{"meta":{"query_hash":"53c7e562b0f3","filters":{"venue":"Multivariate Behavioral Research"},"cohort_total":47,"direct_labels_cover":3,"predictions_cover":47,"exported":47,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/53c7e562b0f3","api":"https://metacan.xera.ac/api/v1/cohort?venue=Multivariate+Behavioral+Research"},"results":[{"id":"W1965908312","doi":"10.1080/00273171.2011.636702","title":"Abstract: Inference and Interval Estimation for Indirect Effects With Latent Variable Models","year":2011,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Mental Health Research Topics","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Statistics; Latent variable; Confidence interval; Type I and type II errors; Structural equation modeling; Mathematics; Coverage probability; Latent variable model; Covariate; Econometrics","score_opus":0.5478691541375651,"score_gpt":0.5494475282255485,"score_spread":0.0015783740879834474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965908312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9764639,0.000092249,0.014735617,0.0000624056,0.00022334328,0.0030102285,0.000049972812,0.00008249807,0.0052797655],"genre_scores_gemma":[0.9696037,0.000007879814,0.027802851,0.000016995762,0.000035824793,0.0012607252,0.00003318286,0.000043325825,0.0011954937],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9972035,0.0003444534,0.0003063385,0.0005597884,0.0005977373,0.0009881664],"domain_scores_gemma":[0.99809736,0.00069021946,0.00007382615,0.00041502903,0.0003563642,0.0003671883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021079516,0.00019309895,0.00026836927,0.00031324223,0.00029615551,0.00008173432,0.0003038715,0.00020515962,0.0005114178],"category_scores_gemma":[0.00016436334,0.00015651001,0.000030307796,0.00030673158,0.00022397879,0.00033234703,0.00019520025,0.00071082293,0.00008784343],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010965092,0.0072870348,0.062762834,0.0024165316,0.00023137263,0.00045065876,0.04398919,0.00010803511,0.011566479,0.09041595,0.00096984557,0.768837],"study_design_scores_gemma":[0.009562083,0.009265662,0.9056681,0.0009089283,0.000085474116,0.000034224016,0.0010081283,0.034547787,0.009487659,0.028158419,0.00038803054,0.0008855249],"about_ca_topic_score_codex":0.009655953,"about_ca_topic_score_gemma":0.0001448371,"teacher_disagreement_score":0.8429052,"about_ca_system_score_codex":0.00018497763,"about_ca_system_score_gemma":0.0001666536,"threshold_uncertainty_score":0.9969388},"labels":[],"label_agreement":null},{"id":"W1981766652","doi":"10.1080/00273171.2012.658328","title":"Modeling Individual Differences in Within-Person Variation of Negative and Positive Affect in a Mixed Effects Location Scale Model Using BUGS/JAGS","year":2012,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Mental Health Research Topics","field":"Psychology","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Affect (linguistics); Stressor; Psychology; Mood; Multilevel model; Scale (ratio); Random effects model; Interaction; Correlation; Variation (astronomy); Developmental psychology; Statistics; Clinical psychology; Medicine; Mathematics; Meta-analysis","score_opus":0.45331745974860327,"score_gpt":0.5344039001917903,"score_spread":0.08108644044318702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981766652","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99402386,0.00015264565,0.003680082,0.000036511592,0.00016252811,0.0018091936,0.00003621738,0.000013787861,0.00008515523],"genre_scores_gemma":[0.9944213,0.0000057703073,0.0052067274,0.0000069030502,0.00004423807,0.00021155097,0.000022764701,0.000029533678,0.00005121379],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9947506,0.002430219,0.00045175385,0.00046756444,0.00091954356,0.0009803099],"domain_scores_gemma":[0.9984618,0.0006852756,0.00010690099,0.00024677473,0.0002528018,0.0002464746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044312845,0.0002036248,0.00038493972,0.00091548904,0.00015613431,0.00004456085,0.00022202084,0.0002731232,0.00002205497],"category_scores_gemma":[0.00032423512,0.0001948529,0.000029988196,0.00093545305,0.0001908471,0.00046141355,0.00018239922,0.0009632995,0.000008275054],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021620323,0.0040723407,0.6410379,0.0005298862,0.0000485939,0.000031923126,0.26285768,0.004998754,0.067924045,0.0025286493,0.0000031949805,0.013805014],"study_design_scores_gemma":[0.0016167696,0.00031080897,0.62165874,0.00028123235,0.00001231577,0.0000022739866,0.0030682124,0.37107995,0.0015680399,0.00027910192,1.3273354e-8,0.00012251925],"about_ca_topic_score_codex":0.05036072,"about_ca_topic_score_gemma":0.0011041671,"teacher_disagreement_score":0.36608118,"about_ca_system_score_codex":0.00055359,"about_ca_system_score_gemma":0.00017897986,"threshold_uncertainty_score":0.955963},"labels":[],"label_agreement":null},{"id":"W1986024887","doi":"10.1080/00273171.2011.636708","title":"Abstract: Within-Person Processes Leading to Quarrelsome Behavior in Interactions Between Romantic Partners","year":2011,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Attachment and Relationship Dynamics","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Psychology; Interpersonal communication; Perception; Developmental psychology; Interpersonal relationship; Multilevel model; Social psychology","score_opus":0.5314181346062891,"score_gpt":0.5929361403061177,"score_spread":0.06151800569982868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986024887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98993456,0.000027376465,0.00016598657,0.0001467446,0.000571981,0.0011491562,0.000027888873,0.00011181616,0.007864463],"genre_scores_gemma":[0.9926167,0.0000014205068,0.00096982595,0.000009164425,0.00010978023,0.00065303035,0.000054056127,0.000063837855,0.005522166],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99702054,0.00026891692,0.0005340495,0.00066454516,0.00057009957,0.00094186905],"domain_scores_gemma":[0.9984935,0.00034453478,0.0001126046,0.00045540414,0.0002732464,0.00032070163],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011891151,0.00025799067,0.00031337483,0.0010862007,0.00033942127,0.00009046136,0.00049139047,0.0002593675,0.0012047628],"category_scores_gemma":[0.00016771596,0.00024574986,0.00007728769,0.0013299058,0.00016842752,0.00039553043,0.0001133854,0.0014613783,0.0019427538],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015909509,0.0011627221,0.95276123,0.000027621269,0.000023346283,0.0001710143,0.03910472,0.000009188488,0.0028930053,0.0008987169,0.0001369333,0.002652419],"study_design_scores_gemma":[0.00064194575,0.0003054371,0.98831856,0.00010952847,0.00005307121,0.0000056129065,0.0094571775,0.000022015096,0.0005518479,0.000082420614,0.00013468656,0.00031771485],"about_ca_topic_score_codex":0.0065301526,"about_ca_topic_score_gemma":0.001861091,"teacher_disagreement_score":0.035557322,"about_ca_system_score_codex":0.00031590526,"about_ca_system_score_gemma":0.00014680049,"threshold_uncertainty_score":0.99999946},"labels":[],"label_agreement":null},{"id":"W1988221738","doi":"10.1080/00273171.2010.498292","title":"Assessing Mediational Models: Testing and Interval Estimation for Indirect Effects","year":2010,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":398,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Markov chain Monte Carlo; Bootstrapping (finance); Computer science; Type I and type II errors; Bayesian probability; Statistics; Confidence interval; Statistical hypothesis testing; Econometrics; Null hypothesis; Prior probability; Mathematics","score_opus":0.6989123915737223,"score_gpt":0.608930368580515,"score_spread":0.08998202299320734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988221738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7655777,0.000005899952,0.23285206,0.000056625635,0.00010025396,0.0009465636,0.000011515343,0.00023472188,0.00021472156],"genre_scores_gemma":[0.55185777,4.866892e-7,0.4477169,0.0000031218947,0.00005106341,0.00030920218,0.000009895136,0.000026212101,0.000025330311],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981856,0.00018022669,0.00029449863,0.0003525856,0.000536491,0.00045064077],"domain_scores_gemma":[0.9920731,0.006798242,0.00010813516,0.00024162987,0.00064909435,0.0001297579],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025478955,0.00016324395,0.00023476941,0.00026336944,0.0003216194,0.00026383917,0.00019901879,0.00019093676,0.00001228137],"category_scores_gemma":[0.010572958,0.00014896889,0.000036273283,0.0002627974,0.00016714235,0.0009648094,0.0001951366,0.00078829203,0.0000030111437],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006368414,0.0004916356,0.003210707,0.00031806584,0.000015706984,0.000014300291,0.0012731532,0.000041104417,0.5571062,0.054263126,0.00012891,0.38307342],"study_design_scores_gemma":[0.0005746021,0.00025017824,0.006332192,0.00016908417,0.000026044081,0.000008552565,0.000087725166,0.23311906,0.048025142,0.7111719,0.000010321245,0.00022517802],"about_ca_topic_score_codex":0.00016579659,"about_ca_topic_score_gemma":0.000047730024,"teacher_disagreement_score":0.6569088,"about_ca_system_score_codex":0.00009869297,"about_ca_system_score_gemma":0.00012387062,"threshold_uncertainty_score":0.9977614},"labels":[],"label_agreement":null},{"id":"W1991374387","doi":"10.1080/00273171.2012.715252","title":"An Investigation of the Sample Performance of Two Nonnormality Corrections for RMSEA","year":2012,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":221,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Structural equation modeling; Statistics; Mathematics; Goodness of fit; Sample (material); Sample size determination; Population; Econometrics; Chemistry","score_opus":0.873633224993975,"score_gpt":0.6517804000643616,"score_spread":0.22185282492961345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991374387","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.992302,0.000020165195,0.0062850174,0.00006183633,0.00064728694,0.0004929941,0.00008572871,0.000013140877,0.00009180956],"genre_scores_gemma":[0.9666016,0.0000019598363,0.033134874,0.0000055523374,0.000084961015,0.000052610325,0.0000051653656,0.000008039115,0.00010525416],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956516,0.001528303,0.0006303616,0.00025888483,0.0014708154,0.00046002527],"domain_scores_gemma":[0.9750326,0.0221137,0.000333796,0.00085124595,0.0015114915,0.00015714778],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0241766,0.00008742293,0.00023287043,0.00041263158,0.0004074126,0.00005099568,0.0009480464,0.000074021205,0.000095744625],"category_scores_gemma":[0.03919747,0.00005280105,0.00010253603,0.0028304837,0.0003860438,0.00051265175,0.0002295821,0.00027971875,0.0000043237424],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006543299,0.00014564252,0.931098,0.000007782463,0.0000022713382,1.7332281e-8,0.0008270971,0.000057745896,0.0303112,0.00036183198,0.000061751394,0.037061226],"study_design_scores_gemma":[0.0003405302,0.0002564165,0.9584437,0.000014847008,0.000007937462,6.2763365e-7,0.00074298563,0.006556606,0.031311356,0.0021252811,0.0001384415,0.00006124989],"about_ca_topic_score_codex":0.0034798768,"about_ca_topic_score_gemma":0.000060146525,"teacher_disagreement_score":0.036999974,"about_ca_system_score_codex":0.000053676245,"about_ca_system_score_gemma":0.0001284078,"threshold_uncertainty_score":0.9688958},"labels":[],"label_agreement":null},{"id":"W1991886460","doi":"10.1080/00273171.2014.963193","title":"Identification of Real and Artifactual Moderators of Effect Size in Meta-Analysis","year":2015,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Mental Health Research Topics","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Mental Health; National Institutes of Health; Medical Research Council Canada","keywords":"Meta-analysis; Confounding; Covariate; Psychology; Outcome (game theory); Clinical psychology; Statistics; Psychotherapist; Medicine; Internal medicine; Mathematics","score_opus":0.6246462726663043,"score_gpt":0.614947560363395,"score_spread":0.009698712302909307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991886460","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99817675,0.00021070485,0.000051185514,0.000104954655,0.00005269504,0.00086213707,0.00006473999,0.0000098972405,0.00046693906],"genre_scores_gemma":[0.99845684,0.000008525303,0.00020667422,0.0000024341557,0.000012060282,0.00021745547,0.000013763338,0.000016329373,0.0010659138],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9941753,0.002873708,0.00078642735,0.00044833584,0.0011855548,0.0005306562],"domain_scores_gemma":[0.99735814,0.001126479,0.00016442599,0.00060220074,0.0004541804,0.00029455626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0092286505,0.00013881187,0.0007874056,0.00079443905,0.00005212043,0.000025636917,0.00027327787,0.00017127804,0.00054689817],"category_scores_gemma":[0.0006586765,0.00011230211,0.00019248988,0.0013599251,0.00030212593,0.00011960132,0.00018330214,0.00048434635,0.00003489429],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006791654,0.0067232666,0.7260352,0.00061578344,0.018553512,0.00021246007,0.045333773,0.0002755164,0.14914441,0.0070853676,0.00046434964,0.038764738],"study_design_scores_gemma":[0.0038154172,0.0024990563,0.9335522,0.000011083584,0.008520267,0.0000023801488,0.0030162265,0.0029250078,0.04443126,0.0008928997,0.000038877282,0.00029532477],"about_ca_topic_score_codex":0.027140066,"about_ca_topic_score_gemma":0.00087589846,"teacher_disagreement_score":0.20751703,"about_ca_system_score_codex":0.00015281134,"about_ca_system_score_gemma":0.00012933057,"threshold_uncertainty_score":0.9793383},"labels":[],"label_agreement":null},{"id":"W2000754699","doi":"10.1080/00273170701360332","title":"Fuzzy Clusterwise Growth Curve Models via Generalized Estimating Equations: An Application to the Antisocial Behavior of Children","year":2007,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sample (material); Monte Carlo method; Population; Covariance; Growth curve (statistics); Mathematics; Fuzzy logic; Econometrics; Computer science; Generalized estimating equation; Cluster analysis; Aggregate (composite); Statistics; Applied mathematics; Artificial intelligence","score_opus":0.39054312890837145,"score_gpt":0.5654358791865369,"score_spread":0.17489275027816548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000754699","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27258998,0.000009929021,0.7250929,0.000073158546,0.000067856105,0.0019233592,0.00011490166,0.00005326277,0.0000746891],"genre_scores_gemma":[0.5181359,0.0000011075405,0.48133093,0.000010944878,0.00012591164,0.00028644654,0.00003890861,0.000038481823,0.000031353746],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959534,0.0007763315,0.0007990526,0.00055738346,0.0011494465,0.0007643808],"domain_scores_gemma":[0.9963062,0.0015007709,0.00020792084,0.00067563355,0.0010083896,0.0003010935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058334307,0.00023704716,0.00040567978,0.00025646226,0.00054659083,0.00006722069,0.0006106118,0.00017837589,0.000015362652],"category_scores_gemma":[0.0013942734,0.00018553907,0.00009804497,0.00068114646,0.00019599902,0.00032682394,0.00030171502,0.0005449628,0.00001349528],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004990677,0.0031745848,0.002294411,0.00007105894,0.000040395815,0.00001630362,0.0064519937,0.002829076,0.07975605,0.51207846,0.000071261624,0.39271733],"study_design_scores_gemma":[0.0016695376,0.00059103983,0.009069467,0.000065187254,0.00016939787,0.0000074546024,0.0004336427,0.26406866,0.006924106,0.71647793,0.0000046277514,0.0005189445],"about_ca_topic_score_codex":0.003533403,"about_ca_topic_score_gemma":0.00037673276,"teacher_disagreement_score":0.39219838,"about_ca_system_score_codex":0.00016861822,"about_ca_system_score_gemma":0.000084836,"threshold_uncertainty_score":0.7566064},"labels":[],"label_agreement":null},{"id":"W2003103389","doi":"10.1080/00273171.2013.841089","title":"Fighting for Intelligence: A Brief Overview of the Academic Work of John L. Horn","year":2014,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute on Aging; National Institutes of Health","keywords":"Psychology; French horn; Personality; Exploratory factor analysis; Confirmatory factor analysis; Trait; Big Five personality traits; Cognition; Cognitive psychology; Social psychology; Developmental psychology; Structural equation modeling; Psychometrics; Computer science","score_opus":0.48454829235878805,"score_gpt":0.5396495645253334,"score_spread":0.05510127216654537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003103389","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99326646,0.0004881328,0.0012591049,0.00023973886,0.00032573385,0.001059595,0.00005618745,0.00002257221,0.0032824492],"genre_scores_gemma":[0.99770033,0.0000119423485,0.0006232155,0.000021611502,0.00012665604,0.00017671665,0.0000048487755,0.000029669138,0.0013050169],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9972764,0.0007348907,0.00055331585,0.0003661638,0.0004854225,0.0005838103],"domain_scores_gemma":[0.9954908,0.003002791,0.00019902382,0.0004977559,0.0007328146,0.00007682106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003474539,0.00013490228,0.00029637874,0.00013623046,0.00019653418,0.000016134656,0.00058474997,0.0001885742,0.00067812705],"category_scores_gemma":[0.0025481342,0.00009869865,0.00018260072,0.00075868267,0.0004019684,0.00005346062,0.00036538698,0.0007647643,0.000019105524],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047256367,0.00059874915,0.1751629,0.00027568234,0.00004564118,0.0000016729699,0.008565221,0.000011327833,0.009373706,0.026266864,0.00087732624,0.7783483],"study_design_scores_gemma":[0.001945401,0.0013692034,0.9407189,0.0017556623,0.00012676317,0.000006554441,0.006835656,0.00087136455,0.020382972,0.013232034,0.01226881,0.00048670205],"about_ca_topic_score_codex":0.002181258,"about_ca_topic_score_gemma":0.00002852463,"teacher_disagreement_score":0.77786165,"about_ca_system_score_codex":0.00004247913,"about_ca_system_score_gemma":0.00007469556,"threshold_uncertainty_score":0.74250156},"labels":[],"label_agreement":null},{"id":"W2005967696","doi":"10.1080/00273171.2014.933697","title":"Adjusting Incremental Fit Indices for Nonnormality","year":2014,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":223,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Ottawa","funders":"","keywords":"Statistics; Mathematics; Index (typography); Structural equation modeling; Population; Goodness of fit; Econometrics; Value (mathematics); Sample (material); Computer science","score_opus":0.9278926090737645,"score_gpt":0.6852634534042872,"score_spread":0.2426291556694773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005967696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97558415,0.000038389946,0.01869609,0.00044383176,0.00056894694,0.00068377284,0.000046602956,0.00008300533,0.003855187],"genre_scores_gemma":[0.95383865,0.0000020041984,0.044696707,0.000059146074,0.00030280705,0.0001170745,0.000009207622,0.00002050412,0.00095389306],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99207723,0.0022802323,0.0008729646,0.00088923646,0.0028366803,0.0010436333],"domain_scores_gemma":[0.9223975,0.074311964,0.0003666044,0.0010535826,0.0015120469,0.00035827918],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.056414478,0.00018736732,0.0004105004,0.0009965936,0.00093226,0.000591249,0.0016341727,0.00017231551,0.0004546859],"category_scores_gemma":[0.18058597,0.00013771685,0.0001582609,0.0025611029,0.0002389319,0.00040642492,0.0008081178,0.000584781,0.00015212264],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025760598,0.00032147596,0.29452303,0.000016767286,0.000009366798,0.0000052211963,0.0005909563,0.000034617817,0.011422127,0.0009836545,0.0032559724,0.6885792],"study_design_scores_gemma":[0.0021224718,0.0009794842,0.92198664,0.000049035327,0.000019573368,0.0000068704194,0.0028327636,0.020357309,0.004262455,0.013564301,0.0333947,0.00042439284],"about_ca_topic_score_codex":0.001932621,"about_ca_topic_score_gemma":0.0000725313,"teacher_disagreement_score":0.6881548,"about_ca_system_score_codex":0.00011599923,"about_ca_system_score_gemma":0.00008661178,"threshold_uncertainty_score":0.97161984},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2014956237","doi":"10.1080/00273171.2013.751295","title":"Abstract: RMSEA With Nonnormal Data: A Comparison of Two Robust Corrections","year":2013,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Multi-Criteria Decision Making","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Structural equation modeling; Computer science; Statistics; Econometrics; Data mining; Mathematics","score_opus":0.8249248068608278,"score_gpt":0.6416101974285493,"score_spread":0.1833146094322785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014956237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9852454,0.000037424794,0.010547406,0.00031119524,0.000577802,0.0012059931,0.00020606088,0.00007230982,0.0017964189],"genre_scores_gemma":[0.9711476,0.0000018715642,0.027038882,0.000010570741,0.00013160176,0.000109281995,0.000057823996,0.000046926038,0.0014554554],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98899317,0.00079323165,0.0016318357,0.0013787802,0.0061367527,0.001066235],"domain_scores_gemma":[0.9879146,0.00376637,0.0004942602,0.003392613,0.003953212,0.00047889512],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008615083,0.00032033445,0.00075485866,0.0013003941,0.000657344,0.0012889672,0.00392835,0.00018472994,0.0056430986],"category_scores_gemma":[0.003325302,0.00022084975,0.00010808883,0.002701383,0.00066412723,0.0021760138,0.0021304241,0.0012561558,0.0023940636],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006274198,0.004102211,0.48631993,0.000023000028,0.00004816999,0.00009350843,0.003894072,0.004242844,0.077522725,0.0004934054,0.023020728,0.399612],"study_design_scores_gemma":[0.003334602,0.0005914292,0.8252726,0.00016873631,0.000036241898,0.000018326207,0.0073890546,0.15360335,0.003575088,0.00091675925,0.0044794776,0.0006143412],"about_ca_topic_score_codex":0.02406668,"about_ca_topic_score_gemma":0.0023993214,"teacher_disagreement_score":0.39899766,"about_ca_system_score_codex":0.00013746908,"about_ca_system_score_gemma":0.0003874481,"threshold_uncertainty_score":0.9997478},"labels":[],"label_agreement":null},{"id":"W2029342244","doi":"10.1207/s15327906mbr3902_8","title":"Psychometric Properties of the HEXACO Personality Inventory","year":2004,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Personality Traits and Psychology","field":"Psychology","cited_by":1958,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; University of Calgary","funders":"","keywords":"Agreeableness; Psychology; Facet (psychology); Personality Assessment Inventory; Personality; Big Five personality traits and culture; Conscientiousness; Openness to experience; Big Five personality traits; Extraversion and introversion; Alternative five model of personality; Hierarchical structure of the Big Five; Social psychology","score_opus":0.48719321848499736,"score_gpt":0.5057646919226918,"score_spread":0.01857147343769444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029342244","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98825073,0.00066856825,0.000018646788,0.0016736024,0.00094430253,0.00062015606,0.00004702254,0.000040922856,0.0077360524],"genre_scores_gemma":[0.99576545,0.000007781206,0.00009015984,0.00015178465,0.00014674493,0.00013147767,0.000004051339,0.000033395252,0.0036691343],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99623704,0.0008843028,0.00043887063,0.00058319233,0.0010314184,0.0008252053],"domain_scores_gemma":[0.9983851,0.000059259728,0.00011460277,0.00087831926,0.00038445543,0.00017827335],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022410383,0.00020594799,0.0003036462,0.00040626145,0.00033283405,0.000038872575,0.0009690714,0.00027407616,0.0012253973],"category_scores_gemma":[0.00014783493,0.000135344,0.00023374656,0.0016991029,0.0010794302,0.0000971043,0.00019654179,0.0010381376,0.00028500686],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020277514,0.014452938,0.46044087,0.00019917148,0.00031495292,0.00004703606,0.061727878,0.000018988498,0.37136242,0.05001275,0.0051912065,0.03420404],"study_design_scores_gemma":[0.0023756933,0.0003784166,0.9858269,0.00008336352,0.000025651923,0.000021498552,0.0016824479,0.0000020992427,0.0027778188,0.00089157827,0.0057211346,0.00021341181],"about_ca_topic_score_codex":0.017872527,"about_ca_topic_score_gemma":0.0002545892,"teacher_disagreement_score":0.52538604,"about_ca_system_score_codex":0.00019988602,"about_ca_system_score_gemma":0.00020835639,"threshold_uncertainty_score":0.9996876},"labels":[],"label_agreement":null},{"id":"W2036193982","doi":"10.1080/00273171.2011.568786","title":"An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies","year":2011,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11884,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Observational study; Covariate; Confounding; Statistics; Inverse probability weighting; Econometrics; Mathematics","score_opus":0.8974226593536919,"score_gpt":0.6794649079660394,"score_spread":0.2179577513876525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036193982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9202135,0.000022144797,0.07665904,0.00020195756,0.00016533416,0.0026595446,0.0000032414498,0.00006038761,0.000014840273],"genre_scores_gemma":[0.58024377,0.0000039873366,0.4189482,0.000005200957,0.00007632076,0.00064324035,0.0000031979241,0.00001906868,0.000057012254],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99763095,0.0009212406,0.0003871311,0.00035927343,0.00032590583,0.00037548895],"domain_scores_gemma":[0.9958278,0.0023781403,0.000111100744,0.00049141847,0.0011282375,0.00006328556],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0067533776,0.00013203618,0.00032604675,0.0002465841,0.00018893168,0.000023301007,0.0003384725,0.0000790503,0.000009914063],"category_scores_gemma":[0.010852301,0.000092967835,0.000039917817,0.00050057867,0.0002033273,0.0003066678,0.00020073452,0.0003656098,0.000001178264],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035559895,0.0006330891,0.005786605,0.0003384953,0.00002239347,0.0000035293046,0.015909398,0.000005958023,0.8450568,0.094109856,0.00017766858,0.03760062],"study_design_scores_gemma":[0.00043097223,0.0015041771,0.047009274,0.00029732336,0.00003366003,0.0000019214062,0.001437723,0.00029813507,0.74971914,0.1989969,0.000077346354,0.00019341597],"about_ca_topic_score_codex":0.0006518969,"about_ca_topic_score_gemma":0.00010462125,"teacher_disagreement_score":0.34228915,"about_ca_system_score_codex":0.00025818826,"about_ca_system_score_gemma":0.000084135405,"threshold_uncertainty_score":0.99747974},"labels":[],"label_agreement":null},{"id":"W2036514462","doi":"10.1080/00273171.2011.589280","title":"Multilevel SEM Strategies for Evaluating Mediation in Three-Level Data","year":2011,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Mount Allison University","keywords":"Mediation; Multilevel model; Computer science; Structural equation modeling; Psychology; Data mining; Econometrics; Statistics; Mathematics; Machine learning; Sociology","score_opus":0.9563346823471308,"score_gpt":0.6781517874356203,"score_spread":0.2781828949115105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036514462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59485775,0.000022466149,0.40054375,0.00004655635,0.000115751034,0.002982783,0.0004281544,0.00030023593,0.0007025687],"genre_scores_gemma":[0.6194851,0.0000037439527,0.3796761,0.0000033518422,0.00003979581,0.00054688123,0.00009945428,0.00004804397,0.00009754101],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99649805,0.00036276336,0.00063830154,0.0007135706,0.0009399936,0.0008473084],"domain_scores_gemma":[0.9961129,0.0015708628,0.00016306013,0.0012425025,0.00078694813,0.00012377117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063841245,0.00024727665,0.00034645337,0.00040504656,0.00019598256,0.00009798583,0.0011847529,0.0002499108,0.00019422312],"category_scores_gemma":[0.0036019357,0.00022768197,0.00004653877,0.00038718467,0.00017183431,0.0011665507,0.0007630719,0.0007046744,0.00002350985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014783116,0.0049844054,0.027676648,0.00060462294,0.000071362134,0.00009795224,0.026818126,0.00002428371,0.19611375,0.31621918,0.0013801217,0.42453125],"study_design_scores_gemma":[0.0016841129,0.00067334645,0.03755224,0.00018989138,0.000030456891,0.0000023939863,0.0027739902,0.055996906,0.010399449,0.89019483,0.000037276794,0.0004651028],"about_ca_topic_score_codex":0.0033749777,"about_ca_topic_score_gemma":0.0037928445,"teacher_disagreement_score":0.5739757,"about_ca_system_score_codex":0.00026672406,"about_ca_system_score_gemma":0.0004240744,"threshold_uncertainty_score":0.9284602},"labels":[],"label_agreement":null},{"id":"W2037948952","doi":"10.1080/00273171.2010.532361","title":"Selection Between Linear Factor Models and Latent Profile Models Using Conditional Covariances","year":2010,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; York University","keywords":"Latent class model; Latent variable model; Latent variable; Factor analysis; Computer science; Model selection; Class (philosophy); Mathematics; Econometrics; Statistics; Artificial intelligence; Machine learning","score_opus":0.47595027100645143,"score_gpt":0.5155987626752487,"score_spread":0.0396484916687973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037948952","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24965602,0.0000068013574,0.7494465,0.000090388785,0.00006321818,0.00040762086,0.00008450304,0.00022136646,0.000023590765],"genre_scores_gemma":[0.53247124,0.0000026378352,0.46736604,0.0000050109284,0.000056498928,0.00004450119,0.000016847778,0.0000145503045,0.000022645076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99725896,0.00020505744,0.00032930728,0.0007127191,0.00088604935,0.00060793315],"domain_scores_gemma":[0.9982796,0.00030153492,0.00007315771,0.00036830423,0.0007135238,0.00026388225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007590007,0.00020120629,0.00024244894,0.00026621655,0.0005668638,0.0002332092,0.0005939137,0.00021786756,0.000026257658],"category_scores_gemma":[0.00008646437,0.00018700628,0.000040076487,0.00044051584,0.00025985728,0.0014807542,0.0005312681,0.0011162863,0.000009118198],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009041818,0.00061536196,0.0046138032,0.0000656289,0.000037844602,0.000047499332,0.0015430497,0.01657879,0.38201767,0.5386043,0.0000651978,0.055720415],"study_design_scores_gemma":[0.00021372458,0.00011250767,0.0013169218,0.000014542765,0.0000049672926,0.000005377609,0.0000053822305,0.7462315,0.0067323297,0.24518277,0.000011590743,0.00016840047],"about_ca_topic_score_codex":0.0013353772,"about_ca_topic_score_gemma":0.000031755426,"teacher_disagreement_score":0.7296527,"about_ca_system_score_codex":0.00011965667,"about_ca_system_score_gemma":0.00021169233,"threshold_uncertainty_score":0.7625895},"labels":[],"label_agreement":null},{"id":"W2051550601","doi":"10.1080/00273171.2014.905766","title":"On Johnson's (2000) Relative Weights Method for Assessing Variable Importance: A Reanalysis","year":2014,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Carleton University","funders":"","keywords":"Variable (mathematics); Metric (unit); Statistics; Mathematics; Linear regression; Regression; Regression analysis; Econometrics; Computer science; Engineering","score_opus":0.4015639991587576,"score_gpt":0.5945831617637344,"score_spread":0.19301916260497676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051550601","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070346487,0.000018573905,0.9860689,0.0001733712,0.00011434496,0.0009912873,0.00009924144,0.000100627905,0.0053990083],"genre_scores_gemma":[0.0321337,0.0000046479677,0.96245855,0.000037701346,0.00014291065,0.00043418648,0.00003336154,0.000098505894,0.004656417],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941757,0.0020153944,0.00065289997,0.0009459989,0.001114198,0.0010958257],"domain_scores_gemma":[0.98115176,0.016436512,0.00022796605,0.0008708864,0.0009657691,0.000347128],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00989653,0.0003327251,0.0007348553,0.0003908654,0.00072934566,0.00018767144,0.00039355966,0.00028595907,0.00027746073],"category_scores_gemma":[0.012909553,0.00026572953,0.0001992898,0.00076976,0.00014356052,0.00038616147,0.00015443216,0.0009543991,0.000025457948],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022912,0.0005915366,0.00006664327,0.00007005373,0.000057187972,0.00001225632,0.0004410424,0.000073392905,0.0040549287,0.94864625,0.0008522852,0.044905283],"study_design_scores_gemma":[0.0011319235,0.00040419312,0.00020818933,0.00011662754,0.00016320108,0.0000019648414,0.0000961896,0.08816712,0.0009464714,0.90349364,0.0049513145,0.00031913223],"about_ca_topic_score_codex":0.00034975237,"about_ca_topic_score_gemma":0.000022067825,"teacher_disagreement_score":0.08809373,"about_ca_system_score_codex":0.00043094007,"about_ca_system_score_gemma":0.00021985303,"threshold_uncertainty_score":0.9999795},"labels":[],"label_agreement":null},{"id":"W2056241146","doi":"10.1080/00273171003680278","title":"The Other Side of Method Bias: The Perils of Distinct Source Research Designs","year":2010,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Variance (accounting); Observer (physics); Computer science; Focus (optics); Data source; Econometrics; Common-method variance; Data science; Data mining; Statistics; Mathematics","score_opus":0.8266679186751913,"score_gpt":0.6096089629458628,"score_spread":0.21705895572932854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056241146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9851825,0.00036030964,0.00049930566,0.0019223524,0.0005940809,0.0012898863,0.00007247466,0.000042659012,0.010036411],"genre_scores_gemma":[0.9884461,0.000015194525,0.0012564467,0.00001805049,0.0002070025,0.0004606005,0.0000030769197,0.0000504558,0.00954308],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.989834,0.0056190277,0.00082540145,0.0006535432,0.0017112988,0.0013567335],"domain_scores_gemma":[0.9894723,0.0073539424,0.00021989664,0.0014699205,0.001293203,0.00019072235],"candidate_categories":["sts","research_integrity","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.021810962,0.00026098828,0.0004516695,0.00021561576,0.0014102522,0.00010304925,0.0018268292,0.00035963103,0.00188455],"category_scores_gemma":[0.0015017465,0.00012522168,0.00024350347,0.0013864716,0.0034399193,0.000058559577,0.00068697147,0.003017233,0.00024503877],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018078954,0.0029408669,0.09255152,0.000024177909,0.00012741833,0.000033988235,0.014674933,0.0000019312513,0.33246505,0.020080483,0.0052499822,0.53004175],"study_design_scores_gemma":[0.0013341799,0.0016045048,0.8361195,0.00004664694,0.00006387839,0.000016758708,0.011279092,0.00003296936,0.012057793,0.0033051036,0.13380666,0.00033292218],"about_ca_topic_score_codex":0.030518666,"about_ca_topic_score_gemma":0.0019867283,"teacher_disagreement_score":0.74356794,"about_ca_system_score_codex":0.00004257327,"about_ca_system_score_gemma":0.000084951156,"threshold_uncertainty_score":0.9998898},"labels":[],"label_agreement":null},{"id":"W2058280804","doi":"10.1080/00273170903504893","title":"Simultaneous Two-Way Clustering of Multiple Correspondence Analysis","year":2010,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Categorical variable; Cluster analysis; Correspondence analysis; Centroid; Variable (mathematics); Multiple correspondence analysis; Partition (number theory); Cluster (spacecraft); Statistics; Mathematics; Data mining; Contingency table; Extant taxon; Multivariate statistics; Computer science; Artificial intelligence","score_opus":0.22477204831980976,"score_gpt":0.4679075736295627,"score_spread":0.24313552530975294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058280804","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9974905,0.000010067687,0.0016628752,0.00007450562,0.00012419501,0.00021612122,0.00014345463,0.000036417816,0.00024181657],"genre_scores_gemma":[0.9868704,0.00000331354,0.01227507,0.000009133624,0.00010267891,0.00001849623,0.000047864254,0.0000020876978,0.00067097106],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9967907,0.0007827951,0.00045340954,0.00052999315,0.00085223455,0.00059087045],"domain_scores_gemma":[0.99313813,0.0056708907,0.000108059176,0.00021588769,0.0006034237,0.00026357823],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023258796,0.00017176439,0.00044166562,0.0001380426,0.00034103086,0.000098278804,0.0005571651,0.00015728695,0.002804252],"category_scores_gemma":[0.002548061,0.00007316015,0.000258335,0.002338051,0.00030582194,0.0000928794,0.00024039348,0.00074118155,0.000054618056],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015661285,0.0002770413,0.029483523,0.0000029352998,0.000042624313,0.000040729596,0.00010246564,0.0004727556,0.81992924,0.000135788,0.000005969865,0.14935035],"study_design_scores_gemma":[0.0005319812,0.00059447315,0.582387,0.000015971667,0.00032196488,0.000005989613,0.00065303233,0.37621862,0.03722919,0.00031350434,0.0012929228,0.0004353699],"about_ca_topic_score_codex":0.011357534,"about_ca_topic_score_gemma":0.015043765,"teacher_disagreement_score":0.7827,"about_ca_system_score_codex":0.000025392053,"about_ca_system_score_gemma":0.000014092156,"threshold_uncertainty_score":0.9981073},"labels":[],"label_agreement":null},{"id":"W2065417422","doi":"10.1080/00273171.2011.540480","title":"A Tutorial and Case Study in Propensity Score Analysis: An Application to Estimating the Effect of In-Hospital Smoking Cessation Counseling on Mortality","year":2011,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":421,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; U.S. Public Health Service; Ontario Ministry of Health and Long-Term Care","keywords":"Propensity score matching; Covariate; Medicine; Inverse probability weighting; Observational study; Matching (statistics); Statistics; Internal medicine; Mathematics","score_opus":0.49956942762470347,"score_gpt":0.5544291490721748,"score_spread":0.05485972144747131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065417422","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98936915,0.0000012595694,0.007351854,0.0000036939489,0.000029825354,0.0031861255,0.0000048774486,0.00004452715,0.000008693598],"genre_scores_gemma":[0.99444634,2.407144e-7,0.0048762024,7.645751e-7,0.00002559479,0.0006285615,0.000004531065,0.000016952388,8.0962093e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972368,0.0010037763,0.00045886624,0.00042802902,0.0005897137,0.00028285445],"domain_scores_gemma":[0.998486,0.00053905667,0.00014269941,0.00052335876,0.00024220298,0.00006671725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068433364,0.00015068626,0.0003569563,0.00042444875,0.00013683566,0.00004745501,0.00021134714,0.00008689401,0.0000035283792],"category_scores_gemma":[0.00083836785,0.00010841024,0.00002990818,0.0010628183,0.00008308078,0.00024502043,0.00015112603,0.0005047229,5.0810513e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023312334,0.0011006668,0.967175,0.000035740148,0.000024478131,0.00017112825,0.023173565,0.00025548652,0.0018024233,0.00025988856,2.6731973e-7,0.005768243],"study_design_scores_gemma":[0.0014548715,0.0056238207,0.9465007,0.0001685695,0.00026748588,0.000006815613,0.0040699034,0.028412258,0.008239657,0.004967135,1.10514236e-7,0.00028866707],"about_ca_topic_score_codex":0.038054578,"about_ca_topic_score_gemma":0.009327245,"teacher_disagreement_score":0.028727332,"about_ca_system_score_codex":0.00018904873,"about_ca_system_score_gemma":0.000032473046,"threshold_uncertainty_score":0.9683511},"labels":[],"label_agreement":null},{"id":"W2068031621","doi":"10.1080/00273171.2014.931800","title":"Recovering Substantive Factor Loadings in the Presence of Acquiescence Bias: A Comparison of Three Approaches","year":2014,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Acquiescence; Factor (programming language); Econometrics; Statistics; Factor analysis; Psychology; Reliability engineering; Computer science; Mathematics; Political science; Engineering; Law","score_opus":0.9425613097282266,"score_gpt":0.6184554955586505,"score_spread":0.32410581416957607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068031621","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9885658,0.00011225669,0.009761167,0.00010036072,0.0001365554,0.00050691754,0.000017928025,0.00001247845,0.00078651076],"genre_scores_gemma":[0.990047,0.000006234101,0.00984056,0.0000026441173,0.000024435392,0.00002912511,9.466891e-7,0.000010195577,0.000038907212],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9913986,0.0031505541,0.0011205183,0.0006168878,0.0031073105,0.00060617574],"domain_scores_gemma":[0.92175305,0.075803936,0.0005669413,0.0010567586,0.0007323833,0.000086937696],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02840683,0.00016265048,0.0006177813,0.00095915835,0.00016170969,0.0001552264,0.002519898,0.00013115644,0.000074302254],"category_scores_gemma":[0.1273967,0.000096753065,0.00011981493,0.004855209,0.00056175335,0.00030494572,0.00053205446,0.0006767644,0.000011124855],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012432376,0.00032410657,0.8366115,0.00001611574,0.0000037555824,0.0000017737912,0.0071431748,0.00008621477,0.015278458,0.0007377336,0.000042542943,0.13963026],"study_design_scores_gemma":[0.00040245787,0.00041037076,0.95694387,0.000101562975,0.0000042761653,0.0000010280361,0.0091483835,0.01806294,0.010624358,0.0040898626,0.00009246532,0.000118396645],"about_ca_topic_score_codex":0.0030124742,"about_ca_topic_score_gemma":0.0003028913,"teacher_disagreement_score":0.13951187,"about_ca_system_score_codex":0.00005109478,"about_ca_system_score_gemma":0.0000748079,"threshold_uncertainty_score":0.98452973},"labels":[],"label_agreement":null},{"id":"W2084126787","doi":"10.1080/00273171.2011.606748","title":"Comparison of Methods for Collecting and Modeling Dissimilarity Data: Applications to Complex Sound Stimuli","year":2011,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Multisensory perception and integration","field":"Psychology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Sorting; Reliability (semiconductor); Computer science; Pattern recognition (psychology); Hierarchical database model; Data mining; Artificial intelligence; Statistics; Mathematics; Algorithm","score_opus":0.9508423595852682,"score_gpt":0.7395595268481697,"score_spread":0.21128283273709847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084126787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2672262,0.00003101239,0.72924376,0.000057879555,0.00009221586,0.0018228145,0.00029810457,0.00004002152,0.0011879794],"genre_scores_gemma":[0.7414334,0.000001691082,0.25758567,0.00001159474,0.000040439158,0.0004072253,0.00014968924,0.00002144323,0.00034885693],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977003,0.0006234858,0.00049110316,0.0005893114,0.00020225893,0.00039353993],"domain_scores_gemma":[0.9980294,0.0004117882,0.00008037801,0.00071100163,0.0005765259,0.00019091567],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022884663,0.00013714038,0.00031338388,0.0002771878,0.00044586766,0.000051842166,0.00041962817,0.00014787918,0.0009183639],"category_scores_gemma":[0.00026913828,0.00013085503,0.000041348092,0.00036465385,0.00013774053,0.00013454926,0.00027444342,0.00035834295,0.000024079618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002359121,0.005790226,0.06464895,0.00014800012,0.00011954663,0.0000013556506,0.079285555,0.000247522,0.3099815,0.01234562,0.0048519876,0.52022064],"study_design_scores_gemma":[0.002032147,0.00091549417,0.12545297,0.00003709773,0.00009804983,0.0000032456567,0.02159645,0.84067386,0.0014448016,0.0014657618,0.0058474834,0.0004326427],"about_ca_topic_score_codex":0.0041740243,"about_ca_topic_score_gemma":0.00033893101,"teacher_disagreement_score":0.8404263,"about_ca_system_score_codex":0.000065677144,"about_ca_system_score_gemma":0.000039912364,"threshold_uncertainty_score":0.99999493},"labels":[{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"bench_or_experimental","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"bench_or_experimental","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2087644214","doi":"10.1080/00273171.2013.752267","title":"Abstract: Longitudinal Examination of the Interpersonal Impact of Behavioral Variability","year":2013,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Interpersonal communication; Psychology; Supervisor; Longitudinal study; Interpersonal relationship; Behavioural sciences; Applied psychology; Social psychology; Political science; Medicine; Psychotherapist; Law","score_opus":0.5059692537244797,"score_gpt":0.5698292122761865,"score_spread":0.0638599585517069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087644214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9969784,0.000004134005,0.0009902566,0.000024017383,0.000072281364,0.0012066099,0.000070698596,0.000059981256,0.00059360353],"genre_scores_gemma":[0.992356,0.0000016627437,0.007205941,7.0642494e-7,0.00002444976,0.00017998918,0.000008119241,0.00003374018,0.00018937557],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99669814,0.00057695067,0.0006970953,0.0003696058,0.0011267132,0.0005314878],"domain_scores_gemma":[0.9961406,0.0009548774,0.00032331047,0.00085664657,0.0016023747,0.00012220786],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029284144,0.00023027614,0.0004035896,0.00022642959,0.00012409301,0.000042994794,0.00073206844,0.00022302338,0.0016580241],"category_scores_gemma":[0.000937844,0.00015331098,0.00027783748,0.00056302577,0.000691254,0.00046927185,0.00046192115,0.0008339851,0.000016884696],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011952319,0.005056804,0.20793137,0.00018967676,0.00004546983,0.0000058881906,0.0039368263,0.000006973147,0.73036337,0.008270805,0.00040843635,0.043664865],"study_design_scores_gemma":[0.00031078252,0.00048572867,0.919775,0.00013206615,0.0000270707,0.0000029692933,0.00030908705,0.00020798491,0.05165557,0.026940783,0.000002003348,0.00015096],"about_ca_topic_score_codex":0.010799967,"about_ca_topic_score_gemma":0.00009170511,"teacher_disagreement_score":0.7118436,"about_ca_system_score_codex":0.0004879779,"about_ca_system_score_gemma":0.00021204853,"threshold_uncertainty_score":0.9992546},"labels":[],"label_agreement":null},{"id":"W2089004370","doi":"10.1080/00273171.2014.911075","title":"Assessing Approximate Fit in Categorical Data Analysis","year":2014,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":276,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Statistics; Categorical variable; Goodness of fit; Bivariate analysis; Statistic; Ordinal data; Mean squared error; Multivariate statistics; Item response theory; Cutoff; Econometrics; Psychometrics","score_opus":0.959382260741685,"score_gpt":0.7182746444274037,"score_spread":0.24110761631428124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089004370","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8743252,0.00005339425,0.120997965,0.00030435692,0.00025613295,0.00026275797,0.000018538029,0.000063156,0.0037185042],"genre_scores_gemma":[0.94636214,0.000004795175,0.053038992,0.000013603955,0.000090851594,0.000021212192,0.000032997374,0.000016228754,0.00041915954],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9877265,0.005116583,0.001031515,0.0015912232,0.0034831513,0.0010510251],"domain_scores_gemma":[0.94018877,0.054261353,0.00029113196,0.004070431,0.0008200483,0.00036828863],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06789506,0.00019377998,0.00068479613,0.0036954018,0.0003645494,0.0015684933,0.0039150664,0.00019483212,0.00045749074],"category_scores_gemma":[0.13530535,0.00013879532,0.00012484723,0.018096842,0.0002166894,0.0010252681,0.0023726805,0.0009957455,0.00015139542],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032535052,0.00037978025,0.5946727,0.0000035544488,0.000021286827,0.00005240723,0.00023815814,0.00032473737,0.0012742633,0.0006026227,0.00036317794,0.40203482],"study_design_scores_gemma":[0.00043445372,0.00006212924,0.6948122,0.0000067289902,0.000036371654,0.0000033761528,0.00088463386,0.29454723,0.000052223113,0.008106944,0.0008746418,0.0001790714],"about_ca_topic_score_codex":0.00768937,"about_ca_topic_score_gemma":0.00028256988,"teacher_disagreement_score":0.40185574,"about_ca_system_score_codex":0.00013810846,"about_ca_system_score_gemma":0.00011551041,"threshold_uncertainty_score":0.99946797},"labels":[],"label_agreement":null},{"id":"W2095572468","doi":"10.1080/00273171.2013.866537","title":"A Computationally Efficient State Space Approach to Estimating Multilevel Regression Models and Multilevel Confirmatory Factor Models","year":2014,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Cultural Differences and Values","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Multilevel model; Univariate; State space; Regression analysis; Structural equation modeling; Confirmatory factor analysis; Multivariate statistics; Marginal model; Computer science; Econometrics; Regression; Statistics; Mathematics; Machine learning","score_opus":0.5219984882668063,"score_gpt":0.5198731016349213,"score_spread":0.0021253866318849957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095572468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7591863,0.00004055681,0.23818275,0.00009263421,0.00021414274,0.0010563855,0.00013221602,0.00010789238,0.000987079],"genre_scores_gemma":[0.93115634,0.000001762986,0.06691326,0.00003891786,0.00008293623,0.00024368531,0.00005724022,0.000057200406,0.0014486333],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99542546,0.00085327495,0.00052863517,0.0010577205,0.0011214244,0.0010135099],"domain_scores_gemma":[0.99768525,0.00052583095,0.00013864576,0.000476292,0.00060331624,0.00057066587],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011758028,0.0004047631,0.00047712278,0.00035005537,0.00056575454,0.0002596559,0.00045005538,0.00021838157,0.00008788219],"category_scores_gemma":[0.00013626699,0.0003068829,0.000092710674,0.00022211528,0.00022891739,0.00023074908,0.00047066243,0.0007350792,0.000118076154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001343759,0.0047314796,0.00391096,0.0002733897,0.00013197695,0.00004035332,0.16359104,0.4406971,0.027184451,0.057373,0.0016137708,0.2991087],"study_design_scores_gemma":[0.0015276824,0.00019623326,0.10841744,0.00012850059,0.000011672307,0.0000078289595,0.0008779337,0.88630617,0.00009881167,0.0020190175,0.00004512025,0.00036359305],"about_ca_topic_score_codex":0.0042982176,"about_ca_topic_score_gemma":0.000015608663,"teacher_disagreement_score":0.44560906,"about_ca_system_score_codex":0.00013503671,"about_ca_system_score_gemma":0.00006357623,"threshold_uncertainty_score":0.9999383},"labels":[],"label_agreement":null},{"id":"W2139491581","doi":"10.1080/00273171.2012.640600","title":"Using Ensemble-Based Methods for Directly Estimating Causal Effects: An Investigation of Tree-Based G-Computation","year":2012,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; U.S. Public Health Service; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Inverse probability weighting; Statistics; Observational study; Logistic regression; Random forest; Regression; Confounding; Causal inference; Regression analysis; Inverse probability; Econometrics; Mathematics; Computer science; Machine learning; Bayesian probability","score_opus":0.6865806864982038,"score_gpt":0.6435797549976086,"score_spread":0.04300093150059525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139491581","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4365646,0.000010132011,0.56209415,0.000011543753,0.000079761965,0.0010617627,0.000009028272,0.00015871187,0.000010328649],"genre_scores_gemma":[0.48216012,7.807107e-8,0.51746637,0.00000551157,0.000054285323,0.00022565969,0.000034909528,0.0000489459,0.000004119105],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99560165,0.002031002,0.0006117257,0.00037785125,0.00059922616,0.0007785496],"domain_scores_gemma":[0.9920454,0.006026205,0.00032610234,0.0004153747,0.0009198311,0.00026708117],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006740844,0.0002669632,0.00045568895,0.0005099928,0.00027282708,0.00006097414,0.00024433192,0.00023699249,0.000008600504],"category_scores_gemma":[0.0029578805,0.00025607608,0.00010420394,0.0006066855,0.00023162857,0.0006110904,0.0000702681,0.00040759039,0.0000014667737],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015858053,0.0004959054,0.0037015246,0.00041853206,0.00000941036,0.0000013246366,0.0008943558,0.00058305427,0.9096794,0.0029264274,0.000008639326,0.08112283],"study_design_scores_gemma":[0.00074408966,0.00048557017,0.0013342622,0.00021924137,0.000059130583,6.273977e-7,0.000060497285,0.3801519,0.5877797,0.028969664,0.0000017724884,0.0001935512],"about_ca_topic_score_codex":0.0007821609,"about_ca_topic_score_gemma":0.000024055247,"teacher_disagreement_score":0.37956885,"about_ca_system_score_codex":0.00041290282,"about_ca_system_score_gemma":0.00027909747,"threshold_uncertainty_score":0.99998915},"labels":[],"label_agreement":null},{"id":"W2141002481","doi":"10.1080/00273170903333590","title":"On the Model-Based Bootstrap With Missing Data: Obtaining a <i>P</i>-Value for a Test of Exact Fit","year":2009,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Science Foundation","keywords":"Goodness of fit; Structural equation modeling; Bootstrapping (finance); Missing data; Covariance; Invertible matrix; Mathematics; Statistics; Applied mathematics; Test statistic; Computer science; Resampling; Covariance matrix; Algorithm; Statistical hypothesis testing; Econometrics; Pure mathematics","score_opus":0.9222058384378413,"score_gpt":0.6512099630886693,"score_spread":0.270995875349172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141002481","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7971844,0.0000731012,0.19562547,0.003406368,0.00009631126,0.0014807879,0.00025489923,0.00006797575,0.0018106535],"genre_scores_gemma":[0.902457,0.0000013533137,0.0971132,0.00011586382,0.00004316265,0.00003488576,0.000009521492,0.000018713203,0.00020630776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939349,0.0009823261,0.0006837457,0.00093383674,0.0026821133,0.00078302145],"domain_scores_gemma":[0.8748834,0.12109804,0.00036469585,0.002338665,0.0011122907,0.00020291099],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026525224,0.00021237963,0.00043014606,0.00069557945,0.0006298576,0.00041471067,0.002596098,0.000118177406,0.000044531138],"category_scores_gemma":[0.14064927,0.00011220949,0.00010036243,0.0026946382,0.0002932762,0.00026605593,0.00022703053,0.0006209342,0.000006626715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027716928,0.0031460333,0.02527013,0.0000321518,0.00003013918,0.000060216244,0.0014146724,0.03595346,0.065192685,0.007445129,0.0063213855,0.85236233],"study_design_scores_gemma":[0.001952943,0.0032134783,0.044423465,0.00023554337,0.000030006886,0.0000039941892,0.000886308,0.9202549,0.0045151077,0.023667831,0.00051613204,0.0003003274],"about_ca_topic_score_codex":0.00025816605,"about_ca_topic_score_gemma":0.000008266986,"teacher_disagreement_score":0.8843014,"about_ca_system_score_codex":0.000065458386,"about_ca_system_score_gemma":0.00046080022,"threshold_uncertainty_score":0.9193166},"labels":[],"label_agreement":null},{"id":"W2142996385","doi":"10.1080/00273171.2010.546731","title":"The Longitudinal Interplay of Adolescents' Self-Esteem and Body Image: A Conditional Autoregressive Latent Trajectory Analysis","year":2011,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Eating Disorders and Behaviors","field":"Psychology","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université de Sherbrooke","funders":"","keywords":"Self-esteem; Psychology; Developmental psychology; Longitudinal study; Autoregressive model; Longitudinal data; Demography; Statistics; Mathematics","score_opus":0.13023069333193568,"score_gpt":0.4511350920320027,"score_spread":0.32090439870006704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142996385","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99833214,0.00019840329,0.0001423828,0.00003096104,0.00017527223,0.0004635164,0.00008114682,0.000051818908,0.00052436604],"genre_scores_gemma":[0.99852264,0.000014443651,0.0005519189,0.0000045349498,0.000033252363,0.00014704939,0.000034003584,0.00002863785,0.0006635402],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99696493,0.0006910404,0.00046380196,0.0005467127,0.000671926,0.0006615759],"domain_scores_gemma":[0.998391,0.0002061153,0.00018525406,0.0005016271,0.00053278345,0.00018326794],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011106138,0.00022146369,0.00033880767,0.00043631607,0.00044543666,0.00007761467,0.00044440475,0.00017540432,0.00096659857],"category_scores_gemma":[0.00005460319,0.00015688002,0.00020637819,0.0005955529,0.00077941763,0.00012001876,0.00022007899,0.0006993394,0.00006040059],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004296896,0.0032472217,0.9819158,0.000019029254,0.0003640511,0.00012538761,0.0068401527,5.0791584e-7,0.004063149,0.0008595303,0.00027888044,0.0018566555],"study_design_scores_gemma":[0.0009589357,0.00067903963,0.995615,0.000041076553,0.00044633498,0.00000882552,0.0015280586,0.000101921316,0.00031331324,0.00010208071,0.000034359873,0.00017104439],"about_ca_topic_score_codex":0.0057956856,"about_ca_topic_score_gemma":0.00042292025,"teacher_disagreement_score":0.013699264,"about_ca_system_score_codex":0.000081856815,"about_ca_system_score_gemma":0.00008744369,"threshold_uncertainty_score":0.99994665},"labels":[],"label_agreement":null},{"id":"W2210755457","doi":"10.1080/00273171.2015.1033510","title":"Reciprocal Markov Modeling of Feedback Mechanisms Between Emotion and Dietary Choice Using Experience-Sampling Data","year":2015,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Mental Health Research Topics","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Dalhousie University","funders":"National Heart, Lung, and Blood Institute","keywords":"Mood; Experience sampling method; Reciprocal; Set (abstract data type); Psychology; Markov chain; Independence (probability theory); Sampling (signal processing); Generalization; Markov model; Computer science; Empirical research; Cognitive psychology; Consumption (sociology); Econometrics; Statistics; Social psychology; Machine learning; Mathematics","score_opus":0.8893287258930511,"score_gpt":0.6465473378346601,"score_spread":0.242781388058391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2210755457","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97588366,0.0001982116,0.021998096,0.00011293499,0.0003333458,0.0009599525,0.00014503721,0.000039758906,0.00032898656],"genre_scores_gemma":[0.96735775,0.00001537616,0.031853106,0.0000088885,0.00023751354,0.000049896098,0.0001712377,0.000051064613,0.0002551518],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946756,0.0011131252,0.0006580322,0.00093295664,0.0015029302,0.0011173906],"domain_scores_gemma":[0.997058,0.00039583346,0.000110068606,0.0012159146,0.00052799535,0.0006922039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050431965,0.00021800425,0.00039766097,0.00038962284,0.00033158934,0.00008251657,0.00094058964,0.0002925304,0.00018919083],"category_scores_gemma":[0.0005883815,0.00021219136,0.000035484958,0.0005697633,0.00027957166,0.0005105069,0.0017019627,0.0010204111,0.000031371685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033707928,0.003291893,0.26402828,0.0006793505,0.00021195361,0.00019867533,0.057771195,0.00078431197,0.052541487,0.0013225944,0.00039821386,0.61540127],"study_design_scores_gemma":[0.009033676,0.0032554313,0.15245129,0.00085957465,0.00016675142,0.000049211594,0.053937003,0.77139425,0.002218731,0.0046577943,0.00066095183,0.0013153336],"about_ca_topic_score_codex":0.031424835,"about_ca_topic_score_gemma":0.00010211715,"teacher_disagreement_score":0.7706099,"about_ca_system_score_codex":0.00032810326,"about_ca_system_score_gemma":0.000258911,"threshold_uncertainty_score":0.975025},"labels":[],"label_agreement":null},{"id":"W2501992360","doi":"10.1080/00273171.2016.1200454","title":"Using Marginal Structural Modeling for Grade Retention Effects","year":2016,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Simon Fraser University; Fordham University","keywords":"Equating; Covariate; Confounding; Propensity score matching; Statistics; Analysis of covariance; Marginal structural model; Econometrics; Missing data; Psychology; Computer science; Mathematics","score_opus":0.8116577974541808,"score_gpt":0.63032002163345,"score_spread":0.18133777582073074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2501992360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57328385,0.000009714624,0.42543882,0.000057503607,0.00008088311,0.000926318,0.000021023881,0.00016333624,0.000018520941],"genre_scores_gemma":[0.7467204,0.0000034355262,0.25270474,0.0000023045902,0.000089697,0.00019779902,0.0000054473658,0.000053984983,0.00022220722],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973812,0.00030241295,0.00035046387,0.00046769518,0.00066685356,0.00083134143],"domain_scores_gemma":[0.9978091,0.00094019703,0.00008646807,0.00043593647,0.0005814821,0.00014679767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013844261,0.00021661779,0.000281446,0.00027342315,0.00034190062,0.00007069901,0.00032340526,0.00019197447,0.000042681397],"category_scores_gemma":[0.0011407434,0.00014942054,0.00011873147,0.00023041993,0.00013626863,0.00045816595,0.00019897328,0.00032993604,0.0000086661],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019549142,0.00010840206,0.0005724303,0.00012631217,0.000012359812,0.00001622927,0.0001731036,0.000020283602,0.93255454,0.046556674,0.00005315394,0.019611012],"study_design_scores_gemma":[0.001727473,0.00051986956,0.00041855176,0.0005417242,0.000055764503,0.0000126990635,0.00008738741,0.08192774,0.13661636,0.7776322,0.00003661941,0.0004236273],"about_ca_topic_score_codex":0.0002977833,"about_ca_topic_score_gemma":0.00001942627,"teacher_disagreement_score":0.7959382,"about_ca_system_score_codex":0.00048741826,"about_ca_system_score_gemma":0.00008043144,"threshold_uncertainty_score":0.60931927},"labels":[],"label_agreement":null},{"id":"W2534977215","doi":"10.1080/00273171.2016.1225563","title":"On the Relationship Between Confidence Sets and Exchangeable Weights in Multiple Linear Regression","year":2016,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Statistics; Linear regression; Regression analysis; Mathematics; Regression; Interpretation (philosophy); Regression diagnostic; Set (abstract data type); Econometrics; Confidence interval; Computer science; Polynomial regression","score_opus":0.7532554752770059,"score_gpt":0.5941128584516712,"score_spread":0.1591426168253347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2534977215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.920071,0.00002243849,0.077812694,0.001095976,0.0000393497,0.0007089367,0.00007313102,0.00003308475,0.00014338669],"genre_scores_gemma":[0.92905164,0.000012100211,0.0696251,0.000009013429,0.000038803333,0.00012266709,0.0000027893004,0.000027629518,0.0011102639],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970283,0.001128203,0.00031364476,0.00041579673,0.0006000591,0.0005140008],"domain_scores_gemma":[0.9650294,0.03416526,0.00006670714,0.0004264962,0.00015808026,0.00015406219],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002975796,0.00015976769,0.00024056066,0.00017367523,0.000354611,0.00003354931,0.0002271216,0.00015254553,0.000088617046],"category_scores_gemma":[0.013425505,0.00007756263,0.000030792566,0.00025368898,0.00027994832,0.0001527617,0.00019419084,0.0005792442,0.000046014502],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003497934,0.000400585,0.14622171,0.00006862739,0.0000074640534,0.00006539334,0.0020806894,0.0000011969942,0.007793349,0.78668964,0.00033882842,0.055982735],"study_design_scores_gemma":[0.0010087051,0.00019391748,0.11590842,0.0006186879,0.000008085927,0.0000011597481,0.000103397346,0.00067967037,0.0019144361,0.87926334,0.00014208158,0.00015812204],"about_ca_topic_score_codex":0.00031950648,"about_ca_topic_score_gemma":0.000084781226,"teacher_disagreement_score":0.092573695,"about_ca_system_score_codex":0.00010846205,"about_ca_system_score_gemma":0.00004206782,"threshold_uncertainty_score":0.99488485},"labels":[],"label_agreement":null},{"id":"W2557900203","doi":"10.1080/00273171.2016.1253452","title":"Estimating Between-Person and Within-Person Subscore Reliability with Profile Analysis","year":2016,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reliability (semiconductor); Strengths and weaknesses; Psychology; Statistics; Reliability engineering; Computer science; Mathematics; Social psychology; Engineering","score_opus":0.7913515426590917,"score_gpt":0.5884301756601152,"score_spread":0.20292136699897645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2557900203","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9698604,0.00003201007,0.02813976,0.00065073225,0.00012758406,0.0005190402,0.00006282978,0.00009196996,0.00051572185],"genre_scores_gemma":[0.8462703,0.0000011230571,0.15242685,0.0000049019386,0.00008904799,0.000053821896,0.0000045216366,0.00002126387,0.001128174],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99144655,0.00224628,0.00066477567,0.0014960583,0.00321968,0.00092665607],"domain_scores_gemma":[0.9576269,0.03859603,0.00039536154,0.0014131991,0.0014829593,0.0004855999],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02596687,0.0002729773,0.0007232703,0.0016648096,0.00067910674,0.00047334918,0.0009480575,0.00018314109,0.00046417062],"category_scores_gemma":[0.06466722,0.00013566973,0.00013929095,0.0076610167,0.0006623157,0.0005332544,0.0002764036,0.00059910724,0.000065970366],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102408005,0.00006885183,0.8418675,0.000005879282,0.000038472554,0.000019349627,0.0008312668,0.00002647054,0.0028841035,0.000038818118,0.0000843638,0.15403253],"study_design_scores_gemma":[0.0008253169,0.00056336704,0.98726916,0.00006622959,0.000119902325,0.000004492709,0.0022781924,0.006397679,0.0011714647,0.0010056543,0.00003530625,0.00026324278],"about_ca_topic_score_codex":0.0024726524,"about_ca_topic_score_gemma":0.00009041718,"teacher_disagreement_score":0.15376928,"about_ca_system_score_codex":0.0001726848,"about_ca_system_score_gemma":0.00014380748,"threshold_uncertainty_score":0.9432115},"labels":[],"label_agreement":null},{"id":"W2801359717","doi":"10.1080/00273171.2019.1614898","title":"Bridge Centrality: A Network Approach to Understanding Comorbidity","year":2019,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Mental Health Research Topics","field":"Psychology","cited_by":1609,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Comorbidity; Betweenness centrality; Bridge (graph theory); Centrality; Psychopathology; Computer science; Psychology; Statistics; Network analysis; Clinical psychology; Psychiatry; Medicine; Mathematics; Engineering","score_opus":0.753763044448797,"score_gpt":0.5947418133457905,"score_spread":0.1590212311030066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801359717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91059273,0.00008852627,0.002814478,0.0011024589,0.0015060302,0.0045062164,0.00008433335,0.0001586053,0.07914664],"genre_scores_gemma":[0.9843332,0.000007699209,0.0017829892,0.00015753855,0.0003746443,0.00031159425,0.00007210816,0.000071410155,0.012888809],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9920586,0.0019772637,0.00048539264,0.0010243244,0.0017132626,0.0027412043],"domain_scores_gemma":[0.99711597,0.00042360296,0.000063145286,0.0011898439,0.00019458059,0.001012828],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0053604813,0.00026297136,0.00041495747,0.00035501705,0.0005076248,0.0001977685,0.0008606362,0.0002842401,0.0031937528],"category_scores_gemma":[0.00009657429,0.00025500337,0.00010873552,0.0013639866,0.00018650579,0.00016894244,0.00070911914,0.0016843008,0.005613073],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002967007,0.006809527,0.45238313,0.00044512167,0.00013737383,0.00029863234,0.014712276,0.00017911292,0.0026024436,0.40841612,0.08466834,0.026380915],"study_design_scores_gemma":[0.0038572934,0.001563677,0.93707836,0.00015386769,0.000019486808,0.00002863136,0.0039756037,0.001070157,0.000118157885,0.0037994396,0.04758433,0.0007510216],"about_ca_topic_score_codex":0.013623719,"about_ca_topic_score_gemma":0.00016361552,"teacher_disagreement_score":0.4846952,"about_ca_system_score_codex":0.0016976086,"about_ca_system_score_gemma":0.00021896699,"threshold_uncertainty_score":0.9999902},"labels":[],"label_agreement":null},{"id":"W2940558384","doi":"10.1080/00273171.2019.1598837","title":"Bayesian Extended Redundancy Analysis: A Bayesian Approach to Component-based Regression with Dimension Reduction","year":2019,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Research Foundation of Korea","keywords":"Computer science; Markov chain Monte Carlo; Frequentist inference; Bayesian probability; Gibbs sampling; Missing data; Statistics; Dimensionality reduction; Bayesian statistics; Posterior probability; Data mining; Econometrics; Artificial intelligence; Mathematics; Machine learning; Bayesian inference","score_opus":0.26606752102610737,"score_gpt":0.512825108832424,"score_spread":0.24675758780631668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940558384","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19190179,0.000012515636,0.80541396,0.00014720096,0.00008020033,0.0016567967,0.000033306602,0.00012054419,0.00063369],"genre_scores_gemma":[0.5391013,8.837173e-7,0.4598985,0.000007160957,0.000026894928,0.00014823682,0.000046569727,0.000050189567,0.00072028633],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945548,0.0012024029,0.00055039756,0.0011550139,0.0015780688,0.0009592776],"domain_scores_gemma":[0.9970601,0.00050787965,0.00015861672,0.0011551557,0.0005799534,0.0005382525],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021301114,0.00037237967,0.0007402429,0.00087745534,0.00037966244,0.000114741,0.0003693433,0.00021197101,0.00015097526],"category_scores_gemma":[0.0003003956,0.0002673624,0.00016612562,0.0019759662,0.00015224775,0.00020659654,0.00018638794,0.0008145416,0.000029193756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014531591,0.019472128,0.0051145544,0.0010604594,0.0008816846,0.00028466756,0.007739856,0.018680204,0.6822259,0.115152,0.0011102683,0.13374668],"study_design_scores_gemma":[0.007934269,0.0042795525,0.012400847,0.0012603935,0.0014147337,0.00003525213,0.0034227741,0.8745185,0.026003761,0.066281185,0.0002939828,0.0021547452],"about_ca_topic_score_codex":0.00049193925,"about_ca_topic_score_gemma":0.000020332069,"teacher_disagreement_score":0.8558383,"about_ca_system_score_codex":0.00030907147,"about_ca_system_score_gemma":0.00014322458,"threshold_uncertainty_score":0.9999779},"labels":[],"label_agreement":null},{"id":"W2965155714","doi":"10.1080/00273171.2019.1633617","title":"Evaluating Equivalence Testing Methods for Measurement Invariance","year":2019,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Equivalence (formal languages); Goodness of fit; Statistics; Mathematics; Type I and type II errors; Sample size determination; Chi-square test; Measurement invariance; Test (biology); Applied mathematics; Econometrics; Structural equation modeling; Discrete mathematics; Confirmatory factor analysis","score_opus":0.9836237612469282,"score_gpt":0.7740472692881768,"score_spread":0.2095764919587514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965155714","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64904815,0.00044547382,0.34047043,0.00039249388,0.0018231509,0.0031044055,0.000018803732,0.00015807794,0.0045390166],"genre_scores_gemma":[0.42879617,0.0000018203573,0.56982756,0.000022706472,0.000103935105,0.00020500604,0.000001170035,0.000026628753,0.0010150154],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9834376,0.0064802356,0.0013093392,0.0016154685,0.005687757,0.0014695941],"domain_scores_gemma":[0.7325107,0.24979226,0.0008715855,0.0029579012,0.01330522,0.00056236004],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19604397,0.00027543312,0.00063048,0.0010390265,0.00070409424,0.0007162992,0.0023419217,0.00019246309,0.0005576227],"category_scores_gemma":[0.58369064,0.00020829983,0.00018961293,0.0054509738,0.00017045919,0.00046916507,0.0010083163,0.00080924964,0.00034864005],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000952273,0.0001167047,0.03614717,0.000018590496,0.0000071294976,0.000001976835,0.00022818604,0.00019698995,0.270252,0.00042035404,0.00015617737,0.6923595],"study_design_scores_gemma":[0.005079351,0.0045272876,0.4588944,0.000535751,0.00006123393,0.000022087479,0.003145099,0.3764821,0.024126159,0.11617714,0.009664318,0.0012850872],"about_ca_topic_score_codex":0.0007656551,"about_ca_topic_score_gemma":0.0000072830317,"teacher_disagreement_score":0.69107443,"about_ca_system_score_codex":0.00038818776,"about_ca_system_score_gemma":0.0005184841,"threshold_uncertainty_score":0.84942204},"labels":[],"label_agreement":null},{"id":"W2974193444","doi":"10.1080/00273171.2019.1664280","title":"Model Selection of Nested and Non-Nested Item Response Models Using Vuong Tests","year":2019,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Nested set model; Item response theory; Context (archaeology); Model selection; Selection (genetic algorithm); Statistical hypothesis testing; Set (abstract data type); Statistical model","score_opus":0.8817116620456461,"score_gpt":0.6364831850108131,"score_spread":0.24522847703483297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974193444","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9821813,0.000038978047,0.01656867,0.000053953056,0.00016366696,0.0006973714,0.00001596715,0.0000445471,0.00023555053],"genre_scores_gemma":[0.9519238,0.0000048552824,0.04687808,0.0000064822366,0.000022920081,0.000015614722,0.0000016524903,0.000028965125,0.0011176161],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925668,0.0025109001,0.00087963237,0.00089488,0.0024253738,0.00072241825],"domain_scores_gemma":[0.96475077,0.031928077,0.0003321795,0.00079138443,0.0019550822,0.00024253716],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023598203,0.00021413754,0.0005464755,0.0019619116,0.0002993428,0.00027211482,0.0007249079,0.00025329698,0.00008136074],"category_scores_gemma":[0.038676556,0.00016707007,0.00009467835,0.005060406,0.00019317897,0.00070238585,0.0005598292,0.00060862646,0.000020159565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012009612,0.00021226937,0.35845974,0.000013086705,0.000007796878,0.00000907324,0.00089285534,0.023872064,0.5989435,0.0000737835,0.000040824085,0.016274063],"study_design_scores_gemma":[0.00064184214,0.00025798587,0.31116483,0.000047646867,0.0000076089223,0.000010468589,0.0005234853,0.6826689,0.002257345,0.002279725,0.0000067581555,0.00013334371],"about_ca_topic_score_codex":0.0018531362,"about_ca_topic_score_gemma":0.000025716565,"teacher_disagreement_score":0.6587969,"about_ca_system_score_codex":0.00014759548,"about_ca_system_score_gemma":0.000323437,"threshold_uncertainty_score":0.9694211},"labels":[],"label_agreement":null},{"id":"W2974998223","doi":"10.1080/00273171.2019.1660605","title":"New Recommendations on the Use of R-Squared Differences in Multilevel Model Comparisons","year":2019,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Set (abstract data type); Mean squared error; Measure (data warehouse); Multilevel model; Computer science; Class (philosophy); Confusion; Data mining; Statistics; Mathematics; Artificial intelligence; Psychology","score_opus":0.8895675119762272,"score_gpt":0.598556855129321,"score_spread":0.2910106568469062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974998223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91486007,0.0000037399902,0.08191853,0.0009828269,0.000058022193,0.0016695551,0.0000923396,0.00010659088,0.00030832668],"genre_scores_gemma":[0.8461451,0.000008022908,0.1517225,0.00001497995,0.000009021197,0.00012451792,0.000010886719,0.000030141704,0.0019348158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973423,0.00052397395,0.0005311266,0.0003664297,0.0007194459,0.00051676197],"domain_scores_gemma":[0.9947316,0.0039047145,0.00014524866,0.0008042339,0.00030621473,0.0001079645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010124882,0.00020190667,0.00039246096,0.00035967078,0.00011292621,0.000071910225,0.0005792105,0.0001539666,0.0004624518],"category_scores_gemma":[0.0010961405,0.0001405288,0.000075156786,0.00045941796,0.00012736456,0.000286912,0.00028006427,0.0009658849,0.00006070297],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084094895,0.0058165663,0.08593088,0.00012944717,0.00006213273,0.000017817883,0.010963871,0.0015445789,0.08654626,0.7056209,0.037178073,0.06534856],"study_design_scores_gemma":[0.003450614,0.0016446717,0.08137008,0.0016649317,0.000051878807,0.0000028401762,0.0028698714,0.5402603,0.042095184,0.3240141,0.0013799479,0.0011955395],"about_ca_topic_score_codex":0.003337477,"about_ca_topic_score_gemma":0.00043624075,"teacher_disagreement_score":0.5387158,"about_ca_system_score_codex":0.00018505403,"about_ca_system_score_gemma":0.00018605358,"threshold_uncertainty_score":0.57305986},"labels":[],"label_agreement":null},{"id":"W2990763132","doi":"10.1080/00273171.2019.1694477","title":"Sparse Extended Redundancy Analysis: Variable Selection via the Exclusive LASSO","year":2019,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Latent variable; Redundancy (engineering); Computer science; Lasso (programming language); Feature selection; Set (abstract data type); Selection (genetic algorithm); Econometrics; Variables; Data mining; Artificial intelligence; Mathematics; Machine learning; Statistics","score_opus":0.19290077209158177,"score_gpt":0.4418091805023224,"score_spread":0.2489084084107406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990763132","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9947808,0.000041766594,0.002129834,0.0005622717,0.00013454747,0.0005788383,0.00004953802,0.00006127116,0.0016611806],"genre_scores_gemma":[0.98902667,0.000007660756,0.005210102,0.000046698668,0.00015785772,0.000057953723,0.00007154155,0.000002555974,0.005418955],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99553525,0.0018712752,0.00036219376,0.00064063206,0.0008621808,0.00072844623],"domain_scores_gemma":[0.9976876,0.0014176021,0.00009862573,0.00020613933,0.0004072886,0.00018279463],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025536993,0.00018868364,0.00038064967,0.000089299174,0.00073981227,0.00023729552,0.000503188,0.00017201323,0.0060342248],"category_scores_gemma":[0.00025989048,0.0000648838,0.00022958443,0.0038150847,0.00013741774,0.00014894956,0.00019820755,0.00066576403,0.00031546678],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021752501,0.0006154267,0.026885733,0.000005054772,0.00023485851,0.000012649861,0.00019101701,0.00021255446,0.8772898,0.007159317,0.00015397568,0.087022126],"study_design_scores_gemma":[0.0003862294,0.0008720361,0.93797505,0.00001783364,0.0005521177,0.0000061507776,0.001045059,0.036987804,0.005866556,0.008570768,0.007299957,0.00042045175],"about_ca_topic_score_codex":0.004478618,"about_ca_topic_score_gemma":0.00052602135,"teacher_disagreement_score":0.9110893,"about_ca_system_score_codex":0.00007789006,"about_ca_system_score_gemma":0.000023317829,"threshold_uncertainty_score":0.9948744},"labels":[],"label_agreement":null},{"id":"W3003574023","doi":"10.1080/00273171.2019.1709405","title":"Different Roles of Prior Distributions in the Single Mediator Model with Latent Variables","year":2020,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute on Drug Abuse","keywords":"Prior probability; Frequentist inference; Bayesian probability; Latent variable; Conjugate prior; Econometrics; Mathematics; Statistics; Bayesian inference; Bayesian statistics; Computer science","score_opus":0.42997985970240477,"score_gpt":0.49058741574929887,"score_spread":0.06060755604689411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003574023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5762245,0.000013218451,0.42177925,0.0009833646,0.0000132461,0.0005973592,0.00025177628,0.000023343853,0.00011394734],"genre_scores_gemma":[0.839123,0.000003953942,0.16069657,0.0000102040085,0.000023458606,0.000102701335,0.000012657247,0.000016069236,0.000011350054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99739736,0.0006390011,0.0003820973,0.0002934511,0.0008434003,0.00044471625],"domain_scores_gemma":[0.99743474,0.0017807651,0.00007731577,0.00030630417,0.00024824787,0.0001526089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010032572,0.00015584183,0.00032299696,0.00007142364,0.0001255226,0.00006378963,0.00044591367,0.0000887049,0.00008255419],"category_scores_gemma":[0.0015295051,0.00008651189,0.000046983358,0.00046057894,0.00023875537,0.00006340819,0.0001590524,0.0005305124,0.0000047005024],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071623974,0.005619465,0.015219897,0.00032097506,0.00004069504,0.0001024182,0.012230431,0.000045917237,0.08798581,0.846724,0.00039345986,0.030600704],"study_design_scores_gemma":[0.0046206373,0.0033355425,0.075288765,0.0006055171,0.0002616398,0.000008531642,0.0037791438,0.11340847,0.043879986,0.75385964,0.0000868112,0.00086532795],"about_ca_topic_score_codex":0.00015787472,"about_ca_topic_score_gemma":0.00009779819,"teacher_disagreement_score":0.26289853,"about_ca_system_score_codex":0.000072880386,"about_ca_system_score_gemma":0.00011363411,"threshold_uncertainty_score":0.35278526},"labels":[],"label_agreement":null},{"id":"W3006236708","doi":"10.1080/00273171.2020.1717922","title":"Improving Fit Indices in Structural Equation Modeling with Categorical Data","year":2020,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":148,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Categorical variable; Structural equation modeling; Estimator; Statistics; Computation; Mathematics; Binary data; Binary number; Econometrics; Algorithm","score_opus":0.9579372916956201,"score_gpt":0.654397403620915,"score_spread":0.3035398880747051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006236708","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9135447,0.000070914255,0.084595546,0.0010805521,0.000106923006,0.00037082765,0.0000244297,0.000049042654,0.00015702781],"genre_scores_gemma":[0.97096545,0.0000027960934,0.028777119,0.000039577608,0.00012607119,0.000016510281,0.000025532147,0.00001832647,0.000028637343],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9930544,0.0013059305,0.0007283404,0.001206503,0.0029753628,0.00072944653],"domain_scores_gemma":[0.98656875,0.01117929,0.00020674296,0.0011146643,0.00060518977,0.00032538493],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011831244,0.00017223303,0.00035832133,0.00076174777,0.00029952644,0.0006149238,0.002501517,0.00013446964,0.00016987498],"category_scores_gemma":[0.06964718,0.00011291899,0.00003262863,0.0048883995,0.000112908194,0.00096877565,0.001553082,0.0010225541,0.000052038522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067476416,0.00014468687,0.4316975,0.000019620767,0.000009979184,0.00021528051,0.004100123,0.0151798725,0.004700505,0.0004509811,0.00016433158,0.54264235],"study_design_scores_gemma":[0.0006825828,0.00024879843,0.047421392,0.0000102586355,0.0000050714157,0.0000036123542,0.0023918964,0.9474733,0.00006214495,0.0015000646,0.00004479162,0.00015609128],"about_ca_topic_score_codex":0.008546857,"about_ca_topic_score_gemma":0.00019638143,"teacher_disagreement_score":0.9322934,"about_ca_system_score_codex":0.00010625362,"about_ca_system_score_gemma":0.00022744178,"threshold_uncertainty_score":0.99805534},"labels":[],"label_agreement":null},{"id":"W3183932977","doi":"10.1080/00273171.2021.1941729","title":"Copula-Based Redundancy Analysis","year":2021,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Copula (linguistics); Computer science; Redundancy (engineering); Regression; Regression analysis; Econometrics; Bivariate analysis; Multivariate statistics; Statistics; Data mining; Machine learning; Mathematics","score_opus":0.2776338551734261,"score_gpt":0.5132476847527523,"score_spread":0.2356138295793262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183932977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808566,0.000639124,0.001090459,0.0003774743,0.000052509833,0.000074454925,0.00010477429,0.0001608277,0.016643772],"genre_scores_gemma":[0.9815495,0.000019255367,0.0025605243,0.000033220753,0.000095031515,0.000055179884,0.00032099712,0.000036231377,0.015330054],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9966883,0.00016264382,0.0003797505,0.0007540543,0.0011559064,0.00085930905],"domain_scores_gemma":[0.9975749,0.00028988713,0.000072733164,0.0009617504,0.0008069477,0.00029374973],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00056160765,0.00022112206,0.00047968712,0.00073981175,0.000398125,0.00021437921,0.0004605722,0.00024860018,0.023817694],"category_scores_gemma":[0.0004508025,0.00021763984,0.00039630348,0.0063329237,0.0001880094,0.00010231126,0.0002061268,0.0008383268,0.00022664154],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012811342,0.0021462515,0.15822022,0.00007936569,0.00069533853,0.0006754447,0.0001992355,0.0001663815,0.8330694,0.0003755912,0.0009174339,0.0033272528],"study_design_scores_gemma":[0.0010671825,0.000049993967,0.018117422,0.000019943185,0.0014535554,0.0000040748637,0.00073991745,0.002255368,0.97206944,0.00015047807,0.0036798643,0.00039275433],"about_ca_topic_score_codex":0.0023680397,"about_ca_topic_score_gemma":0.00021247752,"teacher_disagreement_score":0.14010279,"about_ca_system_score_codex":0.00035791245,"about_ca_system_score_gemma":0.00041661668,"threshold_uncertainty_score":0.9770747},"labels":[],"label_agreement":null},{"id":"W4306691105","doi":"10.1080/00273171.2022.2115965","title":"A Gentle Introduction to Bayesian Network Meta-Analysis Using an Automated R Package","year":2022,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Waterloo; Carleton University","funders":"","keywords":"Computer science; Bayesian probability; Bayesian network; Consistency (knowledge bases); Meta-analysis; Ranking (information retrieval); Rank (graph theory); Data mining; Machine learning; Artificial intelligence; Mathematics; Medicine","score_opus":0.923574189906166,"score_gpt":0.6593108779782532,"score_spread":0.26426331192791286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306691105","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88728917,0.00056447455,0.101505145,0.0043110223,0.00084492296,0.0045253257,0.00036520872,0.00013072458,0.0004640273],"genre_scores_gemma":[0.96104974,6.8296606e-7,0.02661968,0.000093808005,0.00039953442,0.0004989333,0.00009847182,0.00004297155,0.011196194],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.91922945,0.056611203,0.006008905,0.0024516508,0.014620972,0.0010778223],"domain_scores_gemma":[0.98683614,0.00141086,0.0016599495,0.0068590892,0.002547599,0.0006863606],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.23067376,0.0004228023,0.0050166184,0.0026271064,0.0017977454,0.0019855031,0.0033048296,0.00010225234,0.13184232],"category_scores_gemma":[0.0063516255,0.0002485955,0.0043883976,0.019161996,0.00008406569,0.00046400528,0.0013845024,0.00079750636,0.001889755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021885637,0.0029527077,0.019828701,0.000024550338,0.059900533,0.00021687153,0.007547374,0.610333,0.019131562,0.0013524953,0.2698366,0.008656695],"study_design_scores_gemma":[0.00035826454,0.00056784466,0.014313441,0.0000016278007,0.090588644,0.000022915694,0.0050280667,0.82203,0.00015984225,0.001255873,0.06491593,0.00075753854],"about_ca_topic_score_codex":0.0022630594,"about_ca_topic_score_gemma":0.0004615216,"teacher_disagreement_score":0.22432213,"about_ca_system_score_codex":0.00038774332,"about_ca_system_score_gemma":0.00019481045,"threshold_uncertainty_score":0.9999966},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4364353609","doi":"10.1080/00273171.2023.2193600","title":"Pay Attention to the Ignorable Missing Data Mechanisms! An Exploration of Their Impact on the Efficiency of Regression Coefficients","year":2023,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McGill University","funders":"","keywords":"Missing data; Computer science; Regression; Regression analysis; Statistics; Econometrics; Data mining; Mathematics; Machine learning","score_opus":0.6757811365891347,"score_gpt":0.5899222742098614,"score_spread":0.08585886237927332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4364353609","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43296108,0.0000028782385,0.5646417,0.0008901218,0.00011180176,0.0009358644,0.00035979084,0.000036864873,0.000059901322],"genre_scores_gemma":[0.96548784,0.0000042823676,0.034265447,0.0000065370004,0.00002722715,0.000047128557,0.00006624783,0.000025959936,0.000069359034],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959012,0.0016945755,0.00043528783,0.0003996104,0.0011274328,0.00044188043],"domain_scores_gemma":[0.9948632,0.002981401,0.00016220428,0.0014073463,0.00047055146,0.000115304756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008286976,0.00016464309,0.00026626504,0.00022661305,0.00042945938,0.000094525436,0.0010881439,0.00008416306,0.00010584116],"category_scores_gemma":[0.0032566227,0.000064381216,0.000060730577,0.0013263465,0.00014548947,0.00025596865,0.00050823105,0.0003799018,0.000033549975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006483908,0.0025480532,0.00046754783,0.00013641964,0.0000319476,0.000013578686,0.0067868377,0.00009847349,0.54843485,0.1551218,0.0024077748,0.28330433],"study_design_scores_gemma":[0.0010144623,0.0035483423,0.021541242,0.0014742288,0.00008645466,0.000002125683,0.009355864,0.176477,0.13395806,0.6520127,0.00008381795,0.00044570182],"about_ca_topic_score_codex":0.00063269987,"about_ca_topic_score_gemma":0.000020631996,"teacher_disagreement_score":0.53252673,"about_ca_system_score_codex":0.00005828842,"about_ca_system_score_gemma":0.00011705152,"threshold_uncertainty_score":0.3898717},"labels":[],"label_agreement":null},{"id":"W4391785744","doi":"10.1080/00273171.2024.2307034","title":"Correcting for Sampling Error in between-Cluster Effects: An Empirical Bayes Cluster-Mean Approach with Finite Population Corrections","year":2024,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bayes' theorem; Statistics; Cluster (spacecraft); Population; Cluster sampling; Mathematics; Econometrics; Confidence interval; Monte Carlo method; Sample size determination; Computer science; Bayesian probability; Demography","score_opus":0.5093859889745762,"score_gpt":0.5862934565112842,"score_spread":0.07690746753670796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391785744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.345125,0.000009476689,0.65306205,0.000058404214,0.00021335729,0.0012748241,0.00007132493,0.00012163987,0.000063932246],"genre_scores_gemma":[0.55737853,3.0450963e-7,0.44185093,0.0000070201727,0.00015483772,0.00039127545,0.00007871503,0.000057677385,0.00008072322],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960224,0.0011757794,0.00056267163,0.0008031926,0.00062830694,0.0008076221],"domain_scores_gemma":[0.98491347,0.014166251,0.00006643539,0.00036593954,0.0002645035,0.0002233849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035571314,0.0002816195,0.00047483365,0.0005814013,0.00041026715,0.00041265227,0.0002499648,0.00025207756,0.000033650722],"category_scores_gemma":[0.0028822606,0.0002207765,0.00008673348,0.0009958957,0.00012136487,0.00032366582,0.00013319154,0.0011115709,0.000009902297],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011557479,0.002361297,0.22329912,0.002608017,0.00009545772,0.000063577594,0.015839925,0.00033452373,0.0007817191,0.015903143,0.0002436359,0.73731387],"study_design_scores_gemma":[0.0030150625,0.00283197,0.15244499,0.002019646,0.00027023678,0.000032023563,0.0029251634,0.68999153,0.0005002026,0.1447782,0.000120568424,0.0010704086],"about_ca_topic_score_codex":0.0015519586,"about_ca_topic_score_gemma":0.000539536,"teacher_disagreement_score":0.7362434,"about_ca_system_score_codex":0.000325995,"about_ca_system_score_gemma":0.00011882964,"threshold_uncertainty_score":0.9003005},"labels":[],"label_agreement":null},{"id":"W4401671234","doi":"10.1080/00273171.2024.2386686","title":"Equivalence Testing Based Fit Index: Standardized Root Mean Squared Residual","year":2024,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Equivalence (formal languages); Residual; Statistics; Structural equation modeling; Confidence interval; Mathematics; Monte Carlo method; Goodness of fit; Mean squared error; Algorithm; Computer science; Applied mathematics; Discrete mathematics","score_opus":0.8912486649793605,"score_gpt":0.6513070133320435,"score_spread":0.23994165164731696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401671234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96189106,0.00063052453,0.02891869,0.00091951736,0.001335499,0.00084314385,0.00018548689,0.00057208975,0.0047040125],"genre_scores_gemma":[0.961955,0.0000030563583,0.035657633,0.000018709787,0.00029361705,0.00008773198,0.0000069652174,0.000057634345,0.0019196373],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98448575,0.003854087,0.0012618501,0.0017464954,0.007096521,0.0015552965],"domain_scores_gemma":[0.8803643,0.114600584,0.0002059039,0.0016926164,0.0025836197,0.00055295136],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049204096,0.00035464534,0.0006242338,0.002658029,0.0008374203,0.0024281275,0.0022232877,0.00028638207,0.0014547583],"category_scores_gemma":[0.20506056,0.00025922156,0.00021818635,0.011333298,0.00046071256,0.0005850527,0.0009647848,0.0016641399,0.0004204061],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005420629,0.0003642902,0.2044973,0.00006955115,0.000027480988,0.0009014664,0.0012314203,0.00080104574,0.028083669,0.0005202912,0.007933582,0.75502783],"study_design_scores_gemma":[0.0036141442,0.0019760393,0.75216264,0.0010323334,0.00006706421,0.000045959936,0.0033261047,0.1817125,0.006907964,0.027893271,0.019891575,0.0013704436],"about_ca_topic_score_codex":0.0026006692,"about_ca_topic_score_gemma":0.00012288478,"teacher_disagreement_score":0.7536574,"about_ca_system_score_codex":0.00038021177,"about_ca_system_score_gemma":0.00096820144,"threshold_uncertainty_score":0.999986},"labels":[],"label_agreement":null},{"id":"W4406711879","doi":"10.1080/00273171.2024.2444943","title":"Estimated Factor Scores Are Not True Factor Scores","year":2025,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Factor regression model; Statistics; Unobservable; Factor analysis; Linear regression; Latent variable; Regression; Regression analysis; Mathematics; Factor (programming language); Reliability (semiconductor); Latent variable model; Econometrics; Variables; Proper linear model; Bayesian multivariate linear regression; Computer science","score_opus":0.8974028395791328,"score_gpt":0.6651354386211888,"score_spread":0.23226740095794396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406711879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917291,0.00023863386,0.0032797887,0.0010986874,0.0012722334,0.00077398453,0.00027486624,0.00023292685,0.0010998074],"genre_scores_gemma":[0.98323286,0.000032486823,0.011441764,0.00006598146,0.00009522034,0.000085795335,0.000008966539,0.000032874214,0.0050040334],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.989603,0.0024630735,0.0011979407,0.0014833367,0.0038397927,0.001412877],"domain_scores_gemma":[0.9538411,0.04188219,0.0003348568,0.0016121877,0.0019438975,0.00038576405],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0081076715,0.00038953888,0.0008112415,0.0030491028,0.00091375806,0.0012975257,0.0027273928,0.0003572633,0.0018011472],"category_scores_gemma":[0.1849942,0.00027401367,0.00025313842,0.007616877,0.0005223746,0.0004724165,0.0013362044,0.0012799401,0.0004900933],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002593047,0.00035339806,0.63021874,0.000016094802,0.000019702973,0.00007395115,0.00033248006,0.000026293925,0.025452895,0.00032755273,0.0029578581,0.3399617],"study_design_scores_gemma":[0.00092106004,0.00018396514,0.978451,0.00015442727,0.000010350427,0.0000025504219,0.00075733615,0.0021479814,0.0102541465,0.0053150016,0.0015135421,0.00028864737],"about_ca_topic_score_codex":0.004216182,"about_ca_topic_score_gemma":0.00019970468,"teacher_disagreement_score":0.3482322,"about_ca_system_score_codex":0.00026000544,"about_ca_system_score_gemma":0.0003911266,"threshold_uncertainty_score":0.9999712},"labels":[],"label_agreement":null},{"id":"W4409089898","doi":"10.1080/00273171.2025.2443366","title":"Mapping the Garden of Forking Paths in Multilevel Models","year":2025,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Multilevel model; Machine learning","score_opus":0.7429636567015804,"score_gpt":0.5697481756700487,"score_spread":0.17321548103153173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409089898","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94005513,0.00017542491,0.050251912,0.0006882288,0.00023020022,0.00061837735,0.000017433671,0.000025490703,0.007937798],"genre_scores_gemma":[0.99612874,0.000027726264,0.002073028,0.000021914191,0.000014982159,0.00007968096,0.0000034946293,0.000010356204,0.0016400886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99505746,0.00090217614,0.00090437225,0.00052114035,0.0020857255,0.0005291305],"domain_scores_gemma":[0.99585056,0.0022000754,0.00013633158,0.0007582527,0.0009949439,0.00005984814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013630226,0.0001291983,0.0002921896,0.0014134947,0.00030922043,0.00020955518,0.0011784849,0.00013465185,0.00005616142],"category_scores_gemma":[0.001529659,0.00008325095,0.0001300298,0.0026212733,0.00022460199,0.00024556683,0.0004416913,0.00058003946,0.000026082984],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026168505,0.0007666957,0.04748891,0.000031768028,0.000022517768,0.000023994377,0.022646466,0.027478768,0.019341845,0.01427371,0.00075114885,0.8669125],"study_design_scores_gemma":[0.0009398753,0.00005129415,0.08263089,0.00021736852,0.0000067374685,6.952943e-7,0.023627587,0.8114403,0.00046473602,0.07980518,0.00067786593,0.00013748983],"about_ca_topic_score_codex":0.0028989706,"about_ca_topic_score_gemma":0.00038545227,"teacher_disagreement_score":0.866775,"about_ca_system_score_codex":0.00007808774,"about_ca_system_score_gemma":0.00018625024,"threshold_uncertainty_score":0.47239918},"labels":[],"label_agreement":null},{"id":"W4411126428","doi":"10.1080/00273171.2025.2512343","title":"Rnest: An R Package for the Next Eigenvalue Sufficiency Test for Factor Analysis","year":2025,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"R package; Test (biology); Eigenvalues and eigenvectors; Factor (programming language); Statistics; Computer science; Econometrics; Mathematics; Reliability engineering; Programming language; Engineering; Biology","score_opus":0.8971086617303922,"score_gpt":0.674459204693312,"score_spread":0.22264945703708017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411126428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.608094,0.00031172423,0.3861611,0.0012802547,0.00068993645,0.0024392263,0.00044493764,0.000085178624,0.00049366336],"genre_scores_gemma":[0.9690607,0.000014793045,0.024849618,0.000047789774,0.00011961627,0.0005469292,0.000020821348,0.000020338523,0.005319398],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9937738,0.0011586499,0.00089749886,0.0011739203,0.0018944622,0.0011016412],"domain_scores_gemma":[0.8180363,0.17751577,0.00021160136,0.0017880638,0.0022356703,0.00021254482],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.024785232,0.00023695962,0.00056674203,0.0022328363,0.0016842579,0.0013355142,0.0029331977,0.00019828671,0.00031457935],"category_scores_gemma":[0.22480263,0.00013618325,0.000497706,0.012314292,0.0003382308,0.00038385563,0.0004585237,0.00046448183,0.000027675407],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027336317,0.001299436,0.33315217,0.0000178083,0.00013119783,0.000005495803,0.0012357763,0.00018891401,0.023526074,0.003604836,0.0027523257,0.6338126],"study_design_scores_gemma":[0.0010852377,0.0008744159,0.89607066,0.000013577825,0.00025553958,6.8465107e-7,0.0049343766,0.071276926,0.0018443986,0.010587705,0.012770427,0.00028605698],"about_ca_topic_score_codex":0.0015042109,"about_ca_topic_score_gemma":0.00026151814,"teacher_disagreement_score":0.6335265,"about_ca_system_score_codex":0.00013232982,"about_ca_system_score_gemma":0.00031745652,"threshold_uncertainty_score":0.9997012},"labels":[],"label_agreement":null},{"id":"W4414296644","doi":"10.1080/00273171.2025.2551373","title":"Regularized Cross-Sectional Network Modeling with Missing Data: A Comparison of Methods","year":2025,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Mental Health Research Topics","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of the Fraser Valley; McGill University","funders":"","keywords":"Missing data; Covariance; Graphical model; Covariance matrix; Estimation of covariance matrices; Lasso (programming language); Gaussian; Data modeling; Sample (material)","score_opus":0.7826204345838472,"score_gpt":0.7286777603513154,"score_spread":0.05394267423253185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414296644","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72865826,0.0009945383,0.2607148,0.00035884356,0.000935218,0.0017981088,0.00008761418,0.0000988831,0.0063537336],"genre_scores_gemma":[0.82684445,0.0000063251255,0.16856486,0.000019208026,0.00016799194,0.00014820024,0.00015565164,0.000040527993,0.004052814],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928252,0.0029365504,0.000901155,0.00096010644,0.0010854495,0.0012915042],"domain_scores_gemma":[0.9960702,0.0010361633,0.00013747842,0.0016693015,0.0008170362,0.0002698357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010469845,0.00021379489,0.00051987934,0.00046101183,0.0007258664,0.00017127611,0.0012408383,0.00032229442,0.0006527878],"category_scores_gemma":[0.0003732365,0.0001861285,0.00006366887,0.0013925179,0.00050313224,0.00023201115,0.0010666178,0.0016777965,0.000033836688],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007681,0.0031815022,0.77431667,0.00040411833,0.0002428039,0.0000567815,0.0016894634,0.0033639818,0.01157703,0.020147728,0.0019289866,0.17540996],"study_design_scores_gemma":[0.0065168366,0.0010663585,0.43720376,0.00048486458,0.00006160709,0.000013030063,0.0012878667,0.54410684,0.0012296132,0.0032270378,0.004344304,0.00045787115],"about_ca_topic_score_codex":0.00843833,"about_ca_topic_score_gemma":0.00017641274,"teacher_disagreement_score":0.5407429,"about_ca_system_score_codex":0.0003293116,"about_ca_system_score_gemma":0.0006622556,"threshold_uncertainty_score":0.99816453},"labels":[],"label_agreement":null}]}