{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":34,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":34,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"e5913b510d38","filters":{"venue":"Applied Psychological Measurement"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3235615786368179,"gpt":0.4344033213096365,"spread":0.1108417426728185,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001432756,0.0001117021,0.0002068801,0.0000165189,0.0001319883,0.000007623091,0.00007176911,0.00007455173,0.00001507379],"category_scores_gemma":[0.00315715,0.0000704214,0.00003994061,0.0001128752,0.0001265435,0.00001593296,0.000009278722,0.0001236831,6.634935e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003400618,"about_ca_system_score_gemma":0.000009387863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.795488e-7,"about_ca_topic_score_gemma":0.000001679459,"domain_scores_codex":[0.9988279,0.0001558583,0.0003368415,0.0002747623,0.0002402107,0.0001644439],"domain_scores_gemma":[0.9974588,0.001922155,0.0001462711,0.0002354476,0.0001852509,0.00005203857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001844909,0.0005248978,0.001300551,0.00006502272,0.00002499347,1.733111e-7,0.0001540467,0.00003944254,0.004320947,0.9529929,0.0006619478,0.03973059],"study_design_scores_gemma":[0.001136012,0.0002425376,0.02398126,0.00001593767,0.00006706152,8.152476e-7,0.00009273102,0.000231409,0.0006265713,0.9724349,0.001034111,0.00013664],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04599164,0.00002402427,0.9483526,0.00005920341,0.0001545834,0.001301884,0.00001326837,0.00003182859,0.004070915],"genre_scores_gemma":[0.7610411,0.000007060216,0.2385354,0.00005751423,0.00001265067,0.0003294386,8.338178e-7,0.000007435387,0.000008508897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7150494,"threshold_uncertainty_score":0.3779632,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7555750990116348,"gpt":0.5231085521292439,"spread":0.2324665468823909,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03277811,0.0003553296,0.0006139567,0.001643806,0.0004623634,0.0005697061,0.0008999127,0.0003192982,0.0001768735],"category_scores_gemma":[0.1530235,0.0002515817,0.0002565107,0.008229246,0.00009922463,0.0002624897,0.00009414135,0.000347842,0.0001724196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000257732,"about_ca_system_score_gemma":0.00005093406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002381834,"about_ca_topic_score_gemma":5.281879e-7,"domain_scores_codex":[0.9927325,0.0006919041,0.001365929,0.00140571,0.003075307,0.0007286822],"domain_scores_gemma":[0.9665034,0.03059806,0.0007346945,0.001098776,0.0007988521,0.0002662544],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003009045,0.000617484,0.003637668,0.000007357284,0.00003551857,0.000003627542,0.00003693167,0.03958116,0.004506144,0.001868195,0.006841401,0.9398555],"study_design_scores_gemma":[0.002978903,0.0009280038,0.387059,0.00003011458,0.00008853497,0.00002885271,0.0003237144,0.3401472,0.0002471962,0.2585777,0.008839145,0.0007516189],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3487844,0.0001710999,0.6415806,0.0004263498,0.0005641344,0.0007463407,0.000003072329,0.0001663967,0.007557622],"genre_scores_gemma":[0.819648,0.00001316804,0.1790066,0.000747082,0.00009847182,0.0003078772,0.000002825609,0.00002068977,0.0001553588],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9391038,"threshold_uncertainty_score":0.9999936,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Outlier; Statistics; Correlation; Range (aeronautics); Mathematics; Normal distribution; Gaussian; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.2231647714868146,"gpt":0.4176716541584364,"spread":0.1945068826716219,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006975526,0.0001011004,0.0002110993,0.00003284795,0.0000420781,0.000004980192,0.00005156129,0.00009188729,0.0001634342],"category_scores_gemma":[0.0002388282,0.00008111351,0.00002300813,0.0001513366,0.0000933202,0.00002473335,0.000009429863,0.0001491094,0.000007164841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005201895,"about_ca_system_score_gemma":0.000003843437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003623181,"about_ca_topic_score_gemma":0.000003655895,"domain_scores_codex":[0.9988859,0.00008023137,0.0003537753,0.0002469668,0.0002737613,0.0001593765],"domain_scores_gemma":[0.9994806,0.0001874608,0.00006886368,0.0001629635,0.00004183851,0.00005825262],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003233804,0.0007873807,0.0005714067,0.00003453093,0.00001287216,0.000002311756,0.000120256,0.00007041966,0.003627911,0.6927781,0.0002410097,0.3014304],"study_design_scores_gemma":[0.001155191,0.0001534775,0.05636102,0.00003270521,0.00002427386,0.000001787046,0.00003185337,0.000222303,0.0001700439,0.9413502,0.0003691544,0.0001279568],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.152447,0.00006501532,0.8314944,0.0001193751,0.00004325023,0.0004964526,0.00001815236,0.00003519818,0.0152811],"genre_scores_gemma":[0.8923087,0.00007017329,0.1074671,0.00002705598,0.00001530717,0.00007996517,0.000003743474,0.000006050301,0.00002193418],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7398616,"threshold_uncertainty_score":0.3307713,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Variance (accounting); Reliability (semiconductor); Test (biology); Statistics; Econometrics; Psychology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2678450942987462,"gpt":0.4308893442137286,"spread":0.1630442499149824,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002555059,0.0001898166,0.0003293631,0.00001517966,0.0001218633,0.000007119759,0.0002998236,0.00009254701,0.0001302693],"category_scores_gemma":[0.01520595,0.00008850744,0.00008554533,0.0001652211,0.0002824932,0.00001751964,0.00005159695,0.0002628911,0.000009589175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007474322,"about_ca_system_score_gemma":0.00002247909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008611828,"about_ca_topic_score_gemma":0.0000095326,"domain_scores_codex":[0.9977028,0.0003597997,0.0005625548,0.0003756484,0.0007404686,0.0002587752],"domain_scores_gemma":[0.9914194,0.007170764,0.0002987291,0.0008489329,0.0001745534,0.00008764243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004419374,0.00126311,0.001823675,0.0001246575,0.0000598327,0.000001411911,0.000441791,0.002325042,0.158721,0.80756,0.002265084,0.02497242],"study_design_scores_gemma":[0.0008974235,0.0002596538,0.03010196,0.000112758,0.00005180813,0.000001895843,0.00007026379,0.00002706796,0.02163042,0.9450065,0.00164887,0.0001913411],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7027586,0.00005597592,0.2801444,0.0004337771,0.00007159766,0.001061486,0.000008101655,0.00003238103,0.01543365],"genre_scores_gemma":[0.8681635,0.000004950616,0.1313249,0.000370653,0.00001504529,0.0000657424,2.047365e-7,0.00001149028,0.00004344301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1654049,"threshold_uncertainty_score":0.9930894,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3951392929941238,"gpt":0.4304190280454949,"spread":0.03527973505137111,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01601647,0.0002196148,0.0003710813,0.0001784027,0.0003021286,0.0001305997,0.0007244356,0.0001943062,0.00006093144],"category_scores_gemma":[0.1814859,0.0001064817,0.00009207614,0.001451482,0.0002831989,0.00005199243,0.00004305241,0.0003484516,0.00003054664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005631713,"about_ca_system_score_gemma":0.000007665863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000105858,"about_ca_topic_score_gemma":0.00000226326,"domain_scores_codex":[0.9949923,0.0007461641,0.000959552,0.0006808221,0.002317009,0.0003042256],"domain_scores_gemma":[0.900653,0.09741246,0.0006613971,0.0009514213,0.0002408471,0.00008084677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007214034,0.0004993958,0.4788243,0.000007900531,0.00002591412,0.000002268164,0.00007001842,0.001097079,0.03119421,0.04484618,0.001952477,0.4407589],"study_design_scores_gemma":[0.000560661,0.001852484,0.8636762,0.00001951616,0.00001032401,0.000004507788,0.0001194327,0.0000600614,0.01007647,0.1231237,0.0003585672,0.000137987],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9554009,0.00006381226,0.01857754,0.0002173534,0.001103923,0.0005712484,0.000002972047,0.00008951559,0.02397276],"genre_scores_gemma":[0.9913583,0.000003250285,0.008198657,0.0001046908,0.0002346445,0.00007033618,0.000001708871,0.000009388245,0.00001906279],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4406209,"threshold_uncertainty_score":0.8254088,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Equating; Outlier; Statistics; Item response theory; Calibration; Comparability; Mathematics; Econometrics; Computer science; Psychometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.8304468687797645,"gpt":0.5388212625480718,"spread":0.2916256062316926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04040952,0.0001717794,0.0005492193,0.0003424393,0.0001106472,0.00002343053,0.001315474,0.0001329161,0.00007316628],"category_scores_gemma":[0.03888406,0.00009443393,0.0001210291,0.002910648,0.0004278803,0.00004911671,0.00007648367,0.0003168237,0.000007465493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003168411,"about_ca_system_score_gemma":0.00003266718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004256998,"about_ca_topic_score_gemma":0.000004667187,"domain_scores_codex":[0.9919676,0.002857596,0.001580675,0.0005703066,0.002716125,0.0003076698],"domain_scores_gemma":[0.9716399,0.02610949,0.0009193787,0.0009425091,0.0003186446,0.00007006957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002982326,0.0006019457,0.419363,0.00003458612,0.00002823758,0.000008083509,0.003165453,0.001900379,0.2201929,0.006336234,0.002059379,0.3460116],"study_design_scores_gemma":[0.001032091,0.0003859058,0.9069838,0.00005049064,0.0000112765,0.000005960088,0.001138358,0.0012385,0.02045108,0.06812163,0.0003843038,0.0001966053],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8062878,0.0002468303,0.1744903,0.0004985931,0.0002625687,0.0006356837,0.00000221155,0.00002679538,0.01754921],"genre_scores_gemma":[0.8362443,0.000005442124,0.1632294,0.0004221488,0.00002501884,0.00006321304,7.035448e-7,0.000005161414,0.000004537842],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4876208,"threshold_uncertainty_score":0.9881003,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5204254440661797,"gpt":0.4693431790011876,"spread":0.05108226506499214,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05134014,0.000394202,0.0006055025,0.0002234392,0.0001880145,0.00009159016,0.001356576,0.0002438929,0.001702357],"category_scores_gemma":[0.003415193,0.0001996039,0.000243475,0.0005670022,0.0003950023,0.0002262965,0.000107899,0.0002344962,0.0003053813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005671026,"about_ca_system_score_gemma":0.00009329298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001081787,"about_ca_topic_score_gemma":0.000007664737,"domain_scores_codex":[0.9826584,0.002180463,0.001717181,0.001610274,0.01130955,0.0005240708],"domain_scores_gemma":[0.9938155,0.0004484059,0.0006040013,0.002404244,0.002462943,0.0002648791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008011095,0.002245128,0.003600555,0.000005222885,0.00003785496,7.912633e-7,0.0001377712,0.001315764,0.7722567,0.0006300569,0.002136969,0.216832],"study_design_scores_gemma":[0.01000882,0.005190865,0.3183182,0.000424425,0.0003987158,0.000007052219,0.0008105951,0.002037558,0.3831044,0.2652449,0.01266921,0.001785318],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9672068,0.00007349334,0.01767798,0.001277419,0.0008208781,0.001464181,0.00001615485,0.00007133694,0.01139171],"genre_scores_gemma":[0.9975315,0.000009064229,0.001461287,0.0006964535,0.0001240196,0.0001432953,0.000001591808,0.00001743879,0.00001539191],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3891523,"threshold_uncertainty_score":0.9992102,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.534223811307965,"gpt":0.385328940422152,"spread":0.148894870885813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001060076,0.0001374374,0.000177122,0.00004970345,0.001306019,0.0003664051,0.0003504722,0.00004791889,0.000002145619],"category_scores_gemma":[0.0002930706,0.0001128313,0.00003472512,0.00005602745,0.00003046303,0.0001925665,0.0001421016,0.00007154422,0.00001029962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008550854,"about_ca_system_score_gemma":0.0000164059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008349119,"about_ca_topic_score_gemma":0.000002219281,"domain_scores_codex":[0.99875,0.0000487695,0.0002787464,0.0003718559,0.000292753,0.0002578465],"domain_scores_gemma":[0.9990312,0.0001018478,0.0002170621,0.0003352784,0.0002271099,0.00008742941],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002282412,0.0001742294,0.0003611541,0.00005576481,0.00007530279,0.000002352088,0.001489637,0.003588975,0.3189853,0.5180908,0.0004915687,0.156662],"study_design_scores_gemma":[0.001391442,0.0004830671,0.04520983,0.0002473838,0.00002681812,0.0000240407,0.00009057285,0.9371367,0.004553573,0.005508154,0.004722164,0.0006062655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07323544,0.00002677239,0.9243351,0.0003514246,0.0003149278,0.0006929854,0.000001462312,0.00009359196,0.000948355],"genre_scores_gemma":[0.7137338,6.211527e-7,0.2858119,0.0001635493,0.000145537,0.0001183405,9.078199e-7,0.000004666539,0.00002068456],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9335477,"threshold_uncertainty_score":0.9999942,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.72207883373125,"gpt":0.5322352636234017,"spread":0.1898435701078484,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01610793,0.0002600699,0.0004754849,0.0002100711,0.00124109,0.0007584816,0.001541329,0.0001893871,0.0001950488],"category_scores_gemma":[0.1290434,0.0001809172,0.000134881,0.0003623985,0.0001486179,0.0001094695,0.000170104,0.0002543013,0.0001112662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009325043,"about_ca_system_score_gemma":0.00002699206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000131765,"about_ca_topic_score_gemma":0.00000909864,"domain_scores_codex":[0.9950816,0.0002170428,0.0009786108,0.001046965,0.00209821,0.0005775632],"domain_scores_gemma":[0.985225,0.01175572,0.001067722,0.001118193,0.0006314766,0.0002019258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002355108,0.0001829769,0.007813961,0.00001256759,0.00003781842,0.000003657065,0.00007877905,0.0002076964,0.007391111,0.02795454,0.007716538,0.9483649],"study_design_scores_gemma":[0.002579736,0.0006044953,0.5173778,0.00003169721,0.00004611964,0.00001281758,0.0004023937,0.004068144,0.001857552,0.4591814,0.01328402,0.0005537791],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1014713,0.00007272288,0.8705021,0.0005109027,0.001380229,0.0008912444,0.00003228162,0.0001147611,0.02502454],"genre_scores_gemma":[0.727478,0.000004541742,0.2717344,0.0003370214,0.0002237605,0.0001373658,0.000001890002,0.00001432324,0.00006871617],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9478111,"threshold_uncertainty_score":0.954559,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval; Université de Sherbrooke","funders":"","keywords":"Statistics; Cheating; Monte Carlo method; Mathematics; Econometrics; Psychology; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.2430805157256228,"gpt":0.3434006195884511,"spread":0.1003201038628284,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006012805,0.0001692606,0.0002616164,0.00008184493,0.00005193436,0.00001704814,0.001048519,0.0000792639,0.0001674999],"category_scores_gemma":[0.00009860872,0.0001333711,0.00007115871,0.000333712,0.0000983135,0.00009688462,0.0001048046,0.0001554894,0.000072316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005090531,"about_ca_system_score_gemma":0.00001378643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008275875,"about_ca_topic_score_gemma":0.000002508053,"domain_scores_codex":[0.9981903,0.00004620167,0.0003329469,0.0004793988,0.0006786055,0.0002724873],"domain_scores_gemma":[0.9985755,0.00005789315,0.0002450233,0.0008258362,0.0001964074,0.00009933025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004355946,0.0009099183,0.000297467,0.00001418767,0.00007003129,0.0000110312,0.0007323579,0.000003598881,0.031224,0.609364,0.00369801,0.3536319],"study_design_scores_gemma":[0.002330751,0.001855776,0.1090685,0.00008059844,0.0001459683,0.00002292891,0.0003164879,0.0009286323,0.2554444,0.618771,0.009245131,0.001789782],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001705557,0.00008876441,0.9563183,0.00005583121,0.00006713179,0.0002469835,0.000002457822,0.0002341044,0.04128091],"genre_scores_gemma":[0.6095033,0.0000163087,0.3902177,0.0001961308,0.00001052874,0.00004218567,5.223339e-7,0.00000494812,0.000008437964],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6077977,"threshold_uncertainty_score":0.5438714,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3757797696663633,"gpt":0.4016023114350326,"spread":0.02582254176866927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01794613,0.0002687516,0.0005432332,0.0002043824,0.0002199564,0.000104368,0.001275484,0.0001420756,0.0001514731],"category_scores_gemma":[0.003739271,0.0001277387,0.0001230416,0.001424078,0.00027835,0.00009046604,0.0001194214,0.0003216427,0.00009133641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005461424,"about_ca_system_score_gemma":0.00002608682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001027245,"about_ca_topic_score_gemma":0.000003315685,"domain_scores_codex":[0.9939927,0.0006013524,0.0008499559,0.0008182541,0.003282998,0.0004546724],"domain_scores_gemma":[0.9925699,0.004968557,0.0006205798,0.001219653,0.000465532,0.0001557428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009320788,0.0002149275,0.0002122332,0.000003946574,0.00002883483,9.582546e-7,0.0001247796,0.00333622,0.0007070316,0.006621474,0.002270075,0.9863863],"study_design_scores_gemma":[0.002786936,0.001354479,0.08148589,0.0000530109,0.00007556499,0.00002677387,0.0009207497,0.04608518,0.001187567,0.8581313,0.007255835,0.0006367466],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04010677,0.0001188403,0.8927851,0.0007797897,0.0003044304,0.0005083523,0.000002921853,0.00008104049,0.06531275],"genre_scores_gemma":[0.8049097,0.000005067759,0.1942133,0.0006948803,0.00007831468,0.00007166786,9.894686e-7,0.00001202032,0.00001403763],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9857495,"threshold_uncertainty_score":0.6219806,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6421002834531417,"gpt":0.5022808864825751,"spread":0.1398193969705667,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001621898,0.0001801561,0.0002762455,0.00002693722,0.00004959356,0.00001796259,0.0001921277,0.0001042089,0.0001342474],"category_scores_gemma":[0.0009358933,0.0001266281,0.00005147164,0.0001125896,0.00007578095,0.00002395901,0.0000450988,0.0001967905,0.0001807901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000933732,"about_ca_system_score_gemma":0.00001299361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.596009e-7,"about_ca_topic_score_gemma":8.709567e-7,"domain_scores_codex":[0.9980718,0.0000904519,0.0003169145,0.0004053391,0.0007757043,0.0003397795],"domain_scores_gemma":[0.9989004,0.0001590608,0.00007441376,0.0003856872,0.0001587121,0.000321724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001214288,0.0004640264,0.00001222712,0.000008887063,0.00002081828,0.000007721132,0.0001213287,0.000007944132,0.00188521,0.9077596,0.01434983,0.07524097],"study_design_scores_gemma":[0.0008973361,0.0001547475,0.0001736951,0.000007410981,0.00001965651,0.000004255395,0.00008445683,0.00002020223,0.0004212451,0.9826304,0.01539108,0.0001955245],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003410337,0.00004526407,0.811911,0.0002272754,0.0002162457,0.0003437318,0.000003048593,0.0001590471,0.183684],"genre_scores_gemma":[0.5578363,0.000002093737,0.4413136,0.0005385564,0.00008379426,0.000103816,7.390354e-7,0.0000158508,0.0001052998],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.554426,"threshold_uncertainty_score":0.5163746,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3344098990462734,"gpt":0.4815746876227396,"spread":0.1471647885764661,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001081186,0.0001997199,0.0002765025,0.00002169691,0.0001412111,0.00004675661,0.0001917056,0.0001213273,0.008482951],"category_scores_gemma":[0.0007011225,0.0001501527,0.00007074868,0.0001197643,0.0001052371,0.00004342603,0.00001815717,0.0001847432,0.000213954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006229845,"about_ca_system_score_gemma":0.000006159671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003070828,"about_ca_topic_score_gemma":0.000001023485,"domain_scores_codex":[0.9980195,0.00009288478,0.0004135451,0.0004875243,0.0006272478,0.0003593205],"domain_scores_gemma":[0.9987409,0.0005536171,0.00007224308,0.0003995186,0.00009097302,0.0001427691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000235483,0.0005608617,0.00004278413,0.00002136324,0.00002571532,0.000002798275,0.0000675584,0.00008073686,0.004731142,0.3542359,0.0009764181,0.6390192],"study_design_scores_gemma":[0.0007755735,0.0001250592,0.002173889,0.00001163256,0.00002132831,0.000002421957,0.00001028236,0.00003688713,0.002380631,0.9831209,0.01110097,0.0002404368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0601935,0.00003012081,0.8382469,0.0001431351,0.0001090774,0.0005111779,0.00002277563,0.0002172997,0.100526],"genre_scores_gemma":[0.5727174,0.00001503783,0.4265178,0.0003399234,0.00008100567,0.0001308844,0.000004527533,0.00001705834,0.0001762813],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6387787,"threshold_uncertainty_score":0.9924234,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8911900554521754,"gpt":0.6108802067461848,"spread":0.2803098487059906,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03717666,0.0002955317,0.0005752436,0.0002398311,0.0003910942,0.0002340676,0.0008231875,0.0001666622,0.0005646077],"category_scores_gemma":[0.2448359,0.0001949161,0.0002155308,0.0009920165,0.0001243647,0.00005886728,0.00008897724,0.0003003481,0.0001724475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001079082,"about_ca_system_score_gemma":0.00002792909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002596523,"about_ca_topic_score_gemma":0.000001511585,"domain_scores_codex":[0.9931415,0.0008883008,0.0008517151,0.001313445,0.003163989,0.0006410378],"domain_scores_gemma":[0.9127549,0.08472498,0.0005727086,0.0007249512,0.0009670576,0.0002554122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001143748,0.0003563272,0.005810864,0.000008610114,0.00003855743,9.062208e-7,0.0001039776,0.0001233747,0.002969829,0.005144878,0.00442682,0.9809015],"study_design_scores_gemma":[0.005314776,0.003164799,0.8108994,0.0001013313,0.0001275442,0.000009022578,0.001992346,0.005045033,0.0006139904,0.1637731,0.008222825,0.0007357649],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2452468,0.000154349,0.6585056,0.001032794,0.001180555,0.001764726,0.00001138771,0.0001602027,0.09194363],"genre_scores_gemma":[0.9026748,0.000004617017,0.09478346,0.001394163,0.0003110232,0.0007439195,0.000003337504,0.00001695687,0.000067721],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9801657,"threshold_uncertainty_score":0.9914292,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6035678497989727,"gpt":0.4659181755804515,"spread":0.1376496742185212,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02163343,0.0002356025,0.000638536,0.0003335965,0.0002330953,0.00002792511,0.0008590929,0.0001397395,0.0001306475],"category_scores_gemma":[0.1104486,0.0001464415,0.0001675011,0.001757888,0.0002529064,0.00003677107,0.0001176857,0.0003130742,0.000147084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007479545,"about_ca_system_score_gemma":0.00002728946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005476912,"about_ca_topic_score_gemma":5.603997e-7,"domain_scores_codex":[0.9926154,0.001788206,0.001134922,0.000937659,0.003129735,0.0003940833],"domain_scores_gemma":[0.964433,0.03354698,0.0005319899,0.00099279,0.0003386435,0.000156608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.009678965,0.004570398,0.08755188,0.00008117063,0.0001093883,0.0001235655,0.001288178,0.0004319515,0.5420306,0.004109087,0.01041382,0.339611],"study_design_scores_gemma":[0.001170957,0.0008601189,0.9592599,0.00003389254,0.000008424147,0.00001031067,0.00008987034,0.00003992312,0.02137508,0.01654827,0.00041315,0.0001901032],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9692463,0.0001198565,0.01543393,0.0002144798,0.0004594969,0.000599736,0.000001083176,0.00008568002,0.01383948],"genre_scores_gemma":[0.9881403,0.000007457186,0.01122076,0.0004862201,0.00005565381,0.00005154543,2.138948e-7,0.000009109419,0.00002867617],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.871708,"threshold_uncertainty_score":0.8970445,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1400589295419584,"gpt":0.3338867503694962,"spread":0.1938278208275377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001299422,0.0003260275,0.000518182,0.00003456825,0.0007813727,0.0001884369,0.0004725328,0.0001595898,0.004891822],"category_scores_gemma":[0.0003574218,0.0001027896,0.0003508449,0.001561593,0.0001395336,0.00004213131,0.00005536933,0.0002968193,0.000217737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000913299,"about_ca_system_score_gemma":0.000005326537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002839915,"about_ca_topic_score_gemma":0.00007217102,"domain_scores_codex":[0.9963908,0.0004714589,0.0006319394,0.0007608586,0.001144366,0.0006006095],"domain_scores_gemma":[0.9979109,0.001158056,0.0002071262,0.0002455087,0.0001751466,0.0003033269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003996818,0.0005974985,0.003885728,0.000004264994,0.0009303828,0.0000272695,0.00006954311,0.00004196293,0.4009738,0.03461944,0.0004621763,0.5579882],"study_design_scores_gemma":[0.0006807834,0.001071226,0.8667179,0.0000281289,0.000932737,0.00001740102,0.0007293642,0.0003756664,0.002313038,0.02786624,0.09805243,0.001215101],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.97834,0.0005931128,0.002059931,0.00166455,0.000149884,0.0004856336,0.00003096102,0.0001232202,0.0165527],"genre_scores_gemma":[0.9973642,0.0001685438,0.0009705617,0.001036949,0.0001970212,0.00005300668,0.00002376286,0.000002151225,0.0001838147],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8628321,"threshold_uncertainty_score":0.9960178,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04766665868336487,"gpt":0.246875605860797,"spread":0.1992089471774322,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007516431,0.0002687367,0.0003164611,0.0000362785,0.0002754994,0.00004186548,0.0002005675,0.0001152835,0.00004867341],"category_scores_gemma":[0.000031347,0.0001421917,0.00004457185,0.000191645,0.0001054884,0.00008457083,0.00005611066,0.0003447871,0.000007667098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008482989,"about_ca_system_score_gemma":0.00001011672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005180936,"about_ca_topic_score_gemma":0.000007254886,"domain_scores_codex":[0.9985213,0.00002696087,0.0003338748,0.0003421648,0.0004064263,0.0003693152],"domain_scores_gemma":[0.9993691,0.0001223133,0.00008875538,0.0002836685,0.00007527856,0.00006089099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001281482,0.001810364,0.009953039,0.004181127,0.0005945106,0.0000932158,0.006645859,0.8700805,0.02265288,0.0002431352,0.05764495,0.02481895],"study_design_scores_gemma":[0.02977171,0.0006257815,0.06209342,0.004920056,0.0005830848,0.0005224966,0.0005909262,0.8518792,0.02865138,0.0002044185,0.01686108,0.003296477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.608371,0.01020459,0.3722498,0.000501173,0.0006300518,0.003896528,0.00002066558,0.001918468,0.002207738],"genre_scores_gemma":[0.9838617,0.0007737836,0.01442614,0.0007260716,0.0000803884,0.00007907359,0.00001229939,0.00003351654,0.000007035118],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3754907,"threshold_uncertainty_score":0.5798407,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lakehead University","funders":"Lakehead University","keywords":"Computer program; Computer science; Psychology; Statistics; Mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.0944139960001945,"gpt":0.3083394133823271,"spread":0.2139254173821326,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009285427,0.0002368148,0.0002525394,0.00005837261,0.0001407407,0.0002156722,0.00115567,0.0001200523,0.00006027431],"category_scores_gemma":[0.000008372197,0.0001830512,0.00009502815,0.0004983449,0.00004533123,0.00006719612,0.0001892533,0.0001454239,0.0005775451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006706888,"about_ca_system_score_gemma":0.00001087726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003755163,"about_ca_topic_score_gemma":0.000001218311,"domain_scores_codex":[0.9974921,0.00009191997,0.0003428501,0.0007262626,0.0007994676,0.0005473814],"domain_scores_gemma":[0.9987967,0.00002867176,0.0001051571,0.0007509674,0.0001223063,0.0001962096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002565897,0.001176653,0.0003608542,0.00001578474,0.00003887612,0.00005105741,0.0001605215,0.0001585237,0.000408659,0.03397063,0.02758389,0.9360489],"study_design_scores_gemma":[0.00235941,0.001765895,0.04757075,0.00007086777,0.00001480681,0.000183818,0.0000144025,0.009825355,0.000112483,0.007577787,0.9294782,0.001026267],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01095517,0.0001485054,0.9024404,0.0007708112,0.001006531,0.0008187307,8.243197e-7,0.001259031,0.08260005],"genre_scores_gemma":[0.9599756,0.00001292262,0.03821485,0.001136753,0.0003788774,0.00021052,0.000004589599,0.00000899181,0.0000568932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9490204,"threshold_uncertainty_score":0.7464613,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5775002634706006,"gpt":0.460701353218835,"spread":0.1167989102517655,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01248888,0.0002289501,0.0006595029,0.000147765,0.0001329312,0.00003660661,0.001252541,0.00008554746,0.00007825541],"category_scores_gemma":[0.0707149,0.00009583058,0.0001395595,0.001326245,0.0001541132,0.00003080909,0.00006883158,0.0002885077,0.000007693042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003942763,"about_ca_system_score_gemma":0.00001352414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000023475,"about_ca_topic_score_gemma":0.00000487848,"domain_scores_codex":[0.9942262,0.00115778,0.001064465,0.0004977254,0.002809722,0.0002441592],"domain_scores_gemma":[0.9717978,0.02522475,0.001392671,0.001168532,0.0003621054,0.0000541638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001763025,0.002587021,0.1069547,0.00004301629,0.000169602,0.00000349053,0.001810476,0.00209613,0.01411479,0.003131456,0.002435213,0.8648911],"study_design_scores_gemma":[0.000994636,0.003882777,0.9877362,0.00004925694,0.00005737632,0.000001283318,0.0005356582,0.001127737,0.001085612,0.004407116,0.00001530027,0.0001070166],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9882755,0.00005498243,0.007697321,0.0002834975,0.0002907249,0.00159998,0.00002213559,0.00001690672,0.001758983],"genre_scores_gemma":[0.9981664,0.000002617337,0.00163128,0.0001070717,0.00002555605,0.00005502861,2.886549e-7,0.000006113204,0.000005601178],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8807815,"threshold_uncertainty_score":0.9371129,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6812333426754545,"gpt":0.4329920465484254,"spread":0.2482412961270291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01328367,0.0002454872,0.0003665104,0.0003628064,0.0006780036,0.0001349583,0.0008201291,0.0000561263,0.0005516226],"category_scores_gemma":[0.01649879,0.0001398079,0.00004664822,0.006474267,0.0001060941,0.00005057476,0.0001896474,0.0007225862,0.00003679296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003351191,"about_ca_system_score_gemma":0.00004279819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001962153,"about_ca_topic_score_gemma":0.00002044687,"domain_scores_codex":[0.9939356,0.001206018,0.0006642339,0.0009872083,0.002734805,0.0004721298],"domain_scores_gemma":[0.9827898,0.01583891,0.0004424195,0.000490337,0.0003467075,0.00009179107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005642999,0.002815352,0.08965644,0.00001013796,0.0001635294,0.000180964,0.002791474,0.04678565,0.07099558,0.03223433,0.014104,0.7346196],"study_design_scores_gemma":[0.005518064,0.008989912,0.8880799,0.0001008901,0.00003009521,0.00009479337,0.02435626,0.007005433,0.003474442,0.0420245,0.01883215,0.001493537],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8535135,0.0000939414,0.03386654,0.0009608243,0.0004750665,0.001736657,0.00001818305,0.0001797893,0.1091555],"genre_scores_gemma":[0.9688712,0.000001061622,0.02941031,0.0008741032,0.00005560796,0.0007100754,6.415321e-7,0.00001401481,0.00006302418],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7984235,"threshold_uncertainty_score":0.9917856,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8339036917039917,"gpt":0.5454023379535109,"spread":0.2885013537504808,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01469004,0.0002191273,0.0003991887,0.00009310507,0.0005340399,0.0003116945,0.0007710499,0.00006276514,0.00005372968],"category_scores_gemma":[0.006932929,0.0001175536,0.00007242752,0.001074892,0.0001531004,0.00005797681,0.0001997795,0.000279261,0.00004590339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005512619,"about_ca_system_score_gemma":0.00002937433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005048678,"about_ca_topic_score_gemma":0.000009585676,"domain_scores_codex":[0.9945073,0.001441967,0.0008622382,0.0009071004,0.001893449,0.0003879262],"domain_scores_gemma":[0.9916534,0.007101077,0.0003342249,0.0004978162,0.0001839477,0.0002294681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.02810395,0.00186955,0.03044859,0.000006062913,0.0004191737,0.00002362542,0.02439455,0.00166861,0.07583284,0.009996315,0.07352263,0.7537141],"study_design_scores_gemma":[0.008778771,0.004922966,0.8567132,0.000005246391,0.00008270348,0.000008095958,0.07796169,0.005403981,0.001365102,0.03361682,0.01036847,0.0007729962],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9797286,0.000206972,0.01038555,0.004367931,0.0001679323,0.001502258,0.000003675012,0.00008625208,0.003550816],"genre_scores_gemma":[0.9958879,0.0000108743,0.002776695,0.00103564,0.00006185197,0.0002076456,3.456161e-7,0.0000064765,0.00001251168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8262646,"threshold_uncertainty_score":0.8299864,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6476178436147106,"gpt":0.4734027822600229,"spread":0.1742150613546877,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01896636,0.0001884928,0.0003201721,0.0002723295,0.0002334786,0.0001032213,0.001175888,0.0001126105,0.0005033629],"category_scores_gemma":[0.1078829,0.00009739503,0.0001048718,0.002548914,0.0001319398,0.00005708283,0.0001187356,0.0004382833,0.000245997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003374953,"about_ca_system_score_gemma":0.00002725415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001122123,"about_ca_topic_score_gemma":0.00001588149,"domain_scores_codex":[0.9952479,0.0002523581,0.0009037965,0.0007240631,0.002515404,0.0003565045],"domain_scores_gemma":[0.9894258,0.008378698,0.0004452534,0.001080913,0.0005227833,0.0001465823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00005209002,0.0003987245,0.004799329,0.000002267622,0.000007178524,5.588734e-7,0.0002415128,0.0005349847,0.0856842,0.002205799,0.01102188,0.8950515],"study_design_scores_gemma":[0.0005386989,0.0006052664,0.9477506,0.00001854866,0.0000177211,0.00001734339,0.0004404788,0.002573303,0.008017817,0.03329564,0.006442796,0.0002818063],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5448684,0.00004928435,0.3781466,0.002393322,0.005707235,0.001481232,0.000007462992,0.0001435164,0.06720301],"genre_scores_gemma":[0.9642805,0.000001216093,0.03485318,0.0004775207,0.0001288064,0.0001309808,4.166328e-7,0.000007989258,0.0001193672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9429513,"threshold_uncertainty_score":0.8996318,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4601168525429778,"gpt":0.4576214468831099,"spread":0.002495405659867944,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008970705,0.0003241305,0.0006146411,0.000499821,0.000181227,0.0001589945,0.001187154,0.0001845597,0.000145951],"category_scores_gemma":[0.01201443,0.0002167376,0.000135042,0.002376785,0.0001185483,0.0001494927,0.00008204571,0.0002538236,0.0001252444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001129493,"about_ca_system_score_gemma":0.00003368443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009326013,"about_ca_topic_score_gemma":0.000004888982,"domain_scores_codex":[0.9938284,0.0004766414,0.001258114,0.001184705,0.002645048,0.0006070479],"domain_scores_gemma":[0.9959558,0.001591022,0.0004522904,0.00104277,0.0006090562,0.0003490623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003952125,0.0004750317,0.0007481046,0.000003127332,0.000008281066,0.000004027128,0.0003432378,0.0008976628,0.07339801,0.0004868015,0.000262995,0.9229775],"study_design_scores_gemma":[0.001803098,0.005761698,0.7897471,0.00005121161,0.00002110837,0.00002043149,0.0008258669,0.003081809,0.02321674,0.1745421,0.0003452505,0.0005835426],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3451758,0.00007749622,0.6483945,0.0004313317,0.0002655803,0.0008205438,0.00001165357,0.00008748691,0.004735601],"genre_scores_gemma":[0.8092932,0.000002014155,0.1896766,0.0009018435,0.00004679634,0.00006251227,0.000002062257,0.000008688827,0.000006283319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.922394,"threshold_uncertainty_score":0.9963078,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1582989830909169,"gpt":0.3541875478248856,"spread":0.1958885647339687,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002881459,0.0001638102,0.0002357749,0.00004336933,0.00007622099,0.00007575884,0.0004751665,0.00006873375,0.00001972426],"category_scores_gemma":[0.00008409617,0.0001368953,0.0000272186,0.0002139671,0.00005925379,0.0001127449,0.0001493301,0.0001515712,0.00001134135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002097436,"about_ca_system_score_gemma":0.000008131288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001331153,"about_ca_topic_score_gemma":0.000001131373,"domain_scores_codex":[0.9982367,0.00006720303,0.0003308237,0.0006224205,0.0005195476,0.0002232809],"domain_scores_gemma":[0.9991368,0.000048591,0.00008489445,0.0003357397,0.0001086498,0.0002853156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002198808,0.0004319826,0.0003954573,0.00004378012,0.00003259271,0.00000967031,0.0009672403,0.0009372915,0.577937,0.1900752,0.0004223923,0.2285275],"study_design_scores_gemma":[0.005616738,0.01993814,0.1908792,0.0002675561,0.0001606465,0.00002776141,0.001264101,0.05166396,0.1943796,0.5308915,0.001302348,0.003608428],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2016807,0.00004186418,0.7972171,0.0002531735,0.00004560946,0.000221918,0.000002096934,0.0002585878,0.0002789389],"genre_scores_gemma":[0.8783077,0.000004781313,0.1208563,0.0007132248,0.000043638,0.00006465443,0.000001058157,0.000008238051,3.525184e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.676627,"threshold_uncertainty_score":0.5582429,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Cross-cultural; Psychological testing; Applied psychology; Social psychology; Clinical psychology; Sociology; Anthropology","retraction":null,"screen_n_in":null,"score":{"opus":0.1884424090147324,"gpt":0.4865119053793811,"spread":0.2980694963646486,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001690468,0.0005736463,0.0006213806,0.00008377024,0.0004522569,0.0001582265,0.0005340241,0.0003722704,0.008822495],"category_scores_gemma":[0.0001420401,0.0004149309,0.0002400858,0.000317159,0.0004539169,0.0001436939,0.00007290327,0.0005442892,0.0003162673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001897006,"about_ca_system_score_gemma":0.00003050178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001351711,"about_ca_topic_score_gemma":0.000001829029,"domain_scores_codex":[0.9951558,0.0002210386,0.001111467,0.001651011,0.0009476132,0.0009130668],"domain_scores_gemma":[0.9976309,0.0004966629,0.000408373,0.000642951,0.0005194324,0.0003016931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002325257,0.004889497,0.005492632,0.0001143008,0.00009299812,0.000004124882,0.00003981663,0.000003518797,0.00250845,0.09314942,0.8839024,0.009570332],"study_design_scores_gemma":[0.001911407,0.0006155645,0.6311308,0.0001280009,0.00006460698,0.00005980512,0.00004465758,0.000001781872,0.00001281835,0.01708158,0.3484152,0.0005337634],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1399849,0.1687541,0.003965576,0.04701756,0.004969261,0.007958567,0.0001599865,0.0006085272,0.6265815],"genre_scores_gemma":[0.916043,0.001184886,0.01056409,0.05770696,0.001761223,0.006359105,0.0002957085,0.00006124119,0.006023831],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7760581,"threshold_uncertainty_score":0.9998302,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1397537546690987,"gpt":0.3452510035012429,"spread":0.2054972488321442,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001703236,0.000298352,0.0003980836,0.0001073651,0.0003276842,0.0003042208,0.0009403668,0.0001527949,0.00001042496],"category_scores_gemma":[0.00008879098,0.0002344054,0.0002032136,0.0007968162,0.0001182662,0.0001044881,0.0002649583,0.0002900872,0.00005643851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001539237,"about_ca_system_score_gemma":0.00003325494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002384847,"about_ca_topic_score_gemma":0.000005192936,"domain_scores_codex":[0.9963335,0.0001246372,0.0005695157,0.001128143,0.001094561,0.0007496279],"domain_scores_gemma":[0.997682,0.0007764028,0.0001575744,0.0006643397,0.0005633365,0.000156373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004232252,0.001308707,0.0008178631,0.00002692044,0.00005160846,0.000005657314,0.0000414279,0.01388037,0.0007395647,0.01317095,0.001389839,0.9685248],"study_design_scores_gemma":[0.001836877,0.002152464,0.02072139,0.00006210375,0.00002829274,0.00000707738,0.00001018296,0.9399897,0.0003830154,0.02971858,0.004445454,0.0006448523],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0136104,0.00004292583,0.9813066,0.0002948267,0.0001611735,0.001588768,0.000001795485,0.0007242502,0.002269299],"genre_scores_gemma":[0.5459263,3.883485e-7,0.4531072,0.0002808103,0.000336093,0.0003301705,0.000003649007,0.000009504896,0.000005809988],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.96788,"threshold_uncertainty_score":0.9558772,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7210023253769497,"gpt":0.531043618285663,"spread":0.1899587070912867,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03331906,0.0003457165,0.0006634211,0.0006293374,0.000612844,0.0003055469,0.001401497,0.0002542401,0.0002864282],"category_scores_gemma":[0.164273,0.0002420383,0.000264477,0.004983244,0.00007605721,0.00008341152,0.0003016013,0.0003694257,0.0003126585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008949154,"about_ca_system_score_gemma":0.00004891637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002896103,"about_ca_topic_score_gemma":0.0000133815,"domain_scores_codex":[0.992996,0.000430983,0.001227693,0.001547457,0.002879223,0.0009186168],"domain_scores_gemma":[0.9471056,0.05022569,0.0006227305,0.001074937,0.0005475571,0.0004234133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001923013,0.0000743027,0.001822662,0.00000748797,0.00002354739,0.000005889927,0.0001326055,0.0002920153,0.09936117,0.001519588,0.01807573,0.8784927],"study_design_scores_gemma":[0.006413399,0.002106312,0.2654065,0.000169571,0.0001016738,0.00006194335,0.003065366,0.01402223,0.02420528,0.5928633,0.08991892,0.001665497],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01494691,0.0001297608,0.9746787,0.0009962765,0.000871349,0.00121214,0.000009984331,0.0005918519,0.006563029],"genre_scores_gemma":[0.6095884,0.000009999426,0.3889287,0.0007185371,0.0003053276,0.0002098776,0.00000143718,0.00002423615,0.0002134434],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8768272,"threshold_uncertainty_score":0.9954014,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9218223146811826,"gpt":0.5923631288612036,"spread":0.329459185819979,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1367548,0.0003539798,0.0006984674,0.0003882715,0.0005998886,0.0002572282,0.002182934,0.0002477593,0.0009966706],"category_scores_gemma":[0.1155536,0.0002351757,0.0002021472,0.001853547,0.0002032837,0.00006869371,0.0005525107,0.0005993436,0.0007675589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002469597,"about_ca_system_score_gemma":0.00008169239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.316912e-7,"about_ca_topic_score_gemma":2.30539e-7,"domain_scores_codex":[0.9850789,0.005110349,0.001435629,0.002091699,0.005260665,0.001022704],"domain_scores_gemma":[0.951246,0.04618058,0.000340191,0.001161669,0.0004800087,0.0005915749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.008510056,0.0005391631,0.0003380428,0.00001530104,0.0001017802,0.00001459455,0.001299672,0.0002853353,0.07766089,0.01485276,0.01506183,0.8813206],"study_design_scores_gemma":[0.002729097,0.001403507,0.05448961,0.00002219636,0.00002239614,0.000007519898,0.002504734,0.0004148304,0.01020749,0.1310377,0.796499,0.0006618664],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05831437,0.000459964,0.9232092,0.006693102,0.0002756776,0.002264758,0.000008164497,0.0001369433,0.008637769],"genre_scores_gemma":[0.5871417,0.000010402,0.4095684,0.002177484,0.0001416689,0.0007867218,0.000001717842,0.00002569763,0.0001462123],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8806587,"threshold_uncertainty_score":0.9999166,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4958442413042139,"gpt":0.4335076058483659,"spread":0.062336635455848,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007739805,0.0001930299,0.000339637,0.0002828817,0.0003606166,0.00002986372,0.001065794,0.0002572319,0.0002169012],"category_scores_gemma":[0.001560919,0.0001718734,0.00008088383,0.001412619,0.0001695455,0.00008791752,0.0002943084,0.0002316271,0.0004136619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000174792,"about_ca_system_score_gemma":0.0001559639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001189897,"about_ca_topic_score_gemma":0.00002251083,"domain_scores_codex":[0.9962054,0.000457252,0.0004621625,0.0009226702,0.001314151,0.0006383895],"domain_scores_gemma":[0.9981563,0.0003971945,0.0001258347,0.0008207035,0.0001340398,0.0003659404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00797434,0.001003231,0.000254841,0.00001497568,0.0001105695,0.000005676744,0.01435929,0.0009672857,0.4325565,0.1749961,0.3459443,0.02181294],"study_design_scores_gemma":[0.01513217,0.002302573,0.1328619,0.0004516871,0.0003542434,0.00001253383,0.0499942,0.01272244,0.007627157,0.1252987,0.6484345,0.004807887],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6186227,0.00007298621,0.05943077,0.006376629,0.001065836,0.002000043,0.00005038699,0.0006251938,0.3117555],"genre_scores_gemma":[0.9680055,0.00001786561,0.02831464,0.001239932,0.0002024117,0.00007909341,0.00001592711,0.00002203161,0.002102618],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4249294,"threshold_uncertainty_score":0.7008794,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.700374042316265,"gpt":0.4526023993021298,"spread":0.2477716430141352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01264706,0.0002858181,0.0005885048,0.0001619439,0.0002496805,0.0002413632,0.0005669784,0.0001830858,0.0000598771],"category_scores_gemma":[0.01922451,0.0001957064,0.0000959789,0.0007246888,0.0002206243,0.0000889208,0.000180477,0.0002467732,0.00002855691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003191177,"about_ca_system_score_gemma":0.00002931294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002784765,"about_ca_topic_score_gemma":0.000001660828,"domain_scores_codex":[0.9953348,0.0005545309,0.0008465133,0.001274726,0.00148859,0.0005008237],"domain_scores_gemma":[0.9897944,0.008641582,0.0002987754,0.0004856953,0.0002600268,0.000519491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01745035,0.0005470262,0.005096177,0.00004965548,0.0001392098,0.00004904042,0.002052942,0.0005351754,0.1383571,0.01157582,0.02497567,0.7991718],"study_design_scores_gemma":[0.01893383,0.01015349,0.3485048,0.00007917081,0.0002198515,0.0001696745,0.003812532,0.01973137,0.004289268,0.4486026,0.1423895,0.003113886],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7341497,0.00169162,0.2461875,0.007549074,0.000433062,0.001727008,0.00003426442,0.0002433342,0.007984468],"genre_scores_gemma":[0.9738929,0.00003538994,0.0213359,0.004398307,0.0001360957,0.0001680718,9.238002e-7,0.00001453249,0.00001788522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7960579,"threshold_uncertainty_score":0.989037,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7494451842918853,"gpt":0.4901284049147518,"spread":0.2593167793771335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01210779,0.0002534355,0.000780143,0.0002300769,0.0004282589,0.0001298151,0.0009510498,0.00009398497,0.0001344537],"category_scores_gemma":[0.002734555,0.0001911907,0.000162053,0.0006935742,0.0001100831,0.00005216681,0.0005461869,0.0002716189,0.000009343168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001381618,"about_ca_system_score_gemma":0.00001821389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001102629,"about_ca_topic_score_gemma":0.000007912944,"domain_scores_codex":[0.9926737,0.0004134008,0.001562578,0.001372703,0.00355502,0.000422586],"domain_scores_gemma":[0.9972423,0.0007453648,0.0004855465,0.001044187,0.0002493871,0.0002331832],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003321746,0.003234946,0.0456148,0.00005482446,0.00006921624,0.000004112278,0.00647421,0.03845524,0.123373,0.01170195,0.005301985,0.762394],"study_design_scores_gemma":[0.009644388,0.00388258,0.1886887,0.0000912305,0.0001444445,0.00002820234,0.00765675,0.2416549,0.00550148,0.4883482,0.05216604,0.002193017],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8124874,0.0001932912,0.1834043,0.0004866672,0.0002820351,0.002199067,0.00003920848,0.00005090927,0.0008571647],"genre_scores_gemma":[0.9604758,3.609496e-7,0.03814869,0.0003553931,0.00004084373,0.0009342032,0.000004925385,0.0000190524,0.00002070085],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.760201,"threshold_uncertainty_score":0.7796531,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.4091965530648787,"gpt":0.3927407493978079,"spread":0.01645580366707078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00100571,0.000404959,0.0005685597,0.00004615551,0.0001977934,0.00002158461,0.0005214797,0.000240969,0.07762001],"category_scores_gemma":[0.00003448056,0.0002724844,0.0002197805,0.0004611878,0.0002016275,0.0000357008,0.00007439405,0.0004664235,0.009142432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007169181,"about_ca_system_score_gemma":0.000003835695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000838519,"about_ca_topic_score_gemma":0.000001405187,"domain_scores_codex":[0.9966307,0.0001648501,0.0006387327,0.000985537,0.0007941318,0.000786087],"domain_scores_gemma":[0.998621,0.00004632928,0.0001572529,0.0007863707,0.0001198852,0.0002691009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001873377,0.001229808,0.0004754967,0.00002213985,0.00006289434,0.00007387576,0.00004427302,8.162848e-8,0.0003881529,0.003454414,0.8789092,0.1151524],"study_design_scores_gemma":[0.0008464293,0.0003410762,0.07591856,0.0001156527,0.00007178145,0.0000637054,0.00003294905,2.748479e-8,0.00001265374,0.0007564435,0.921463,0.0003777352],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"commentary","genre_scores_codex":[0.002251551,0.4009157,0.0004546296,0.008848426,0.001089704,0.001149188,0.000003977401,0.0004220606,0.5848647],"genre_scores_gemma":[0.4449048,0.06265172,0.0003458057,0.4738506,0.0007717888,0.002971092,0.00001838402,0.00007325278,0.0144125],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.5704523,"threshold_uncertainty_score":0.9999728,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Index (typography); Statistics; Econometrics; Mathematics; Psychology; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.6224068475520583,"gpt":0.5555954167953175,"spread":0.06681143075674079,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0139394,0.0001400491,0.0002092759,0.0003045292,0.0002103252,0.0002403596,0.0008223165,0.0001230182,0.0004697726],"category_scores_gemma":[0.0006021005,0.00007441773,0.00005838443,0.001805913,0.00005652565,0.0003046732,0.0001095889,0.000319029,0.0005792576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001604774,"about_ca_system_score_gemma":0.00005416128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008292787,"about_ca_topic_score_gemma":0.00001869483,"domain_scores_codex":[0.9956038,0.0002156975,0.0008099866,0.000328861,0.002757973,0.0002836688],"domain_scores_gemma":[0.9986581,0.0002947972,0.0001722486,0.0005745069,0.000254824,0.00004553828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004082709,0.0007193444,0.2332389,0.00001348435,0.00001911268,0.000001733686,0.00493418,0.0003517708,0.0001483829,0.02012139,0.07163732,0.6684061],"study_design_scores_gemma":[0.0008862074,0.00005815609,0.8041853,0.00002014563,0.000004982458,4.887057e-7,0.001114329,0.0003999966,0.00003553803,0.01683434,0.1763555,0.0001049921],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4910924,0.0001355187,0.01286636,0.03742069,0.001002964,0.002525274,0.000002062985,0.00009019939,0.4548645],"genre_scores_gemma":[0.9773301,0.0000144051,0.0003074054,0.02168168,0.00004790667,0.0005560362,0.000002757819,0.000002091324,0.00005760402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6683011,"threshold_uncertainty_score":0.7445378,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7563916288387372,"gpt":0.5558183455944733,"spread":0.2005732832442639,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01793241,0.0002074922,0.0003120292,0.0004719866,0.0002104532,0.0009078548,0.001912627,0.000132749,0.0002446172],"category_scores_gemma":[0.03541715,0.0001327557,0.00009340419,0.001844855,0.0000542852,0.0007007443,0.0001708481,0.0002446277,0.0002875839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001387683,"about_ca_system_score_gemma":0.00003377419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000100996,"about_ca_topic_score_gemma":0.000004066246,"domain_scores_codex":[0.9959873,0.0001120892,0.0007973635,0.001057425,0.001650745,0.0003950602],"domain_scores_gemma":[0.9893472,0.008083365,0.0001927503,0.001651283,0.0005553286,0.0001701278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001348422,0.0003738735,0.002288302,0.00002229313,0.00007631572,0.000004916293,0.0005252307,0.00007151246,0.005281869,0.1320227,0.04878762,0.8104105],"study_design_scores_gemma":[0.001681932,0.001642628,0.123611,0.00008674321,0.0001439363,0.00003515967,0.009089461,0.01582799,0.0005510147,0.6398067,0.2064317,0.001091775],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009968944,0.001017952,0.9131413,0.002160958,0.001715724,0.001266798,0.0001646642,0.0005490098,0.07001472],"genre_scores_gemma":[0.9578236,0.00001782837,0.0411517,0.0005583303,0.0002881813,0.0001013475,0.00002729786,0.00001029997,0.000021454],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9478546,"threshold_uncertainty_score":0.9727079,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}