_codex":0.000023848468,"about_ca_topic_score_gemma":0.000005192936,"teacher_disagreement_score":0.96787995,"about_ca_system_score_codex":0.00015392368,"about_ca_system_score_gemma":0.000033254943,"threshold_uncertainty_score":0.95587724},"labels":[],"label_agreement":null},{"id":"W2029082333","doi":"10.1177/0146621607301094","title":"Effects of Semantic Incompatibility on Rating Response","year":2008,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Psychology; Rating scale; Semantic differential; Internal consistency; Consistency (knowledge bases); Scale (ratio); Cognitive psychology; Social psychology; Statistics; Psychometrics; Developmental psychology; Artificial intelligence; Computer science; Mathematics","score_opus":0.6035678497989727,"score_gpt":0.4659181755804515,"score_spread":0.1376496742185212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029082333","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96924627,0.000119856544,0.015433929,0.00021447976,0.00045949686,0.000599736,0.0000010831764,0.00008568002,0.013839476],"genre_scores_gemma":[0.98814034,0.0000074571863,0.011220758,0.00048622006,0.00005565381,0.000051545434,2.1389477e-7,0.000009109419,0.00002867617],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9926154,0.0017882059,0.0011349218,0.000937659,0.0031297347,0.0003940833],"domain_scores_gemma":[0.964433,0.033546984,0.0005319899,0.00099279,0.00033864353,0.00015660797],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021633433,0.00023560252,0.000638536,0.00033359654,0.00023309534,0.00002792511,0.00085909286,0.00013973954,0.00013064753],"category_scores_gemma":[0.1104486,0.00014644148,0.00016750113,0.0017578881,0.00025290638,0.000036771075,0.000117685675,0.0003130742,0.00014708399],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0096789645,0.0045703985,0.087551884,0.000081170634,0.000109388326,0.0001235655,0.0012881783,0.00043195148,0.5420306,0.0041090874,0.010413825,0.339611],"study_design_scores_gemma":[0.0011709575,0.0008601189,0.9592599,0.000033892542,0.000008424147,0.000010310675,0.000089870344,0.000039923118,0.021375077,0.01654827,0.00041315,0.00019010322],"about_ca_topic_score_codex":0.0000054769116,"about_ca_topic_score_gemma":5.6039966e-7,"teacher_disagreement_score":0.87170804,"about_ca_system_score_codex":0.000074795455,"about_ca_system_score_gemma":0.000027289465,"threshold_uncertainty_score":0.8970445},"labels":[],"label_agreement":null},{"id":"W2035434565","doi":"10.1177/01466216010251006","title":"The Extra-Factor Phenomenon Revisited: Unidimensional Unfolding as Quadratic Factor Analysis","year":2001,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Phenomenon; Factor (programming language); Covariance; Quadratic equation; Metric (unit); Factor analysis; Mathematics; Set (abstract data type); Applied mathematics; Statistics; Computer science; Physics; Geometry","score_opus":0.14005892954195845,"score_gpt":0.33388675036949617,"score_spread":0.19382782082753772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035434565","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97834,0.00059311284,0.002059931,0.0016645502,0.00014988397,0.00048563365,0.00003096102,0.00012322016,0.0165527],"genre_scores_gemma":[0.99736416,0.00016854377,0.0009705617,0.0010369485,0.00019702116,0.000053006675,0.000023762865,0.000002151225,0.00018381474],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99639076,0.0004714589,0.00063193945,0.0007608586,0.0011443658,0.0006006095],"domain_scores_gemma":[0.99791086,0.0011580564,0.00020712618,0.00024550874,0.00017514665,0.00030332693],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012994215,0.00032602754,0.000518182,0.00003456825,0.0007813727,0.00018843688,0.0004725328,0.00015958978,0.004891822],"category_scores_gemma":[0.00035742176,0.000102789585,0.00035084487,0.0015615933,0.00013953359,0.000042131305,0.00005536933,0.0002968193,0.00021773705],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003996818,0.0005974985,0.0038857276,0.000004264994,0.00093038275,0.000027269502,0.00006954311,0.000041962932,0.40097383,0.034619436,0.00046217634,0.5579882],"study_design_scores_gemma":[0.0006807834,0.0010712255,0.8667179,0.0000281289,0.00093273696,0.000017401017,0.0007293642,0.0003756664,0.0023130383,0.02786624,0.09805243,0.0012151006],"about_ca_topic_score_codex":0.000028399149,"about_ca_topic_score_gemma":0.000072171024,"teacher_disagreement_score":0.8628321,"about_ca_system_score_codex":0.0000913299,"about_ca_system_score_gemma":0.0000053265367,"threshold_uncertainty_score":0.9960178},"labels":[],"label_agreement":null},{"id":"W2037069694","doi":"10.1177/01466210022031741","title":"Restriction of Range and Correlation in Outlier-Prone Distributions","year":2000,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":71,"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":"Outlier; Statistics; Correlation; Range (aeronautics); Mathematics; Normal distribution; Gaussian; Physics","score_opus":0.22316477148681457,"score_gpt":0.41767165415843643,"score_spread":0.19450688267162186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037069694","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15244704,0.000065015316,0.8314944,0.00011937512,0.00004325023,0.0004964526,0.00001815236,0.000035198183,0.0152811],"genre_scores_gemma":[0.89230865,0.000070173286,0.10746711,0.000027055978,0.00001530717,0.00007996517,0.000003743474,0.000006050301,0.000021934182],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99888587,0.000080231366,0.00035377534,0.0002469668,0.00027376125,0.00015937655],"domain_scores_gemma":[0.9994806,0.00018746084,0.00006886368,0.0001629635,0.000041838513,0.000058252615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006975526,0.00010110044,0.00021109931,0.000032847955,0.0000420781,0.000004980192,0.00005156129,0.00009188729,0.0001634342],"category_scores_gemma":[0.00023882822,0.00008111351,0.000023008128,0.00015133657,0.000093320195,0.000024733348,0.000009429863,0.0001491094,0.0000071648406],"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":[0.00032338043,0.0007873807,0.00057140674,0.00003453093,0.0000128721595,0.000002311756,0.000120256045,0.00007041966,0.0036279112,0.6927781,0.00024100974,0.30143043],"study_design_scores_gemma":[0.0011551905,0.0001534775,0.056361023,0.00003270521,0.00002427386,0.0000017870464,0.000031853368,0.00022230303,0.00017004386,0.9413502,0.0003691544,0.00012795675],"about_ca_topic_score_codex":0.0000036231813,"about_ca_topic_score_gemma":0.0000036558952,"teacher_disagreement_score":0.7398616,"about_ca_system_score_codex":0.00005201895,"about_ca_system_score_gemma":0.0000038434373,"threshold_uncertainty_score":0.3307713},"labels":[],"label_agreement":null},{"id":"W2055728918","doi":"10.1177/0146621608329503","title":"A Monte Carlo Study of the Effect of Item Characteristic Curve Estimation on the Accuracy of Three Person-Fit Statistics","year":2009,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":10,"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 Laval; Université de Sherbrooke","funders":"","keywords":"Nonparametric statistics; Statistics; Monte Carlo method; Logistic regression; Parametric statistics; Mathematics; Item response theory; Sample size determination; Econometrics; Psychometrics","score_opus":0.5775002634706006,"score_gpt":0.46070135321883504,"score_spread":0.11679891025176553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055728918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98827547,0.000054982425,0.007697321,0.00028349753,0.00029072494,0.0015999798,0.000022135593,0.00001690672,0.0017589828],"genre_scores_gemma":[0.99816644,0.0000026173368,0.00163128,0.000107071726,0.00002555605,0.000055028613,2.886549e-7,0.0000061132037,0.000005601178],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99422616,0.0011577796,0.001064465,0.0004977254,0.0028097222,0.00024415922],"domain_scores_gemma":[0.97179776,0.025224745,0.0013926706,0.0011685318,0.00036210538,0.0000541638],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01248888,0.00022895006,0.0006595029,0.00014776498,0.0001329312,0.00003660661,0.001252541,0.00008554746,0.000078255405],"category_scores_gemma":[0.0707149,0.00009583058,0.0001395595,0.0013262447,0.00015411321,0.00003080909,0.000068831585,0.00028850773,0.000007693042],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017630247,0.0025870209,0.10695472,0.00004301629,0.00016960196,0.0000034905302,0.0018104761,0.0020961303,0.014114792,0.0031314557,0.0024352132,0.86489105],"study_design_scores_gemma":[0.000994636,0.003882777,0.9877362,0.00004925694,0.000057376317,0.0000012833182,0.00053565815,0.0011277365,0.0010856125,0.0044071157,0.000015300271,0.00010701658],"about_ca_topic_score_codex":0.000023474995,"about_ca_topic_score_gemma":0.0000048784796,"teacher_disagreement_score":0.88078153,"about_ca_system_score_codex":0.00003942763,"about_ca_system_score_gemma":0.00001352414,"threshold_uncertainty_score":0.93711287},"labels":[],"label_agreement":null},{"id":"W2056123061","doi":"10.1177/01466210122032127","title":"Book Review","year":2001,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology","score_opus":0.4091965530648787,"score_gpt":0.3927407493978079,"score_spread":0.01645580366707078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056123061","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022515506,0.4009157,0.00045462957,0.008848426,0.0010897041,0.001149188,0.000003977401,0.0004220606,0.58486474],"genre_scores_gemma":[0.4449048,0.06265172,0.00034580566,0.47385064,0.00077178876,0.0029710918,0.000018384022,0.00007325278,0.014412497],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99663067,0.00016485015,0.0006387327,0.000985537,0.0007941318,0.000786087],"domain_scores_gemma":[0.99862105,0.00004632928,0.0001572529,0.00078637066,0.00011988519,0.0002691009],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010057098,0.00040495896,0.0005685597,0.00004615551,0.00019779342,0.000021584608,0.0005214797,0.000240969,0.07762001],"category_scores_gemma":[0.000034480556,0.00027248438,0.00021978053,0.00046118777,0.00020162752,0.0000357008,0.000074394055,0.0004664235,0.009142432],"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":[0.00018733769,0.0012298079,0.0004754967,0.000022139853,0.00006289434,0.00007387576,0.00004427302,8.162848e-8,0.0003881529,0.0034544142,0.8789092,0.115152374],"study_design_scores_gemma":[0.0008464293,0.0003410762,0.075918555,0.0001156527,0.00007178145,0.000063705396,0.000032949054,2.7484791e-8,0.000012653737,0.0007564435,0.921463,0.00037773515],"about_ca_topic_score_codex":0.00000838519,"about_ca_topic_score_gemma":0.0000014051869,"teacher_disagreement_score":0.5704523,"about_ca_system_score_codex":0.00007169181,"about_ca_system_score_gemma":0.000003835695,"threshold_uncertainty_score":0.99997276},"labels":[],"label_agreement":null},{"id":"W2066165827","doi":"10.1177/01466210122032046","title":"Nonparametric Item Response Function Estimation for Assessing Parametric Model Fit","year":2001,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Nonparametric statistics; Item response theory; Identifiability; Resampling; Parametric statistics; Consistency (knowledge bases); Econometrics; Parametric model; Statistics; Mathematics; Differential item functioning; Computer science; Artificial intelligence; Psychometrics","score_opus":0.7555750990116348,"score_gpt":0.5231085521292439,"score_spread":0.23246654688239088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066165827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34878436,0.00017109986,0.64158064,0.00042634978,0.0005641344,0.0007463407,0.000003072329,0.00016639671,0.007557622],"genre_scores_gemma":[0.81964797,0.0000131680445,0.17900656,0.000747082,0.00009847182,0.00030787723,0.0000028256086,0.000020689773,0.00015535882],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99273247,0.0006919041,0.0013659289,0.0014057101,0.0030753075,0.0007286822],"domain_scores_gemma":[0.9665034,0.03059806,0.0007346945,0.0010987757,0.0007988521,0.0002662544],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032778114,0.00035532963,0.0006139567,0.0016438065,0.00046236336,0.00056970614,0.00089991273,0.00031929815,0.00017687348],"category_scores_gemma":[0.15302347,0.0002515817,0.00025651068,0.008229246,0.00009922463,0.0002624897,0.00009414135,0.00034784197,0.00017241956],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030090455,0.000617484,0.0036376675,0.0000073572837,0.000035518573,0.0000036275417,0.000036931666,0.03958116,0.0045061437,0.0018681949,0.0068414006,0.93985546],"study_design_scores_gemma":[0.0029789032,0.0009280038,0.387059,0.000030114585,0.000088534965,0.000028852706,0.00032371443,0.34014723,0.0002471962,0.25857767,0.008839145,0.00075161894],"about_ca_topic_score_codex":0.0000023818343,"about_ca_topic_score_gemma":5.281879e-7,"teacher_disagreement_score":0.93910384,"about_ca_system_score_codex":0.00025773203,"about_ca_system_score_gemma":0.000050934064,"threshold_uncertainty_score":0.9999936},"labels":[],"label_agreement":null},{"id":"W2070673350","doi":"10.1177/0146621606292215","title":"Investigation of IRT-Based Equating Methods in the Presence of Outlier Common Items","year":2008,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Equating; Outlier; Statistics; Item response theory; Calibration; Comparability; Mathematics; Econometrics; Computer science; Psychometrics","score_opus":0.8304468687797645,"score_gpt":0.5388212625480718,"score_spread":0.29162560623169265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070673350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8062878,0.0002468303,0.1744903,0.00049859314,0.00026256873,0.0006356837,0.0000022115503,0.00002679538,0.017549211],"genre_scores_gemma":[0.83624434,0.000005442124,0.16322944,0.00042214885,0.00002501884,0.00006321304,7.035448e-7,0.0000051614143,0.0000045378415],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9919676,0.002857596,0.001580675,0.0005703066,0.002716125,0.00030766983],"domain_scores_gemma":[0.97163993,0.02610949,0.00091937865,0.0009425091,0.0003186446,0.000070069575],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040409517,0.00017177942,0.00054921926,0.00034243928,0.000110647234,0.00002343053,0.0013154738,0.00013291607,0.00007316628],"category_scores_gemma":[0.038884062,0.000094433926,0.000121029116,0.0029106482,0.0004278803,0.00004911671,0.00007648367,0.00031682375,0.000007465493],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029823257,0.0006019457,0.41936296,0.000034586123,0.000028237582,0.000008083509,0.0031654532,0.0019003788,0.2201929,0.006336234,0.0020593787,0.3460116],"study_design_scores_gemma":[0.0010320912,0.0003859058,0.9069838,0.000050490642,0.000011276503,0.0000059600884,0.0011383578,0.0012384999,0.020451078,0.068121634,0.0003843038,0.00019660534],"about_ca_topic_score_codex":0.000042569984,"about_ca_topic_score_gemma":0.000004667187,"teacher_disagreement_score":0.48762083,"about_ca_system_score_codex":0.00003168411,"about_ca_system_score_gemma":0.00003266718,"threshold_uncertainty_score":0.98810035},"labels":[],"label_agreement":null},{"id":"W2078503709","doi":"10.1177/0146621614557272","title":"Evaluating Person Fit for Cognitive Diagnostic Assessment","year":2014,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Alberta","funders":"","keywords":"Statistic; Cognition; Psychology; Item response theory; Conformity; Cognitive psychology; Context (archaeology); Statistics; Social psychology; Applied psychology; Psychometrics; Clinical psychology; Mathematics","score_opus":0.8911900554521754,"score_gpt":0.6108802067461848,"score_spread":0.2803098487059906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078503709","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24524683,0.00015434898,0.65850556,0.0010327937,0.0011805551,0.001764726,0.000011387707,0.00016020269,0.09194363],"genre_scores_gemma":[0.9026748,0.0000046170167,0.094783455,0.0013941631,0.0003110232,0.00074391946,0.0000033375043,0.000016956868,0.000067721],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99314153,0.0008883008,0.0008517151,0.0013134452,0.0031639887,0.0006410378],"domain_scores_gemma":[0.9127549,0.08472498,0.0005727086,0.0007249512,0.0009670576,0.0002554122],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037176665,0.00029553173,0.00057524355,0.00023983115,0.00039109425,0.0002340676,0.0008231875,0.00016666215,0.00056460773],"category_scores_gemma":[0.24483585,0.00019491612,0.00021553082,0.0009920165,0.00012436468,0.000058867285,0.00008897724,0.0003003481,0.0001724475],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011437478,0.00035632722,0.0058108643,0.000008610114,0.00003855743,9.062208e-7,0.00010397764,0.00012337472,0.0029698294,0.0051448783,0.00442682,0.9809015],"study_design_scores_gemma":[0.0053147757,0.0031647987,0.81089944,0.000101331265,0.00012754416,0.000009022578,0.0019923456,0.0050450326,0.0006139904,0.16377312,0.008222825,0.0007357649],"about_ca_topic_score_codex":0.0000025965232,"about_ca_topic_score_gemma":0.0000015115847,"teacher_disagreement_score":0.9801657,"about_ca_system_score_codex":0.00010790817,"about_ca_system_score_gemma":0.00002792909,"threshold_uncertainty_score":0.9914292},"labels":[],"label_agreement":null},{"id":"W2097506538","doi":"10.1177/01466216010251011","title":"Computer Program Exchange","year":2001,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Distributed and Parallel Computing Systems","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Lakehead University","keywords":"Computer program; Computer science; Psychology; Statistics; Mathematics; Programming language","score_opus":0.0944139960001945,"score_gpt":0.30833941338232707,"score_spread":0.21392541738213255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097506538","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0109551735,0.0001485054,0.90244037,0.00077081117,0.0010065313,0.00081873074,8.243197e-7,0.0012590308,0.08260005],"genre_scores_gemma":[0.9599756,0.00001292262,0.038214855,0.0011367529,0.0003788774,0.00021051997,0.0000045895986,0.00000899181,0.000056893205],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99749213,0.000091919974,0.0003428501,0.00072626263,0.0007994676,0.00054738135],"domain_scores_gemma":[0.9987967,0.000028671762,0.000105157065,0.00075096736,0.00012230629,0.00019620964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009285427,0.00023681477,0.00025253944,0.000058372607,0.00014074071,0.0002156722,0.0011556698,0.000120052275,0.000060274306],"category_scores_gemma":[0.000008372197,0.00018305123,0.000095028154,0.00049834495,0.00004533123,0.000067196124,0.00018925333,0.00014542392,0.00057754514],"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":[0.000025658968,0.0011766534,0.0003608542,0.00001578474,0.00003887612,0.000051057406,0.00016052152,0.00015852373,0.00040865905,0.033970628,0.027583892,0.93604887],"study_design_scores_gemma":[0.0023594103,0.0017658949,0.04757075,0.00007086777,0.000014806814,0.00018381803,0.000014402496,0.009825355,0.000112482965,0.007577787,0.92947817,0.0010262674],"about_ca_topic_score_codex":0.0000037551633,"about_ca_topic_score_gemma":0.000001218311,"teacher_disagreement_score":0.94902045,"about_ca_system_score_codex":0.00006706888,"about_ca_system_score_gemma":0.0000108772565,"threshold_uncertainty_score":0.7464613},"labels":[],"label_agreement":null},{"id":"W2100391776","doi":"10.1177/0146621606286206","title":"The Effect of Examinee Motivation on Test Construction Within an IRT Framework","year":2006,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Item response theory; Test (biology); Psychology; Statistics; Econometrics; Bayesian probability; Differential item functioning; Equating; Response bias; Computerized adaptive testing; Logistic regression; Social psychology; Mathematics; Psychometrics; Rasch model","score_opus":0.39513929299412376,"score_gpt":0.43041902804549487,"score_spread":0.03527973505137111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100391776","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9554009,0.00006381226,0.018577538,0.00021735336,0.0011039231,0.0005712484,0.0000029720468,0.00008951559,0.023972757],"genre_scores_gemma":[0.9913583,0.0000032502846,0.008198657,0.00010469082,0.00023464453,0.00007033618,0.0000017088707,0.000009388245,0.000019062785],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99499226,0.0007461641,0.000959552,0.00068082206,0.0023170086,0.0003042256],"domain_scores_gemma":[0.900653,0.09741246,0.0006613971,0.0009514213,0.00024084706,0.00008084677],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01601647,0.00021961483,0.00037108126,0.00017840268,0.00030212864,0.00013059967,0.00072443555,0.00019430615,0.000060931445],"category_scores_gemma":[0.18148594,0.00010648172,0.000092076145,0.0014514823,0.00028319893,0.000051992425,0.000043052405,0.0003484516,0.00003054664],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007214034,0.00049939577,0.47882426,0.000007900531,0.000025914116,0.0000022681643,0.00007001842,0.0010970787,0.031194208,0.044846177,0.0019524766,0.4407589],"study_design_scores_gemma":[0.00056066096,0.0018524843,0.86367625,0.000019516157,0.000010324007,0.000004507788,0.0001194327,0.000060061397,0.0100764735,0.12312372,0.00035856717,0.00013798702],"about_ca_topic_score_codex":0.0000105858,"about_ca_topic_score_gemma":0.0000022632598,"teacher_disagreement_score":0.44062093,"about_ca_system_score_codex":0.00005631713,"about_ca_system_score_gemma":0.0000076658625,"threshold_uncertainty_score":0.82540876},"labels":[],"label_agreement":null},{"id":"W2128248024","doi":"10.1177/0146621609336540","title":"An Iterative Maximum a Posteriori Estimation of Proficiency Level to Detect Multiple Local Likelihood Maxima","year":2009,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"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":"Maximum a posteriori estimation; Estimator; Maxima; Maximum likelihood; Mathematics; Statistics; Focus (optics); A priori and a posteriori; Restricted maximum likelihood; M-estimator; Maximum likelihood sequence estimation; Estimation theory; Computer science","score_opus":0.4601168525429778,"score_gpt":0.45762144688310985,"score_spread":0.002495405659867944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128248024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34517577,0.000077496225,0.6483945,0.0004313317,0.00026558034,0.00082054385,0.000011653567,0.000087486915,0.004735601],"genre_scores_gemma":[0.8092932,0.0000020141554,0.18967657,0.00090184354,0.000046796344,0.00006251227,0.0000020622574,0.000008688827,0.000006283319],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9938284,0.0004766414,0.0012581142,0.0011847051,0.0026450476,0.00060704787],"domain_scores_gemma":[0.9959558,0.0015910215,0.00045229038,0.0010427701,0.00060905615,0.00034906235],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008970705,0.0003241305,0.0006146411,0.00049982104,0.000181227,0.00015899453,0.0011871536,0.0001845597,0.00014595104],"category_scores_gemma":[0.012014431,0.0002167376,0.00013504199,0.0023767853,0.00011854831,0.00014949271,0.000082045706,0.0002538236,0.00012524436],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039521253,0.0004750317,0.0007481046,0.0000031273319,0.000008281066,0.0000040271284,0.0003432378,0.00089766283,0.07339801,0.0004868015,0.000262995,0.9229775],"study_design_scores_gemma":[0.0018030982,0.0057616984,0.7897471,0.00005121161,0.00002110837,0.000020431487,0.0008258669,0.0030818095,0.023216736,0.1745421,0.00034525053,0.0005835426],"about_ca_topic_score_codex":0.000009326013,"about_ca_topic_score_gemma":0.000004888982,"teacher_disagreement_score":0.922394,"about_ca_system_score_codex":0.00011294928,"about_ca_system_score_gemma":0.00003368443,"threshold_uncertainty_score":0.9963078},"labels":[],"label_agreement":null},{"id":"W2134979859","doi":"10.1177/01466210022031606","title":"Cross-Validation Sample Sizes","year":2000,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Sample size determination; Mathematics; Correlation coefficient; Mean squared error; Correlation; Pearson product-moment correlation coefficient; Linear regression; Sample (material); Cross-validation; Coefficient of determination; Chemistry","score_opus":0.33440989904627344,"score_gpt":0.4815746876227396,"score_spread":0.14716478857646614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134979859","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0601935,0.00003012081,0.8382469,0.00014313514,0.00010907743,0.0005111779,0.000022775632,0.00021729972,0.100526005],"genre_scores_gemma":[0.5727174,0.000015037828,0.42651784,0.0003399234,0.000081005666,0.00013088436,0.0000045275333,0.000017058343,0.00017628133],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99801946,0.00009288478,0.0004135451,0.00048752432,0.0006272478,0.0003593205],"domain_scores_gemma":[0.99874085,0.0005536171,0.00007224308,0.0003995186,0.000090973015,0.0001427691],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010811859,0.00019971986,0.00027650254,0.000021696906,0.00014121112,0.00004675661,0.0001917056,0.00012132729,0.008482951],"category_scores_gemma":[0.00070112245,0.00015015271,0.000070748676,0.00011976428,0.00010523712,0.000043426033,0.000018157172,0.00018474317,0.000213954],"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":[0.00023548299,0.0005608617,0.000042784133,0.000021363237,0.000025715322,0.000002798275,0.0000675584,0.000080736856,0.0047311424,0.35423595,0.0009764181,0.6390192],"study_design_scores_gemma":[0.00077557354,0.00012505923,0.0021738887,0.000011632561,0.000021328306,0.0000024219567,0.000010282359,0.000036887133,0.0023806312,0.9831209,0.011100967,0.0002404368],"about_ca_topic_score_codex":0.0000030708281,"about_ca_topic_score_gemma":0.0000010234851,"teacher_disagreement_score":0.63877875,"about_ca_system_score_codex":0.00006229845,"about_ca_system_score_gemma":0.000006159671,"threshold_uncertainty_score":0.9924234},"labels":[],"label_agreement":null},{"id":"W2143619291","doi":"10.1177/0146621603254799","title":"A New Look at the Influence of Guessing on the Reliability of Multiple-Choice Tests","year":2003,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":59,"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":"Variance (accounting); Reliability (semiconductor); Test (biology); Statistics; Econometrics; Psychology; Mathematics","score_opus":0.2678450942987462,"score_gpt":0.4308893442137286,"score_spread":0.1630442499149824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143619291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7027586,0.00005597592,0.2801444,0.00043377708,0.00007159766,0.0010614857,0.000008101655,0.00003238103,0.015433653],"genre_scores_gemma":[0.8681635,0.000004950616,0.13132492,0.00037065303,0.000015045292,0.0000657424,2.0473645e-7,0.000011490282,0.000043443008],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977028,0.0003597997,0.0005625548,0.00037564844,0.00074046856,0.0002587752],"domain_scores_gemma":[0.9914194,0.007170764,0.00029872914,0.00084893295,0.00017455342,0.00008764243],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025550586,0.00018981662,0.00032936313,0.000015179665,0.000121863304,0.000007119759,0.0002998236,0.00009254701,0.00013026934],"category_scores_gemma":[0.015205953,0.00008850744,0.000085545325,0.0001652211,0.00028249325,0.00001751964,0.000051596948,0.00026289106,0.000009589175],"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":[0.00044193742,0.0012631102,0.0018236747,0.00012465745,0.000059832695,0.0000014119107,0.00044179097,0.0023250422,0.158721,0.80756,0.002265084,0.024972416],"study_design_scores_gemma":[0.00089742354,0.00025965378,0.030101962,0.00011275799,0.000051808132,0.0000018958434,0.00007026379,0.000027067961,0.021630421,0.94500655,0.0016488696,0.0001913411],"about_ca_topic_score_codex":0.000008611828,"about_ca_topic_score_gemma":0.0000095325995,"teacher_disagreement_score":0.16540492,"about_ca_system_score_codex":0.00007474322,"about_ca_system_score_gemma":0.000022479095,"threshold_uncertainty_score":0.9930894},"labels":[],"label_agreement":null},{"id":"W2144652829","doi":"10.1177/0146621606288556","title":"Book Review: Adapting Educational and Psychological Tests for Cross-Cultural Assessment","year":2006,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Cross-cultural; Psychological testing; Applied psychology; Social psychology; Clinical psychology; Sociology; Anthropology","score_opus":0.18844240901473244,"score_gpt":0.4865119053793811,"score_spread":0.29806949636464863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144652829","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13998488,0.16875413,0.0039655757,0.04701756,0.0049692607,0.007958567,0.00015998652,0.00060852716,0.6265815],"genre_scores_gemma":[0.916043,0.0011848862,0.010564087,0.057706956,0.0017612233,0.0063591045,0.0002957085,0.00006124119,0.006023831],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9951558,0.00022103863,0.0011114667,0.0016510107,0.00094761315,0.0009130668],"domain_scores_gemma":[0.9976309,0.0004966629,0.00040837296,0.000642951,0.00051943236,0.00030169313],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016904679,0.0005736463,0.00062138063,0.00008377024,0.0004522569,0.0001582265,0.0005340241,0.00037227044,0.008822495],"category_scores_gemma":[0.00014204007,0.00041493087,0.00024008584,0.00031715902,0.0004539169,0.00014369395,0.00007290327,0.00054428924,0.00031626725],"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":[0.00023252566,0.004889497,0.0054926323,0.00011430078,0.00009299812,0.0000041248823,0.000039816627,0.0000035187975,0.0025084496,0.093149416,0.8839024,0.009570332],"study_design_scores_gemma":[0.0019114066,0.00061556447,0.6311308,0.00012800086,0.00006460698,0.000059805123,0.00004465758,0.0000017818724,0.00001281835,0.017081585,0.34841523,0.0005337634],"about_ca_topic_score_codex":0.000013517113,"about_ca_topic_score_gemma":0.0000018290289,"teacher_disagreement_score":0.7760581,"about_ca_system_score_codex":0.00018970057,"about_ca_system_score_gemma":0.000030501777,"threshold_uncertainty_score":0.99983025},"labels":[],"label_agreement":null},{"id":"W2151525783","doi":"10.1177/0146621610378289","title":"A Test-Length Correction to the Estimation of Extreme Proficiency Levels","year":2010,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"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":"Maximum a posteriori estimation; Estimator; Statistics; Rasch model; Mathematics; Bayes estimator; Item response theory; Bayesian probability; Estimation; Bias of an estimator; Scale (ratio); Econometrics; Maximum likelihood; Minimum-variance unbiased estimator; Psychometrics","score_opus":0.6476178436147106,"score_gpt":0.4734027822600229,"score_spread":0.17421506135468773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151525783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54486835,0.000049284346,0.37814662,0.0023933218,0.0057072346,0.0014812317,0.0000074629916,0.00014351636,0.06720301],"genre_scores_gemma":[0.96428055,0.0000012160931,0.034853183,0.00047752072,0.00012880638,0.00013098077,4.166328e-7,0.000007989258,0.00011936719],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9952479,0.00025235806,0.00090379646,0.0007240631,0.0025154043,0.00035650452],"domain_scores_gemma":[0.9894258,0.0083786985,0.00044525342,0.0010809128,0.0005227833,0.00014658232],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018966364,0.00018849279,0.00032017208,0.0002723295,0.0002334786,0.00010322131,0.0011758885,0.00011261047,0.0005033629],"category_scores_gemma":[0.1078829,0.00009739503,0.00010487176,0.0025489142,0.00013193984,0.000057082827,0.00011873562,0.0004382833,0.000245997],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052090018,0.0003987245,0.004799329,0.0000022676222,0.0000071785244,5.5887335e-7,0.00024151278,0.0005349847,0.0856842,0.002205799,0.011021877,0.8950515],"study_design_scores_gemma":[0.0005386989,0.00060526637,0.94775057,0.000018548655,0.000017721099,0.000017343395,0.00044047882,0.002573303,0.008017817,0.033295635,0.0064427964,0.00028180628],"about_ca_topic_score_codex":0.00001122123,"about_ca_topic_score_gemma":0.000015881495,"teacher_disagreement_score":0.94295126,"about_ca_system_score_codex":0.00003374953,"about_ca_system_score_gemma":0.000027254153,"threshold_uncertainty_score":0.8996318},"labels":[],"label_agreement":null},{"id":"W2169517221","doi":"10.1177/0146621610391777","title":"Accuracy of Person-Fit Statistics","year":2011,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Université de Sherbrooke","funders":"","keywords":"Statistics; Cheating; Monte Carlo method; Mathematics; Econometrics; Psychology; Social psychology","score_opus":0.24308051572562275,"score_gpt":0.34340061958845114,"score_spread":0.10032010386282839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169517221","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001705557,0.000088764406,0.95631826,0.000055831213,0.00006713179,0.0002469835,0.0000024578217,0.00023410442,0.04128091],"genre_scores_gemma":[0.60950327,0.000016308699,0.39021766,0.00019613077,0.000010528735,0.00004218567,5.223339e-7,0.00000494812,0.000008437964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99819034,0.000046201672,0.00033294692,0.00047939876,0.0006786055,0.00027248735],"domain_scores_gemma":[0.9985755,0.000057893154,0.00024502332,0.0008258362,0.0001964074,0.000099330246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060128054,0.00016926057,0.00026161643,0.000081844926,0.000051934363,0.000017048136,0.0010485186,0.000079263904,0.00016749992],"category_scores_gemma":[0.00009860872,0.00013337107,0.00007115871,0.00033371203,0.000098313496,0.00009688462,0.00010480464,0.00015548938,0.000072316005],"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":[0.000043559463,0.00090991834,0.00029746705,0.00001418767,0.00007003129,0.000011031197,0.0007323579,0.0000035988805,0.031224005,0.609364,0.0036980105,0.35363188],"study_design_scores_gemma":[0.0023307512,0.0018557762,0.109068535,0.00008059844,0.00014596827,0.000022928905,0.00031648792,0.00092863233,0.25544438,0.618771,0.009245131,0.0017897821],"about_ca_topic_score_codex":0.000008275875,"about_ca_topic_score_gemma":0.0000025080528,"teacher_disagreement_score":0.60779774,"about_ca_system_score_codex":0.000050905313,"about_ca_system_score_gemma":0.000013786426,"threshold_uncertainty_score":0.5438714},"labels":[],"label_agreement":null},{"id":"W2171716385","doi":"10.1177/0146621614520958","title":"Maximum-Likelihood Estimation of Noncompensatory IRT Models With the MH-RM Algorithm","year":2014,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"York University","funders":"","keywords":"Item response theory; Estimation; Maximum likelihood; Latent variable; Statistics; Computer science; Econometrics; Population; Estimation theory; Expectation–maximization algorithm; Mathematics; Algorithm; Artificial intelligence; Machine learning; Psychometrics; Engineering","score_opus":0.3757797696663633,"score_gpt":0.40160231143503256,"score_spread":0.02582254176866927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171716385","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040106766,0.00011884035,0.89278513,0.0007797897,0.0003044304,0.0005083523,0.000002921853,0.00008104049,0.06531275],"genre_scores_gemma":[0.8049097,0.0000050677586,0.19421335,0.0006948803,0.00007831468,0.00007166786,9.894686e-7,0.000012020318,0.000014037627],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99399275,0.0006013524,0.00084995595,0.0008182541,0.0032829985,0.0004546724],"domain_scores_gemma":[0.9925699,0.0049685566,0.0006205798,0.0012196526,0.00046553204,0.00015574285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01794613,0.00026875155,0.0005432332,0.0002043824,0.0002199564,0.000104368046,0.0012754836,0.00014207563,0.00015147313],"category_scores_gemma":[0.0037392706,0.00012773873,0.00012304162,0.0014240784,0.00027834997,0.00009046604,0.00011942141,0.00032164267,0.00009133641],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093207884,0.00021492754,0.00021223321,0.000003946574,0.000028834827,9.582546e-7,0.00012477963,0.00333622,0.00070703164,0.006621474,0.002270075,0.9863863],"study_design_scores_gemma":[0.0027869365,0.0013544795,0.08148589,0.000053010903,0.00007556499,0.00002677387,0.00092074974,0.04608518,0.0011875669,0.8581313,0.0072558345,0.0006367466],"about_ca_topic_score_codex":0.000010272451,"about_ca_topic_score_gemma":0.0000033156846,"teacher_disagreement_score":0.98574954,"about_ca_system_score_codex":0.00005461424,"about_ca_system_score_gemma":0.000026086822,"threshold_uncertainty_score":0.6219806},"labels":[],"label_agreement":null},{"id":"W2580371235","doi":"10.1177/0146621616684584","title":"An Evaluation of Interrater Reliability Measures on Binary Tasks Using <i>d-Prime</i>","year":2016,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Inter-rater reliability; Kappa; Prime (order theory); Psychology; Statistics; Reliability (semiconductor); Cohen's kappa; Binary number; Agreement; Psychometrics; Social psychology; Mathematics; Combinatorics; Arithmetic; Rating scale; Linguistics","score_opus":0.5204254440661797,"score_gpt":0.4693431790011876,"score_spread":0.05108226506499214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2580371235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96720684,0.00007349334,0.017677976,0.0012774194,0.0008208781,0.0014641808,0.000016154849,0.00007133694,0.011391706],"genre_scores_gemma":[0.9975315,0.000009064229,0.0014612873,0.0006964535,0.00012401963,0.00014329534,0.0000015918083,0.000017438788,0.000015391912],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98265845,0.0021804634,0.0017171813,0.0016102736,0.011309546,0.0005240708],"domain_scores_gemma":[0.99381554,0.00044840586,0.00060400134,0.0024042442,0.0024629426,0.0002648791],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.051340144,0.00039420204,0.0006055025,0.0002234392,0.00018801454,0.00009159016,0.0013565761,0.00024389292,0.001702357],"category_scores_gemma":[0.0034151927,0.00019960388,0.00024347505,0.00056700216,0.00039500234,0.00022629647,0.000107899,0.00023449621,0.00030538128],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080110953,0.002245128,0.0036005555,0.000005222885,0.000037854956,7.9126335e-7,0.00013777122,0.0013157636,0.77225673,0.0006300569,0.0021369685,0.21683203],"study_design_scores_gemma":[0.010008819,0.0051908647,0.31831816,0.00042442497,0.0003987158,0.0000070522187,0.0008105951,0.0020375578,0.38310438,0.2652449,0.012669214,0.0017853181],"about_ca_topic_score_codex":0.000010817869,"about_ca_topic_score_gemma":0.0000076647375,"teacher_disagreement_score":0.38915235,"about_ca_system_score_codex":0.0005671026,"about_ca_system_score_gemma":0.00009329298,"threshold_uncertainty_score":0.99921024},"labels":[],"label_agreement":null},{"id":"W2582841787","doi":"10.1177/0146621615597894","title":"faoutlier","year":2015,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Exploratory factor analysis; Computer science; Confirmatory factor analysis; Regression analysis; Software; Extant taxon; Factor (programming language); Statistics; Statistical analysis; Regression; Artificial intelligence; Machine learning; Mathematics; Structural equation modeling; Programming language; Biology","score_opus":0.6421002834531417,"score_gpt":0.5022808864825751,"score_spread":0.13981939697056667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2582841787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003410337,0.000045264074,0.81191105,0.0002272754,0.00021624571,0.0003437318,0.0000030485928,0.00015904706,0.18368402],"genre_scores_gemma":[0.5578363,0.0000020937366,0.44131356,0.00053855637,0.000083794264,0.000103816004,7.390354e-7,0.000015850803,0.000105299776],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980718,0.000090451904,0.0003169145,0.00040533906,0.00077570433,0.00033977954],"domain_scores_gemma":[0.9989004,0.00015906076,0.00007441376,0.00038568722,0.00015871211,0.00032172402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016218981,0.00018015606,0.0002762455,0.000026937218,0.00004959356,0.000017962595,0.00019212773,0.00010420891,0.00013424737],"category_scores_gemma":[0.0009358933,0.00012662815,0.000051471645,0.000112589565,0.000075780954,0.000023959012,0.000045098805,0.00019679054,0.00018079006],"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":[0.000121428806,0.00046402644,0.000012227124,0.000008887063,0.000020818283,0.000007721132,0.00012132869,0.0000079441315,0.0018852102,0.9077596,0.014349834,0.07524097],"study_design_scores_gemma":[0.00089733605,0.00015474753,0.00017369507,0.0000074109807,0.00001965651,0.0000042553947,0.00008445683,0.000020202233,0.00042124506,0.9826304,0.015391079,0.00019552448],"about_ca_topic_score_codex":7.596009e-7,"about_ca_topic_score_gemma":8.7095674e-7,"teacher_disagreement_score":0.55442595,"about_ca_system_score_codex":0.0000933732,"about_ca_system_score_gemma":0.000012993605,"threshold_uncertainty_score":0.5163746},"labels":[],"label_agreement":null},{"id":"W2590325518","doi":"10.1177/0146621617692079","title":"Plausible-Value Imputation Statistics for Detecting Item Misfit","year":2017,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Statistics; Statistic; Item response theory; Trait; Imputation (statistics); Econometrics; Parametric statistics; Test statistic; Mathematics; Statistical hypothesis testing; Differential item functioning; Latent variable model; Item analysis; Null hypothesis; Latent variable; Computer science; Psychometrics; Missing data","score_opus":0.72207883373125,"score_gpt":0.5322352636234017,"score_spread":0.18984357010784836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590325518","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10147127,0.00007272288,0.87050205,0.00051090267,0.0013802287,0.0008912444,0.000032281623,0.00011476107,0.02502454],"genre_scores_gemma":[0.727478,0.000004541742,0.27173436,0.00033702137,0.00022376052,0.00013736579,0.0000018900017,0.000014323236,0.00006871617],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9950816,0.00021704278,0.0009786108,0.0010469654,0.0020982097,0.0005775632],"domain_scores_gemma":[0.98522496,0.011755716,0.0010677215,0.0011181935,0.00063147664,0.00020192581],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016107928,0.00026006994,0.00047548488,0.00021007111,0.0012410905,0.0007584816,0.0015413291,0.00018938714,0.00019504878],"category_scores_gemma":[0.12904336,0.00018091715,0.00013488105,0.00036239848,0.00014861794,0.00010946947,0.00017010396,0.00025430133,0.00011126624],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023551084,0.00018297693,0.007813961,0.000012567591,0.000037818423,0.0000036570648,0.00007877905,0.0002076964,0.0073911105,0.02795454,0.007716538,0.94836485],"study_design_scores_gemma":[0.0025797356,0.0006044953,0.5173778,0.00003169721,0.000046119636,0.000012817579,0.00040239366,0.0040681437,0.001857552,0.45918143,0.01328402,0.00055377913],"about_ca_topic_score_codex":0.0000131764955,"about_ca_topic_score_gemma":0.0000090986405,"teacher_disagreement_score":0.94781107,"about_ca_system_score_codex":0.00009325043,"about_ca_system_score_gemma":0.000026992057,"threshold_uncertainty_score":0.95455897},"labels":[],"label_agreement":null},{"id":"W2745464303","doi":"10.1177/0146621617726788","title":"Using Automatic Item Generation to Create Solutions and Rationales for Computerized Formative Testing","year":2017,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Computer science; Item bank; Computerized adaptive testing; Test (biology); Quality (philosophy); Item response theory; Psychometrics; Psychology; Mathematics education","score_opus":0.534223811307965,"score_gpt":0.38532894042215204,"score_spread":0.148894870885813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745464303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07323544,0.000026772394,0.92433506,0.0003514246,0.0003149278,0.0006929854,0.0000014623122,0.00009359196,0.00094835495],"genre_scores_gemma":[0.7137338,6.2115265e-7,0.28581193,0.00016354934,0.00014553698,0.00011834047,9.078199e-7,0.0000046665386,0.000020684556],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875003,0.000048769496,0.00027874636,0.00037185592,0.00029275304,0.00025784652],"domain_scores_gemma":[0.99903125,0.000101847836,0.0002170621,0.00033527843,0.00022710991,0.000087429406],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0010600757,0.00013743741,0.00017712203,0.000049703445,0.0013060189,0.00036640515,0.00035047217,0.00004791889,0.0000021456185],"category_scores_gemma":[0.0002930706,0.00011283131,0.000034725123,0.000056027453,0.000030463027,0.00019256651,0.00014210165,0.00007154422,0.000010299624],"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":[0.00002282412,0.00017422941,0.00036115412,0.000055764813,0.000075302785,0.000002352088,0.0014896374,0.003588975,0.31898528,0.51809084,0.0004915687,0.15666205],"study_design_scores_gemma":[0.0013914419,0.00048306707,0.045209832,0.00024738384,0.000026818117,0.0000240407,0.00009057285,0.9371367,0.0045535727,0.0055081537,0.0047221645,0.0006062655],"about_ca_topic_score_codex":0.000008349119,"about_ca_topic_score_gemma":0.000002219281,"teacher_disagreement_score":0.93354774,"about_ca_system_score_codex":0.00008550854,"about_ca_system_score_gemma":0.000016405902,"threshold_uncertainty_score":0.99999416},"labels":[],"label_agreement":null},{"id":"W3016903275","doi":"10.1177/0146621620909897","title":"The Monotonic Polynomial Graded Response Model: Implementation and a Comparative Study","year":2020,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"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":"Fonds de recherche du Québec – Nature et technologies","keywords":"Monotonic function; Mathematics; Categorical variable; Probit; Probit model; Heteroscedasticity; Polynomial; Applied mathematics; Logistic regression; Function (biology); Statistics; Econometrics","score_opus":0.8339036917039917,"score_gpt":0.5454023379535109,"score_spread":0.2885013537504808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016903275","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97972864,0.00020697202,0.010385547,0.0043679313,0.00016793233,0.0015022585,0.0000036750123,0.00008625208,0.003550816],"genre_scores_gemma":[0.99588794,0.000010874297,0.0027766954,0.0010356396,0.00006185197,0.00020764559,3.456161e-7,0.0000064765,0.000012511682],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9945073,0.0014419673,0.0008622382,0.0009071004,0.0018934486,0.0003879262],"domain_scores_gemma":[0.99165344,0.0071010767,0.00033422493,0.00049781625,0.00018394772,0.00022946812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0146900425,0.00021912725,0.0003991887,0.00009310507,0.0005340399,0.00031169446,0.00077104993,0.00006276514,0.000053729676],"category_scores_gemma":[0.0069329287,0.000117553565,0.00007242752,0.0010748924,0.00015310041,0.00005797681,0.00019977946,0.00027926103,0.000045903394],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028103948,0.0018695503,0.030448586,0.0000060629127,0.0004191737,0.000023625424,0.024394546,0.00166861,0.075832844,0.0099963145,0.073522635,0.7537141],"study_design_scores_gemma":[0.008778771,0.0049229655,0.8567132,0.0000052463906,0.00008270348,0.000008095958,0.07796169,0.0054039806,0.0013651015,0.03361682,0.010368468,0.00077299617],"about_ca_topic_score_codex":0.000005048678,"about_ca_topic_score_gemma":0.000009585676,"teacher_disagreement_score":0.82626456,"about_ca_system_score_codex":0.00005512619,"about_ca_system_score_gemma":0.000029374325,"threshold_uncertainty_score":0.8299864},"labels":[],"label_agreement":null},{"id":"W3022866891","doi":"10.1177/0146621620909898","title":"Partially and Fully Noncompensatory Response Models for Dichotomous and Polytomous Items","year":2020,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"","keywords":"Polytomous Rasch model; Item response theory; Econometrics; Set (abstract data type); Statistics; Computer science; Psychometrics; Mathematics","score_opus":0.700374042316265,"score_gpt":0.4526023993021298,"score_spread":0.24777164301413518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022866891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7341497,0.0016916197,0.24618748,0.0075490745,0.00043306203,0.0017270081,0.000034264416,0.00024333423,0.007984468],"genre_scores_gemma":[0.97389287,0.000035389945,0.021335898,0.0043983073,0.00013609574,0.00016807183,9.238002e-7,0.000014532491,0.000017885222],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953348,0.00055453094,0.00084651326,0.0012747257,0.0014885899,0.0005008237],"domain_scores_gemma":[0.98979443,0.008641582,0.00029877538,0.00048569535,0.00026002678,0.00051949103],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012647056,0.00028581807,0.00058850483,0.00016194387,0.0002496805,0.00024136323,0.0005669784,0.00018308584,0.000059877097],"category_scores_gemma":[0.019224513,0.00019570644,0.000095978896,0.00072468875,0.00022062428,0.0000889208,0.00018047703,0.00024677324,0.000028556911],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01745035,0.00054702617,0.005096177,0.00004965548,0.00013920983,0.00004904042,0.0020529423,0.00053517544,0.1383571,0.011575821,0.024975674,0.7991718],"study_design_scores_gemma":[0.018933827,0.010153491,0.34850484,0.00007917081,0.00021985154,0.00016967452,0.0038125324,0.019731374,0.0042892676,0.4486026,0.1423895,0.0031138863],"about_ca_topic_score_codex":0.0000027847648,"about_ca_topic_score_gemma":0.0000016608276,"teacher_disagreement_score":0.79605794,"about_ca_system_score_codex":0.000031911768,"about_ca_system_score_gemma":0.000029312936,"threshold_uncertainty_score":0.989037},"labels":[],"label_agreement":null},{"id":"W3035107461","doi":"10.1177/0146621620929431","title":"OpenMx: A Modular Research Environment for Item Response Theory Method Development","year":2020,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute on Drug Abuse; National Institutes of Health","keywords":"Modular design; Computer science; Implementation; Item response theory; Source code; Code (set theory); Selection (genetic algorithm); Software; Software engineering; Theoretical computer science; Programming language; Machine learning; Statistics; Mathematics; Psychometrics","score_opus":0.9218223146811826,"score_gpt":0.5923631288612036,"score_spread":0.329459185819979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035107461","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058314368,0.00045996395,0.92320925,0.006693102,0.00027567756,0.0022647576,0.000008164497,0.0001369433,0.008637769],"genre_scores_gemma":[0.5871417,0.0000104019955,0.40956843,0.0021774836,0.00014166888,0.0007867218,0.0000017178423,0.000025697625,0.00014621233],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98507893,0.005110349,0.0014356287,0.0020916988,0.0052606645,0.0010227036],"domain_scores_gemma":[0.95124596,0.046180584,0.000340191,0.0011616688,0.00048000872,0.0005915749],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13675483,0.0003539798,0.0006984674,0.00038827147,0.0005998886,0.00025722818,0.002182934,0.0002477593,0.0009966706],"category_scores_gemma":[0.11555357,0.00023517567,0.00020214717,0.0018535473,0.00020328368,0.00006869371,0.0005525107,0.0005993436,0.00076755893],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008510056,0.00053916307,0.00033804277,0.000015301039,0.00010178025,0.000014594546,0.0012996718,0.00028533526,0.07766089,0.014852761,0.015061834,0.8813206],"study_design_scores_gemma":[0.002729097,0.0014035067,0.054489605,0.000022196362,0.000022396142,0.000007519898,0.0025047339,0.00041483037,0.010207494,0.13103774,0.796499,0.00066186645],"about_ca_topic_score_codex":7.316912e-7,"about_ca_topic_score_gemma":2.3053896e-7,"teacher_disagreement_score":0.8806587,"about_ca_system_score_codex":0.00024695974,"about_ca_system_score_gemma":0.00008169239,"threshold_uncertainty_score":0.99991655},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3037823530","doi":"10.1177/0146621620931190","title":"An Exploratory Strategy to Identify and Define Sources of Differential Item Functioning","year":2020,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Ministry of Science and Technology","keywords":"Differential item functioning; Item response theory; Differential (mechanical device); Set (abstract data type); Computer science; Dimension (graph theory); Psychology; Process (computing); Data mining; Cognitive psychology; Psychometrics; Mathematics; Developmental psychology","score_opus":0.15829898309091692,"score_gpt":0.3541875478248856,"score_spread":0.19588856473396868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037823530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20168069,0.000041864176,0.79721713,0.00025317352,0.000045609457,0.00022191805,0.0000020969337,0.0002585878,0.00027893888],"genre_scores_gemma":[0.8783077,0.000004781313,0.12085632,0.0007132248,0.000043637996,0.00006465443,0.0000010581567,0.000008238051,3.5251836e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982367,0.00006720303,0.0003308237,0.00062242046,0.00051954755,0.00022328088],"domain_scores_gemma":[0.9991368,0.000048591,0.000084894455,0.00033573972,0.000108649816,0.00028531565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028814594,0.00016381024,0.00023577492,0.00004336933,0.00007622099,0.000075758835,0.00047516648,0.000068733745,0.000019724264],"category_scores_gemma":[0.000084096166,0.00013689531,0.000027218603,0.00021396707,0.00005925379,0.00011274492,0.00014933012,0.00015157119,0.000011341354],"study_design_candidate":"bench_or_experimental","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":[0.00021988084,0.00043198263,0.0003954573,0.000043780117,0.000032592707,0.00000967031,0.00096724025,0.00093729154,0.577937,0.19007517,0.0004223923,0.22852752],"study_design_scores_gemma":[0.0056167375,0.019938141,0.19087921,0.00026755608,0.00016064645,0.000027761405,0.0012641011,0.051663958,0.19437955,0.53089154,0.0013023483,0.0036084277],"about_ca_topic_score_codex":0.0000013311527,"about_ca_topic_score_gemma":0.0000011313731,"teacher_disagreement_score":0.67662704,"about_ca_system_score_codex":0.00002097436,"about_ca_system_score_gemma":0.000008131288,"threshold_uncertainty_score":0.55824286},"labels":[],"label_agreement":null},{"id":"W4223957752","doi":"10.1177/01466216221084210","title":"A Comparison of Modern and Popular Approaches to Calculating Reliability for Dichotomously Scored Items","year":2022,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Multi-Criteria Decision Making","field":"Decision Sciences","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":"McGill University; Université de Montréal","funders":"","keywords":"Cronbach's alpha; Reliability (semiconductor); Monte Carlo method; Statistics; Mathematics; Econometrics; Psychology; Computer science; Psychometrics","score_opus":0.7494451842918853,"score_gpt":0.49012840491475185,"score_spread":0.2593167793771335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223957752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81248736,0.00019329118,0.18340428,0.00048666718,0.00028203512,0.0021990668,0.000039208477,0.000050909268,0.00085716473],"genre_scores_gemma":[0.9604758,3.6094957e-7,0.038148694,0.0003553931,0.00004084373,0.00093420316,0.0000049253854,0.0000190524,0.000020700845],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926737,0.00041340082,0.0015625779,0.0013727028,0.0035550203,0.000422586],"domain_scores_gemma":[0.99724233,0.00074536476,0.0004855465,0.0010441873,0.00024938706,0.00023318318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012107792,0.00025343546,0.00078014296,0.00023007685,0.0004282589,0.00012981513,0.0009510498,0.00009398497,0.00013445366],"category_scores_gemma":[0.0027345554,0.0001911907,0.00016205301,0.0006935742,0.00011008307,0.000052166808,0.00054618693,0.00027161892,0.000009343168],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003321746,0.0032349462,0.045614798,0.000054824464,0.000069216236,0.0000041122785,0.0064742104,0.03845524,0.12337296,0.011701948,0.0053019854,0.762394],"study_design_scores_gemma":[0.009644388,0.0038825797,0.18868871,0.000091230504,0.00014444454,0.000028202345,0.00765675,0.24165489,0.00550148,0.48834825,0.052166045,0.0021930172],"about_ca_topic_score_codex":0.000011026285,"about_ca_topic_score_gemma":0.000007912944,"teacher_disagreement_score":0.760201,"about_ca_system_score_codex":0.00013816176,"about_ca_system_score_gemma":0.00001821389,"threshold_uncertainty_score":0.7796531},"labels":[],"label_agreement":null},{"id":"W4293408802","doi":"10.1177/01466216221124089","title":"Item Selection With Collaborative Filtering in On-The-Fly Multistage Adaptive Testing","year":2022,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computerized adaptive testing; Item bank; Selection (genetic algorithm); Computer science; Item response theory; Collaborative filtering; On the fly; Feature selection; Test (biology); Machine learning; Data mining; Artificial intelligence; Statistics; Recommender system; Mathematics; Psychometrics","score_opus":0.6812333426754545,"score_gpt":0.43299204654842544,"score_spread":0.2482412961270291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293408802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85351354,0.0000939414,0.033866536,0.0009608243,0.00047506654,0.0017366566,0.000018183046,0.00017978935,0.10915546],"genre_scores_gemma":[0.9688712,0.0000010616221,0.029410314,0.0008741032,0.000055607958,0.0007100754,6.415321e-7,0.000014014813,0.00006302418],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9939356,0.0012060183,0.0006642339,0.0009872083,0.0027348048,0.00047212976],"domain_scores_gemma":[0.9827898,0.015838912,0.0004424195,0.000490337,0.0003467075,0.00009179107],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013283672,0.00024548717,0.00036651042,0.00036280643,0.00067800365,0.00013495829,0.0008201291,0.000056126304,0.0005516226],"category_scores_gemma":[0.016498785,0.00013980795,0.00004664822,0.006474267,0.00010609409,0.00005057476,0.0001896474,0.00072258624,0.000036792957],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005642999,0.002815352,0.08965644,0.000010137962,0.00016352945,0.000180964,0.0027914736,0.04678565,0.07099558,0.03223433,0.014103996,0.73461956],"study_design_scores_gemma":[0.005518064,0.008989912,0.88807994,0.0001008901,0.000030095205,0.00009479337,0.02435626,0.007005433,0.0034744423,0.042024504,0.018832145,0.0014935369],"about_ca_topic_score_codex":0.000019621531,"about_ca_topic_score_gemma":0.000020446869,"teacher_disagreement_score":0.79842347,"about_ca_system_score_codex":0.00033511908,"about_ca_system_score_gemma":0.00004279819,"threshold_uncertainty_score":0.99178565},"labels":[],"label_agreement":null},{"id":"W4317423393","doi":"10.1177/01466216231151704","title":"A New Approach to Desirable Responding: Multidimensional Item Response Model of Overclaiming Data","year":2023,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":4,"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 British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Ministry of Science and Technology, Taiwan","keywords":"Item response theory; Variety (cybernetics); Set (abstract data type); Computer science; Selection (genetic algorithm); Response bias; Empirical research; Artificial intelligence; Machine learning; Psychology; Econometrics; Cognitive psychology; Statistics; Psychometrics; Social psychology; Mathematics","score_opus":0.4958442413042139,"score_gpt":0.4335076058483659,"score_spread":0.062336635455848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317423393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61862266,0.00007298621,0.059430774,0.0063766288,0.0010658358,0.0020000427,0.00005038699,0.0006251938,0.3117555],"genre_scores_gemma":[0.9680055,0.000017865612,0.028314643,0.0012399317,0.00020241167,0.00007909341,0.000015927106,0.000022031612,0.002102618],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962054,0.00045725197,0.00046216248,0.00092267024,0.0013141512,0.0006383895],"domain_scores_gemma":[0.9981563,0.0003971945,0.00012583467,0.00082070346,0.00013403983,0.00036594036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007739805,0.00019302989,0.00033963704,0.00028288167,0.00036061663,0.00002986372,0.0010657937,0.00025723188,0.00021690123],"category_scores_gemma":[0.0015609188,0.0001718734,0.00008088383,0.0014126186,0.0001695455,0.00008791752,0.00029430835,0.0002316271,0.00041366194],"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":[0.00797434,0.0010032308,0.00025484103,0.000014975679,0.00011056954,0.0000056767435,0.014359289,0.00096728565,0.4325565,0.1749961,0.34594426,0.021812942],"study_design_scores_gemma":[0.015132166,0.002302573,0.13286193,0.00045168708,0.00035424336,0.0000125338265,0.0499942,0.012722441,0.007627157,0.12529866,0.6484345,0.004807887],"about_ca_topic_score_codex":0.0001189897,"about_ca_topic_score_gemma":0.00002251083,"teacher_disagreement_score":0.42492935,"about_ca_system_score_codex":0.00017479203,"about_ca_system_score_gemma":0.00015596395,"threshold_uncertainty_score":0.7008794},"labels":[],"label_agreement":null},{"id":"W4327910164","doi":"10.1177/01466216231165299","title":"Confidence Screening Detector: A New Method for Detecting Test Collusion","year":2023,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Collusion; Cheating; Clique; Computer science; Test (biology); Detector; Item response theory; Scale (ratio); Statistical hypothesis testing; Variable (mathematics); Similarity (geometry); Selection (genetic algorithm); Statistics; Data mining; Algorithm; Machine learning; Artificial intelligence; Mathematics; Psychology; Psychometrics; Social psychology","score_opus":0.7210023253769497,"score_gpt":0.531043618285663,"score_spread":0.1899587070912867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327910164","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01494691,0.00012976084,0.9746787,0.0009962765,0.000871349,0.00121214,0.000009984331,0.00059185195,0.006563029],"genre_scores_gemma":[0.60958844,0.000009999426,0.3889287,0.00071853714,0.00030532756,0.00020987757,0.0000014371795,0.000024236153,0.00021344342],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99299604,0.00043098303,0.0012276926,0.0015474571,0.0028792233,0.0009186168],"domain_scores_gemma":[0.94710565,0.050225694,0.0006227305,0.0010749369,0.0005475571,0.00042341326],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03331906,0.00034571654,0.0006634211,0.00062933745,0.00061284396,0.0003055469,0.0014014973,0.00025424015,0.00028642823],"category_scores_gemma":[0.16427304,0.00024203834,0.00026447696,0.004983244,0.000076057215,0.00008341152,0.00030160134,0.00036942572,0.00031265846],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019230135,0.0000743027,0.0018226623,0.0000074879704,0.000023547389,0.0000058899273,0.00013260554,0.0002920153,0.09936117,0.0015195876,0.018075733,0.8784927],"study_design_scores_gemma":[0.006413399,0.0021063124,0.26540652,0.00016957095,0.000101673824,0.00006194335,0.003065366,0.014022233,0.024205284,0.59286326,0.08991892,0.0016654966],"about_ca_topic_score_codex":0.000028961029,"about_ca_topic_score_gemma":0.000013381505,"teacher_disagreement_score":0.8768272,"about_ca_system_score_codex":0.000089491536,"about_ca_system_score_gemma":0.00004891637,"threshold_uncertainty_score":0.99540144},"labels":[],"label_agreement":null},{"id":"W4405622011","doi":"10.1177/01466216241310600","title":"An Information Manifold Perspective for Analyzing Test Data","year":2024,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","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":"Ottawa Hospital; McGill University","funders":"","keywords":"Item response theory; Mathematics; Measure (data warehouse); Metric (unit); Computer science; Test (biology); Manifold (fluid mechanics); Perspective (graphical); Scale (ratio); Artificial intelligence; Data mining; Statistics; Psychometrics","score_opus":0.7563916288387372,"score_gpt":0.5558183455944733,"score_spread":0.20057328324426393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405622011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009968944,0.0010179516,0.91314125,0.002160958,0.0017157239,0.0012667975,0.00016466418,0.00054900977,0.07001472],"genre_scores_gemma":[0.9578236,0.00001782837,0.041151702,0.0005583303,0.00028818127,0.00010134753,0.00002729786,0.000010299975,0.000021453996],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959873,0.00011208923,0.0007973635,0.001057425,0.0016507447,0.00039506017],"domain_scores_gemma":[0.98934716,0.008083365,0.00019275032,0.0016512835,0.00055532856,0.0001701278],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017932411,0.00020749216,0.0003120292,0.00047198657,0.00021045325,0.00090785476,0.0019126268,0.00013274903,0.00024461717],"category_scores_gemma":[0.035417154,0.00013275571,0.00009340419,0.0018448551,0.000054285203,0.00070074433,0.00017084806,0.00024462774,0.0002875839],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013484221,0.00037387345,0.0022883017,0.000022293128,0.00007631572,0.0000049162927,0.00052523066,0.000071512455,0.0052818693,0.13202271,0.048787616,0.8104105],"study_design_scores_gemma":[0.0016819321,0.0016426276,0.12361095,0.00008674321,0.00014393627,0.00003515967,0.009089461,0.01582799,0.0005510147,0.63980675,0.20643166,0.0010917754],"about_ca_topic_score_codex":0.0000100995985,"about_ca_topic_score_gemma":0.0000040662458,"teacher_disagreement_score":0.94785464,"about_ca_system_score_codex":0.00013876829,"about_ca_system_score_gemma":0.000033774188,"threshold_uncertainty_score":0.9727079},"labels":[],"label_agreement":null},{"id":"W4412156054","doi":"10.1177/01466216251358492","title":"Including Empirical Prior Information in the Reliable Change Index","year":2025,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Evaluation and Performance Assessment","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":"York University","funders":"","keywords":"Index (typography); Statistics; Econometrics; Mathematics; Psychology; Computer science","score_opus":0.6224068475520583,"score_gpt":0.5555954167953175,"score_spread":0.06681143075674079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412156054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49109244,0.0001355187,0.012866363,0.037420686,0.0010029643,0.0025252737,0.000002062985,0.00009019939,0.4548645],"genre_scores_gemma":[0.9773301,0.000014405102,0.0003074054,0.021681678,0.00004790667,0.0005560362,0.0000027578192,0.0000020913237,0.00005760402],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9956038,0.00021569747,0.0008099866,0.00032886103,0.002757973,0.0002836688],"domain_scores_gemma":[0.99865806,0.00029479718,0.00017224859,0.00057450694,0.000254824,0.000045538276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0139393965,0.00014004909,0.0002092759,0.00030452915,0.0002103252,0.00024035959,0.0008223165,0.00012301817,0.00046977258],"category_scores_gemma":[0.0006021005,0.00007441773,0.00005838443,0.0018059126,0.00005652565,0.0003046732,0.00010958889,0.00031902903,0.0005792576],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040827086,0.0007193444,0.2332389,0.00001348435,0.000019112676,0.0000017336862,0.00493418,0.0003517708,0.0001483829,0.020121394,0.07163732,0.6684061],"study_design_scores_gemma":[0.0008862074,0.000058156093,0.80418533,0.000020145628,0.000004982458,4.8870567e-7,0.0011143291,0.00039999658,0.000035538025,0.016834343,0.1763555,0.00010499211],"about_ca_topic_score_codex":0.000008292787,"about_ca_topic_score_gemma":0.000018694827,"teacher_disagreement_score":0.6683011,"about_ca_system_score_codex":0.00016047743,"about_ca_system_score_gemma":0.00005416128,"threshold_uncertainty_score":0.74453783},"labels":[],"label_agreement":null}]}