{"meta":{"query_hash":"5003ca732a82","filters":{"venue":"International Journal of Testing"},"cohort_total":24,"direct_labels_cover":0,"predictions_cover":24,"exported":24,"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/5003ca732a82","api":"https://metacan.xera.ac/api/v1/cohort?venue=International+Journal+of+Testing"},"results":[{"id":"W1966255248","doi":"10.1080/15305050701438058","title":"The Beck Depression Inventory-II: Testing for Measurement Equivalence and Factor Mean Differences Across Hong Kong and American Adolescents","year":2007,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Child and Adolescent Psychosocial and Emotional Development","field":"Psychology","cited_by":68,"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 Ottawa","funders":"","keywords":"Beck Depression Inventory; Psychology; Confirmatory factor analysis; Equivalence (formal languages); Measurement invariance; Clinical psychology; Structural equation modeling; Statistics; Psychiatry; Mathematics","score_opus":0.10692464916155962,"score_gpt":0.36365584791829336,"score_spread":0.2567311987567337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966255248","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":[0.9957341,0.0006210701,0.001341504,0.0005205977,0.0014536177,0.00010615304,0.000007439304,0.0000109523235,0.00020458267],"genre_scores_gemma":[0.9977431,0.000027026439,0.0012764294,0.00015375025,0.00073690416,0.0000017079606,5.6770125e-7,0.00000913053,0.00005137243],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99850047,0.00003503224,0.0004612431,0.0001738001,0.0005652653,0.0002642126],"domain_scores_gemma":[0.9982393,0.00036882612,0.00055255933,0.00004988929,0.0006700638,0.00011938103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009962987,0.00012590003,0.00014513197,0.000055444812,0.00047612475,0.000114723734,0.00025796812,0.000029898727,0.000003297399],"category_scores_gemma":[0.0008506386,0.000085732565,0.000050087005,0.000084094005,0.00014155392,0.00010612044,0.000112103866,0.00018197738,6.175622e-7],"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":[0.00010938498,0.00006882136,0.72412056,0.000012615682,0.000062144056,0.000007684909,0.0013000801,9.998074e-7,0.0017600718,0.000056158122,0.00006232781,0.27243918],"study_design_scores_gemma":[0.0006437299,0.00015569328,0.99575114,0.0011492581,0.000010153957,0.00008753024,0.0011457754,0.000057456265,0.00009501604,0.0005020068,0.00029611253,0.00010613255],"about_ca_topic_score_codex":0.0000574244,"about_ca_topic_score_gemma":0.000059794744,"teacher_disagreement_score":0.27233306,"about_ca_system_score_codex":0.000077356504,"about_ca_system_score_gemma":0.000034668235,"threshold_uncertainty_score":0.36620146},"labels":[],"label_agreement":null},{"id":"W1983043858","doi":"10.1080/15305058.2001.9669474","title":"Illustrating the Use of Nonparametric Regression to Assess Differential Item and Bundle Functioning Among Multiple Groups","year":2001,"lang":"en","type":"article","venue":"International Journal of Testing","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 Alberta","funders":"","keywords":"Nonparametric statistics; Differential item functioning; Bundle; Nonparametric regression; Differential (mechanical device); Statistics; Regression analysis; Regression; Smoothing; Psychology; Mathematics; Econometrics; Item response theory; Psychometrics","score_opus":0.6770030026306908,"score_gpt":0.4656857700680094,"score_spread":0.21131723256268142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983043858","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":[0.8711365,0.0000608335,0.12675805,0.00029911567,0.0014299045,0.00006725309,0.0000023972248,0.000009801714,0.00023615357],"genre_scores_gemma":[0.92053795,0.00000749543,0.07886679,0.000052681855,0.00042810084,0.0000012791326,3.6907682e-7,0.00000779503,0.00009753148],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99645627,0.00034254635,0.0011849359,0.00022628046,0.0016051299,0.00018485003],"domain_scores_gemma":[0.91687363,0.078822,0.0019451951,0.00020962892,0.0020242035,0.00012531999],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033212146,0.00012770396,0.000295468,0.0009484454,0.00019534116,0.0005606475,0.00078881904,0.00005405924,0.000051332405],"category_scores_gemma":[0.34306237,0.000072588104,0.00010922879,0.0017857113,0.00008462518,0.00064887595,0.0002960926,0.00032052948,0.0000016381408],"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":[0.0000552982,0.000040585626,0.8330714,0.0000015495074,0.000030793144,0.000022249362,0.0001307198,0.0043351674,0.0036046784,0.000026178144,0.0001915206,0.15848987],"study_design_scores_gemma":[0.0004288973,0.00022444996,0.92077416,0.00029458647,0.000016870737,0.0004830958,0.00073313684,0.07546449,0.00033140878,0.00079683086,0.00035165928,0.00010040291],"about_ca_topic_score_codex":0.000120001394,"about_ca_topic_score_gemma":0.000014710595,"teacher_disagreement_score":0.33974117,"about_ca_system_score_codex":0.00004678383,"about_ca_system_score_gemma":0.00003778501,"threshold_uncertainty_score":0.6624713},"labels":[],"label_agreement":null},{"id":"W1999798470","doi":"10.1080/15305050701193520","title":"Using Exploratory and Confirmatory Methods to Identify the Cognitive Dimensions In a Large-Scale Science Assessment","year":2007,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":20,"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":"Confirmatory factor analysis; Psychology; Scale (ratio); Item response theory; Cognition; Psychometrics; Measurement invariance; Test validity; Applied psychology; Structural equation modeling; Clinical psychology; Statistics; Mathematics","score_opus":0.13349672751734007,"score_gpt":0.4887037303380774,"score_spread":0.35520700282073736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999798470","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":[0.43109944,0.000041824464,0.56758815,0.0002816699,0.0005237249,0.000048191818,5.3745606e-7,0.0000050268563,0.0004114559],"genre_scores_gemma":[0.71890926,0.0000016871644,0.28039685,0.00061914045,0.00006829686,8.110095e-7,3.360316e-8,0.0000019880706,0.000001928103],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99844706,0.00009525609,0.00037421114,0.00018540196,0.0006613179,0.00023672642],"domain_scores_gemma":[0.997028,0.0011285755,0.00026523686,0.00007922138,0.0013771991,0.0001217543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008387464,0.00007233859,0.0001029588,0.0005455896,0.00021585368,0.0002755904,0.000772516,0.000014737516,0.0000021862763],"category_scores_gemma":[0.0020157362,0.000054907145,0.000028501996,0.00081077946,0.00015166038,0.0011545923,0.0005834643,0.0002190364,0.0000013334843],"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":[0.000022201613,0.00017665386,0.104559354,0.0000063267394,0.00004373527,0.00047067835,0.014622549,0.00049843855,0.5760795,0.0052466774,0.00002387833,0.29825002],"study_design_scores_gemma":[0.0011226429,0.00016481706,0.8114436,0.0012630335,0.000020244037,0.0013437526,0.0148466015,0.14121702,0.023178795,0.0047609597,0.0003101043,0.00032838006],"about_ca_topic_score_codex":0.000012645843,"about_ca_topic_score_gemma":0.000014409028,"teacher_disagreement_score":0.70688426,"about_ca_system_score_codex":0.00013702997,"about_ca_system_score_gemma":0.0003838694,"threshold_uncertainty_score":0.29069442},"labels":[],"label_agreement":null},{"id":"W2025305573","doi":"10.1080/15305050903106859","title":"Uncovering the Psychometric Properties of Scales Measuring Individualist and Collectivist Orientations","year":2009,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Cultural Differences and Values","field":"Psychology","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":"University of Calgary","funders":"","keywords":"Collectivism; Psychology; Individualism; Social psychology; Scale (ratio); Psychometrics; Developmental psychology; Geography; Political science","score_opus":0.2054654203050422,"score_gpt":0.3769399820431952,"score_spread":0.17147456173815298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025305573","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":[0.9956687,0.0007143592,0.00013066914,0.0006449393,0.0004931437,0.00004137046,0.0000032489575,0.0000052509376,0.0022983332],"genre_scores_gemma":[0.998967,0.000012784016,0.00063798117,0.000066331944,0.000197183,9.992967e-7,3.1098511e-7,0.0000029138603,0.00011449665],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99922234,0.000041142812,0.00030559296,0.000064810876,0.00029396053,0.00007217364],"domain_scores_gemma":[0.99898994,0.00016373055,0.0003409382,0.000043007236,0.00043713703,0.00002523028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026298265,0.000059676924,0.000103016246,0.00016607065,0.00008042764,0.0000777671,0.00021563881,0.00001721087,0.000016953962],"category_scores_gemma":[0.0006776754,0.00003492109,0.00004176194,0.00026107568,0.000052235275,0.00012670895,0.000021559525,0.000111119516,8.5687225e-7],"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":[0.00018953044,0.00030398314,0.72936195,0.000018297716,0.0004813231,0.000020426764,0.010624881,0.00054963893,0.03777392,0.0029283452,0.0007467756,0.21700093],"study_design_scores_gemma":[0.000385481,0.00017883914,0.995011,0.00020732466,0.000021116286,0.00027742417,0.0012837469,0.00006398615,0.00084905524,0.0015930079,0.00007365156,0.000055422748],"about_ca_topic_score_codex":0.00008688558,"about_ca_topic_score_gemma":0.000011734197,"teacher_disagreement_score":0.265649,"about_ca_system_score_codex":0.000027378508,"about_ca_system_score_gemma":0.000017994786,"threshold_uncertainty_score":0.14240408},"labels":[],"label_agreement":null},{"id":"W2051773947","doi":"10.1080/15305058.2014.957382","title":"Reading Proficiency and Comparability of Mathematics and Science Scores for Students From English and Non-English Backgrounds: An International Perspective","year":2014,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"School Choice and Performance","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; University of Victoria; University of British Columbia","funders":"","keywords":"Comparability; Reading (process); Mathematics education; Perspective (graphical); Language proficiency; Meaning (existential); English language; Variance (accounting); Psychology; Point (geometry); Mathematics; Linguistics; Accounting","score_opus":0.052396182738244396,"score_gpt":0.40292358747675916,"score_spread":0.35052740473851474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051773947","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":[0.9964788,0.000035707137,0.0007286012,0.0001270986,0.00067011634,0.00009354543,0.000010330427,0.00000693092,0.001848883],"genre_scores_gemma":[0.9793755,0.000030261917,0.0195353,0.00002621357,0.0010194696,0.0000017373139,6.930403e-7,0.0000038388416,0.0000070001443],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998654,0.0000296071,0.00031833514,0.00016125898,0.0007204232,0.00011639424],"domain_scores_gemma":[0.9955992,0.0008543215,0.00040478059,0.00005743732,0.0029860623,0.00009820909],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022797799,0.00006963908,0.00014732342,0.00014309934,0.0002167022,0.00033460886,0.0005180565,0.0000282132,0.0000053935814],"category_scores_gemma":[0.008623614,0.00006247367,0.000020640116,0.00010692543,0.00046936175,0.0013716235,0.00010408627,0.00011376789,9.720587e-8],"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":[0.000028445731,0.00009179992,0.95362866,0.000010831638,0.000027215168,5.7602495e-7,0.039022285,0.000019131676,0.00123285,0.0035760046,0.00000777588,0.0023544345],"study_design_scores_gemma":[0.0012018834,0.00033007225,0.9217174,0.0004913532,0.000034866553,0.000009949336,0.050735686,0.012388794,0.0006059324,0.012176921,0.00014358095,0.00016354657],"about_ca_topic_score_codex":0.00048333817,"about_ca_topic_score_gemma":0.000089579844,"teacher_disagreement_score":0.03191124,"about_ca_system_score_codex":0.00010284321,"about_ca_system_score_gemma":0.00011750727,"threshold_uncertainty_score":0.9997272},"labels":[],"label_agreement":null},{"id":"W2057990449","doi":"10.1080/15305058.2012.738266","title":"Analysis of Sources of Latent Class Differential Item Functioning in International Assessments","year":2013,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Comparability; Differential item functioning; Psychology; Multinomial logistic regression; Latent variable; Item response theory; Latent class model; Logistic regression; Matching (statistics); Statistics; Construct validity; Linear discriminant analysis; Construct (python library); Psychometrics; Developmental psychology; Mathematics; Computer science","score_opus":0.3977077293797573,"score_gpt":0.4811063293577611,"score_spread":0.0833985999780038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057990449","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":[0.9718423,0.00005057207,0.024058659,0.00025457962,0.0018196958,0.000044885695,0.0000077696595,0.000005119118,0.0019164149],"genre_scores_gemma":[0.9781033,0.0000073109377,0.021568915,0.000029082668,0.00017601046,0.0000015347629,0.0000021173923,0.0000053267786,0.00010641335],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99525434,0.00023717567,0.0020050895,0.000201664,0.0021543119,0.00014739647],"domain_scores_gemma":[0.9767593,0.016732357,0.0031208722,0.00016297335,0.003159693,0.00006479948],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031472372,0.000110754874,0.00050391286,0.0032907226,0.00002817976,0.00016748132,0.0012852388,0.000055075285,0.0008488807],"category_scores_gemma":[0.05684236,0.00008179507,0.00028890753,0.00214768,0.00006205502,0.0005049806,0.00022936735,0.0002292393,0.000003586134],"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":[0.000030405188,0.000096807795,0.881137,0.0000017983679,0.0005914421,0.000008961999,0.00011284593,0.014264387,0.004447816,0.00005694803,0.00005738668,0.09919418],"study_design_scores_gemma":[0.00043154223,0.000088400164,0.88697344,0.00009615309,0.00007016002,0.000025360134,0.00042478865,0.10971614,0.00037440506,0.0016998878,0.000037328424,0.000062378305],"about_ca_topic_score_codex":0.0002839933,"about_ca_topic_score_gemma":0.0000109987695,"teacher_disagreement_score":0.0991318,"about_ca_system_score_codex":0.00008945358,"about_ca_system_score_gemma":0.00006620961,"threshold_uncertainty_score":0.95110226},"labels":[],"label_agreement":null},{"id":"W2058922083","doi":"10.1080/15305058.2014.891223","title":"Uncovering Substantive Patterns in Student Responses in International Large-Scale Assessments—Comparing a Latent Class to a Manifest DIF Approach","year":2014,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":19,"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":"Generalizability theory; Differential item functioning; Psychology; Item response theory; Latent class model; Homogeneous; Contrast (vision); Homogeneity (statistics); Reading comprehension; Cognitive psychology; Scale (ratio); Comprehension; Social psychology; Psychometrics; Developmental psychology; Reading (process); Statistics; Mathematics","score_opus":0.3759875606329405,"score_gpt":0.4999896769691466,"score_spread":0.12400211633620611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058922083","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":[0.90678924,0.000022644332,0.086315356,0.00042429694,0.001872557,0.00011169525,0.000008516719,0.000013282709,0.0044424087],"genre_scores_gemma":[0.92774874,0.0000058080573,0.07160754,0.00019187233,0.0003485806,0.000007057259,0.0000015024814,0.000013539817,0.000075389005],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99435747,0.00062218227,0.0017431444,0.00044233515,0.0024685673,0.00036631883],"domain_scores_gemma":[0.9848703,0.012649115,0.0011077729,0.00023178157,0.0010054666,0.00013553577],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012712886,0.00019157513,0.00047770495,0.0022687383,0.00005397756,0.0004898458,0.0020607593,0.0000604468,0.000051557974],"category_scores_gemma":[0.049568377,0.00015665819,0.00012394683,0.001241185,0.000022012522,0.00053373934,0.0006443435,0.00050949963,0.000009028298],"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":[0.0001725475,0.00027019173,0.94519216,0.000002883766,0.000038578648,0.00013122566,0.00095048884,0.03054462,0.00055263005,0.00013582385,0.000027909948,0.02198095],"study_design_scores_gemma":[0.0013200036,0.00014345637,0.93478227,0.00035143315,0.000004739696,0.00016922066,0.0027290904,0.058445778,0.00006666108,0.0014927685,0.0003381016,0.00015647362],"about_ca_topic_score_codex":0.00012362446,"about_ca_topic_score_gemma":0.00018023228,"teacher_disagreement_score":0.036855493,"about_ca_system_score_codex":0.00046808907,"about_ca_system_score_gemma":0.00007811494,"threshold_uncertainty_score":0.9584375},"labels":[],"label_agreement":null},{"id":"W2063611796","doi":"10.1080/15305058.2011.617475","title":"Methodologies for Investigating Item- and Test-Level Measurement Equivalence in International Large-Scale Assessments","year":2012,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Differential item functioning; Comparability; Psychology; Item response theory; Equivalence (formal languages); Statistics; Nonparametric statistics; Test (biology); Psychometrics; Consistency (knowledge bases); Item analysis; Logistic regression; Mathematics","score_opus":0.84777911019985,"score_gpt":0.5833143230805201,"score_spread":0.26446478711932986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063611796","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":[0.68800366,0.0007646934,0.30237707,0.0016906849,0.0050249035,0.0001876176,0.000044624445,0.000024650084,0.0018821089],"genre_scores_gemma":[0.52843344,0.000012644574,0.4708877,0.00016394928,0.00045100105,0.000005564054,6.2369355e-7,0.000007271503,0.000037800193],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9949619,0.00041222115,0.0015182747,0.00028387652,0.002419526,0.00040415738],"domain_scores_gemma":[0.8772222,0.11575153,0.0024265216,0.00023604,0.004127027,0.0002367326],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034230035,0.00016995177,0.00037775436,0.0009512466,0.000099104014,0.0002991174,0.0013203663,0.00007479876,0.0000382111],"category_scores_gemma":[0.6310325,0.00013069958,0.000112794805,0.00064823293,0.000077699246,0.0010896659,0.00042335707,0.000315677,0.0000024373123],"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":[0.000023704535,0.00008440615,0.83637863,0.0000060620337,0.000041106632,0.000005538834,0.00038438942,0.00015817079,0.0069586583,0.0001928567,0.00032408323,0.15544239],"study_design_scores_gemma":[0.0013852279,0.00020991372,0.9500422,0.00040519956,0.000019863115,0.0003014881,0.0028683655,0.012280847,0.001264212,0.02952302,0.0014813254,0.00021833488],"about_ca_topic_score_codex":0.000020930825,"about_ca_topic_score_gemma":0.000007369788,"teacher_disagreement_score":0.59680253,"about_ca_system_score_codex":0.00022632239,"about_ca_system_score_gemma":0.00012604576,"threshold_uncertainty_score":0.9944634},"labels":[],"label_agreement":null},{"id":"W2076222948","doi":"10.1080/15305058.2010.509554","title":"Using the Attribute Hierarchy Method to Make Diagnostic Inferences about Examinees’ Knowledge and Skills in Mathematics: An Operational Implementation of Cognitive Diagnostic Assessment","year":2010,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Advanced Education; University of Alberta","funders":"","keywords":"Cognition; Hierarchy; Set (abstract data type); Item response theory; Test (biology); Computer science; Computerized adaptive testing; Psychology; Psychometrics; Artificial intelligence; Mathematics education; Developmental psychology","score_opus":0.0804734892655436,"score_gpt":0.4593924747952735,"score_spread":0.3789189855297299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076222948","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":[0.9216115,0.000029858189,0.077132754,0.0002368769,0.00018958039,0.00035081943,0.000041442116,0.0000065461336,0.00040060375],"genre_scores_gemma":[0.71850383,0.0000063888624,0.28125206,0.0000595543,0.00013785111,0.000014846903,0.000005870912,0.000011248064,0.000008382012],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997999,0.00015236675,0.00095843157,0.00015716442,0.00055970345,0.00017332705],"domain_scores_gemma":[0.96771324,0.030246362,0.0005387815,0.000075588396,0.0013189213,0.0001071119],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019037172,0.00016749742,0.00031653847,0.00028011185,0.00007887088,0.00011519193,0.00031613433,0.00004513674,0.0001267867],"category_scores_gemma":[0.022143928,0.000120183475,0.000050858056,0.0002162159,0.00007663352,0.00029871063,0.00019036344,0.00031401982,0.000001887382],"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":[0.00004551155,0.0036819961,0.5980329,0.0002745439,0.0006712045,0.00021644484,0.025385663,0.00015689734,0.030097792,0.052806754,0.00008702031,0.28854328],"study_design_scores_gemma":[0.0020925887,0.00053421647,0.78319234,0.0032751367,0.00017288748,0.00067347777,0.0069404477,0.0038769352,0.012222408,0.1866129,0.000017866698,0.00038876955],"about_ca_topic_score_codex":0.000056452805,"about_ca_topic_score_gemma":0.00030925803,"teacher_disagreement_score":0.2881545,"about_ca_system_score_codex":0.0000755612,"about_ca_system_score_gemma":0.00024152514,"threshold_uncertainty_score":0.986093},"labels":[],"label_agreement":null},{"id":"W2086483769","doi":"10.1080/15305058.2011.552748","title":"Teachers' Perceptions of Large-Scale Assessment Programs Within Low-Stakes Accountability Frameworks","year":2011,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Educational Assessment and Improvement","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre for Advancing Health Outcomes; University of Alberta; Queen's University","funders":"","keywords":"Accountability; Seriousness; Scale (ratio); Perception; Psychology; Standardized test; Educational assessment; Medical education; Pedagogy; Mathematics education; Political science; Geography; Medicine","score_opus":0.15653966944316988,"score_gpt":0.4547954859236611,"score_spread":0.2982558164804912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086483769","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":[0.97330576,0.000019440424,0.020552495,0.00065417204,0.0015711397,0.00011916294,0.000014584852,0.000010730989,0.0037525077],"genre_scores_gemma":[0.8541455,0.0000015856457,0.14521055,0.00014019357,0.0003119141,0.000006120892,0.000004076792,0.0000075127855,0.00017253327],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995809,0.00013432332,0.0014597554,0.0002205616,0.0021996477,0.000176694],"domain_scores_gemma":[0.9935382,0.00081078167,0.0016045831,0.00023464975,0.0037008286,0.000110937246],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0044126012,0.00012922255,0.0002556754,0.00027781233,0.000086882974,0.00018239944,0.0011692533,0.00009539515,0.0010521528],"category_scores_gemma":[0.0026610934,0.000094193456,0.00018732039,0.00033044146,0.000109431545,0.00077759527,0.00014530552,0.00056563085,0.000014530182],"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":[0.000024312738,0.001204979,0.95246756,0.0000037478826,0.00007983964,0.0000036558438,0.007977939,0.00009605121,0.0018915292,0.00060707895,0.00042573357,0.035217553],"study_design_scores_gemma":[0.0005354072,0.00040762112,0.9347942,0.0002473034,0.00003339819,0.00004529777,0.038697507,0.0024248334,0.00056040485,0.02169471,0.0004015026,0.00015780592],"about_ca_topic_score_codex":0.00007326438,"about_ca_topic_score_gemma":0.000049934177,"teacher_disagreement_score":0.124658056,"about_ca_system_score_codex":0.00018482798,"about_ca_system_score_gemma":0.00043092045,"threshold_uncertainty_score":0.999861},"labels":[],"label_agreement":null},{"id":"W2089954256","doi":"10.1080/15305058.2010.501536","title":"Evaluating the Bookmark Standard Setting Method: The Impact of Random Item Ordering","year":2011,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Licensure; Assertion; Test (biology); Computer science; Psychology; Process (computing); Mathematics education; Statistics; Medical education; Mathematics; Medicine; Programming language","score_opus":0.7272170666147368,"score_gpt":0.606127092720526,"score_spread":0.12108997389421083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089954256","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":[0.8057243,0.00045163656,0.18249679,0.00046954173,0.0013607648,0.00013886702,0.000007998587,0.000014594683,0.009335478],"genre_scores_gemma":[0.6995415,0.0000053303684,0.30000323,0.000054463544,0.0003431174,0.0000015240256,1.0788308e-7,0.000009296701,0.00004138342],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99372035,0.0015421819,0.0018065242,0.00020830345,0.002471321,0.00025131393],"domain_scores_gemma":[0.7766666,0.2104888,0.005999786,0.00058245886,0.006142882,0.00011947806],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0506505,0.00015641401,0.00041189263,0.00044514716,0.00023942743,0.00023922761,0.0024476731,0.0000425364,0.00028295448],"category_scores_gemma":[0.45426464,0.00006730375,0.00041498992,0.0010755114,0.0001106196,0.0003514488,0.00033821655,0.00046850878,0.0000030919248],"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":[0.0005028751,0.000026477017,0.2080978,0.000002548917,0.00028168832,0.000024219327,0.0020535812,0.012706206,0.0058443192,0.00010803618,0.00048300804,0.76986927],"study_design_scores_gemma":[0.0044464637,0.0023330096,0.5941211,0.00080883456,0.00015969295,0.0028774922,0.006850333,0.2586156,0.0044391057,0.12455568,0.00036518832,0.0004274721],"about_ca_topic_score_codex":0.00021175206,"about_ca_topic_score_gemma":0.0000019025629,"teacher_disagreement_score":0.7694418,"about_ca_system_score_codex":0.00009901107,"about_ca_system_score_gemma":0.00027042834,"threshold_uncertainty_score":0.9775551},"labels":[],"label_agreement":null},{"id":"W2113879845","doi":"10.1080/15305058.2012.690140","title":"Investigating Sources of Differential Item Functioning in International Large-Scale Assessments Using a Confirmatory Approach","year":2013,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Differential item functioning; Psychology; Equivalence (formal languages); Measurement invariance; Scale (ratio); Item response theory; Pairwise comparison; Cognition; Psychometrics; Differential (mechanical device); Confirmatory factor analysis; Clinical psychology; Developmental psychology; Social psychology; Statistics; Structural equation modeling","score_opus":0.1081283061996754,"score_gpt":0.4028085569126335,"score_spread":0.2946802507129581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113879845","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":[0.9762044,0.000061360995,0.007825714,0.00021831466,0.003229065,0.00011153347,0.000011099944,0.0000122317515,0.012326266],"genre_scores_gemma":[0.96766365,0.000001545708,0.031167986,0.00021128955,0.0007186123,0.000013253881,0.000013552778,0.000015376094,0.00019474508],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99763227,0.00016441889,0.0010500607,0.00021808599,0.0006995623,0.00023559733],"domain_scores_gemma":[0.99719703,0.00052110985,0.001192564,0.00010125313,0.0008863432,0.000101683814],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005426865,0.00015928791,0.00026797937,0.0004102665,0.000057311343,0.000101194004,0.0006016135,0.00009568985,0.0014830845],"category_scores_gemma":[0.00040999646,0.00014022253,0.00011306686,0.0002157831,0.00007873706,0.00043415464,0.00010971581,0.00042816057,0.000015525084],"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":[0.00003079099,0.00082295126,0.9822505,0.000012426717,0.00026787206,0.000012757721,0.0016510097,0.0008305908,0.008220622,0.0006127974,0.00024082525,0.0050468156],"study_design_scores_gemma":[0.001775918,0.00012394912,0.96841717,0.00035536848,0.000027013397,0.00040909284,0.006223802,0.020412732,0.00014248204,0.0017436596,0.00017837802,0.0001904236],"about_ca_topic_score_codex":0.0002448435,"about_ca_topic_score_gemma":0.0000024024596,"teacher_disagreement_score":0.023342272,"about_ca_system_score_codex":0.00013293269,"about_ca_system_score_gemma":0.00009565746,"threshold_uncertainty_score":0.9994297},"labels":[],"label_agreement":null},{"id":"W2119846802","doi":"10.1080/15305058.2014.976865","title":"Impact of Inclusion of Varying Percentages of Repeaters on Equating","year":2015,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"School Choice and Performance","field":"Social 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":"Centre for Advancing Health Outcomes; University of Alberta","funders":"","keywords":"Equating; Statistics; Representativeness heuristic; Population; Sample (material); Psychology; Mathematics; Demography; Econometrics; Chemistry","score_opus":0.13508841521482362,"score_gpt":0.43790685740107455,"score_spread":0.3028184421862509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119846802","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":[0.9928899,0.000054113232,0.00007607526,0.00018575236,0.00031902132,0.000023214554,0.0000034274524,0.0000029911228,0.006445519],"genre_scores_gemma":[0.9971341,0.00001557391,0.0024129413,0.000018865474,0.00039404383,1.2710937e-7,5.5814314e-7,0.0000037561558,0.00002002193],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984651,0.00006917466,0.00047369988,0.000048315243,0.0008588582,0.00008481293],"domain_scores_gemma":[0.9972957,0.00045131828,0.0009989538,0.0000475302,0.0011456347,0.00006087114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014565942,0.000049469283,0.00014220658,0.00017040609,0.00006479395,0.000012128932,0.0003508331,0.000028456825,0.000030744595],"category_scores_gemma":[0.004038692,0.00003954358,0.00009488443,0.00013224148,0.00005921013,0.00030465983,0.00010886316,0.00011462698,7.6806674e-7],"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":[0.00017248066,0.00009232168,0.9150168,0.000013232919,0.00008222034,0.000012667221,0.018480767,0.009972522,0.034984272,0.00008623977,0.00013186052,0.020954633],"study_design_scores_gemma":[0.006498565,0.0062181805,0.872264,0.010801856,0.00016203526,0.00021528148,0.01968079,0.015507445,0.060304053,0.0072884653,0.0003861577,0.000673145],"about_ca_topic_score_codex":0.0018657616,"about_ca_topic_score_gemma":0.00001762389,"teacher_disagreement_score":0.04275276,"about_ca_system_score_codex":0.0001557491,"about_ca_system_score_gemma":0.00029130763,"threshold_uncertainty_score":0.4834983},"labels":[],"label_agreement":null},{"id":"W2126572511","doi":"10.1207/s15327574ijt0403_1","title":"Validating the Beck Depression Inventory-II for Hong Kong Community Adolescents","year":2004,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Child and Adolescent Psychosocial and Emotional Development","field":"Psychology","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Confirmatory factor analysis; Beck Depression Inventory; Structural equation modeling; Exploratory factor analysis; Clinical psychology; Internal consistency; Depression (economics); Psychometrics; Developmental psychology; Psychiatry; Anxiety; Statistics; Mathematics","score_opus":0.08080420797592054,"score_gpt":0.3520861026986411,"score_spread":0.2712818947227206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126572511","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":[0.9880078,0.000143137,0.0029371765,0.002367306,0.003918729,0.00012562312,0.000007744297,0.000016583128,0.0024759239],"genre_scores_gemma":[0.9956763,0.0000042654656,0.0018837934,0.0008302392,0.0014125647,0.0000032065868,0.0000069968364,0.00001209953,0.00017053993],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99880916,0.00009078533,0.00046556478,0.0000920369,0.00037533825,0.00016710882],"domain_scores_gemma":[0.9987196,0.0001430873,0.0004888257,0.00009205696,0.00049234723,0.00006408704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077779253,0.00010648866,0.00012190093,0.0000805428,0.0005307435,0.00006273699,0.0005875397,0.000046306108,0.000037814563],"category_scores_gemma":[0.00052631256,0.00007491035,0.00013766895,0.00008796711,0.000042790016,0.00013362482,0.00011780126,0.00042888752,0.0000087900735],"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":[0.00057361956,0.0025325015,0.7958207,0.00009302758,0.0006980319,0.000070721144,0.014671519,0.0021700696,0.00623008,0.0048053823,0.007904283,0.16443007],"study_design_scores_gemma":[0.0040160543,0.0002193157,0.9679355,0.0038962516,0.000044227214,0.00037782348,0.0018768712,0.00006621151,0.0006035228,0.017325459,0.0034035984,0.00023515822],"about_ca_topic_score_codex":0.00012253936,"about_ca_topic_score_gemma":0.000012489233,"teacher_disagreement_score":0.17211482,"about_ca_system_score_codex":0.00013005201,"about_ca_system_score_gemma":0.00007318931,"threshold_uncertainty_score":0.40821037},"labels":[],"label_agreement":null},{"id":"W2135248568","doi":"10.1080/15305058.2011.602810","title":"A Generalized Logistic Regression Procedure to Detect Differential Item Functioning Among Multiple Groups","year":2011,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Differential item functioning; Logistic regression; Completeness (order theory); Statistics; Item response theory; Mathematics; Set (abstract data type); Extension (predicate logic); Differential (mechanical device); Flexibility (engineering); Regression; Psychology; Psychometrics; Computer science","score_opus":0.548040852468272,"score_gpt":0.4478112341211973,"score_spread":0.10022961834707478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135248568","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":[0.8289563,0.000066762244,0.16658586,0.00010946088,0.0030281395,0.00008221934,0.0000027888507,0.000032789252,0.0011356511],"genre_scores_gemma":[0.8323534,0.0000023173625,0.16668299,0.00007861635,0.00072495337,0.0000037679613,5.432254e-7,0.0000124228145,0.00014097495],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961699,0.0002917955,0.0012588196,0.00033492883,0.001682195,0.000262326],"domain_scores_gemma":[0.9804429,0.015135385,0.0017308876,0.00023581955,0.0022291304,0.00022587612],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028129905,0.0001768094,0.0003556771,0.0010322854,0.0001635482,0.0002770731,0.0013288374,0.000077884135,0.00031502038],"category_scores_gemma":[0.32235733,0.00011521476,0.0001832548,0.0010275469,0.00005735019,0.0004053769,0.00029143353,0.00033149484,0.000021159301],"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":[0.00030068308,0.000054029024,0.8231879,0.0000039783554,0.000070541,0.00018262275,0.0005064168,0.00071689766,0.01062423,0.00006699181,0.00089348847,0.16339225],"study_design_scores_gemma":[0.000992294,0.0003728979,0.9672252,0.00039333326,0.000026856287,0.0007037269,0.00039646158,0.015205227,0.001952559,0.012351519,0.00016703394,0.00021290402],"about_ca_topic_score_codex":0.00007911449,"about_ca_topic_score_gemma":0.00001430183,"teacher_disagreement_score":0.31954435,"about_ca_system_score_codex":0.00009156694,"about_ca_system_score_gemma":0.0000695466,"threshold_uncertainty_score":0.68335074},"labels":[],"label_agreement":null},{"id":"W2137207467","doi":"10.1080/15305058.2014.977444","title":"Explore the Usefulness of Person-Fit Analysis on Large-Scale Assessment","year":2014,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Mental Health Research Topics","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":true,"ca_institutions":"Centre for Health Evaluation and Outcome Sciences; University of Alberta","funders":"","keywords":"Item response theory; Scale (ratio); Psychology; Econometrics; Statistics; Psychometrics; Developmental psychology; Mathematics","score_opus":0.29003612976753645,"score_gpt":0.48466932499598236,"score_spread":0.1946331952284459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137207467","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":[0.9718126,0.000035145637,0.008321088,0.003216991,0.0010053907,0.0000713212,0.000011274122,0.000006269771,0.015519895],"genre_scores_gemma":[0.99587536,0.0000019706329,0.0029023958,0.00034819197,0.0005130898,0.0000056731324,0.0000023169302,0.000008338189,0.0003426828],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99810123,0.00027502468,0.00044484358,0.000111500565,0.00088090776,0.00018647671],"domain_scores_gemma":[0.9974274,0.0011514197,0.00056763587,0.0001753901,0.0005962552,0.00008187839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019249974,0.000076551034,0.00019421172,0.00030068663,0.00007215852,0.000030594823,0.0005971738,0.000035182395,0.0006824856],"category_scores_gemma":[0.000610082,0.000051365092,0.00014561189,0.0002744756,0.00004367925,0.000074290576,0.00005530899,0.00036931888,0.000016938615],"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":[0.00029534832,0.0011403366,0.8452838,0.000045394678,0.0024342134,0.00012123313,0.008144482,0.0037685705,0.00063424313,0.01166414,0.0032796073,0.1231886],"study_design_scores_gemma":[0.0015629489,0.00089102756,0.96134424,0.00024071346,0.00017552052,0.00012600451,0.007283838,0.02326134,0.00044897012,0.0007441327,0.0037864065,0.0001348319],"about_ca_topic_score_codex":0.00007594217,"about_ca_topic_score_gemma":0.00001998269,"teacher_disagreement_score":0.123053774,"about_ca_system_score_codex":0.00012419242,"about_ca_system_score_gemma":0.000057171575,"threshold_uncertainty_score":0.74727386},"labels":[],"label_agreement":null},{"id":"W2142413505","doi":"10.1080/15305058.2011.635830","title":"The Role of Item Models in Automatic Item Generation","year":2012,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":73,"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":"Computer science; Item bank; Item response theory; Field (mathematics); Process (computing); Task (project management); Item analysis; Artificial intelligence; Machine learning; Psychometrics; Psychology","score_opus":0.055843275432405984,"score_gpt":0.2802359057096199,"score_spread":0.22439263027721396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142413505","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":[0.76094747,0.0017639762,0.23304608,0.00022316734,0.001914477,0.000056221128,3.4184234e-7,0.000016337875,0.0020319219],"genre_scores_gemma":[0.9800276,0.0000064503133,0.019309228,0.00001579494,0.0005468738,0.0000010110347,1.1104384e-7,0.0000037480713,0.000089191155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884784,0.00007309751,0.00048805913,0.000052001316,0.00041313845,0.00012584944],"domain_scores_gemma":[0.9982786,0.000619226,0.0005416789,0.00007565037,0.00045336198,0.000031439926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011233655,0.0000549732,0.000090847476,0.00012105652,0.00004866486,0.0000937959,0.000565279,0.000019374746,0.0000015227592],"category_scores_gemma":[0.00080673205,0.000038633396,0.000046547426,0.000110031775,0.000009873956,0.0007630216,0.000076153476,0.00013552186,0.0000025852446],"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":[0.000005637917,0.00010253866,0.11813102,0.000009463947,0.000085603024,0.000017073042,0.004145116,0.063904524,0.03249722,0.33087716,0.00004594932,0.4501787],"study_design_scores_gemma":[0.000101048005,0.000036170088,0.0066870474,0.00022248788,0.0000022508743,0.0001477198,0.00017201086,0.9844022,0.004600285,0.0022453866,0.0013285383,0.00005486505],"about_ca_topic_score_codex":0.00003488693,"about_ca_topic_score_gemma":0.0000018583352,"teacher_disagreement_score":0.92049766,"about_ca_system_score_codex":0.00008477976,"about_ca_system_score_gemma":0.000046945206,"threshold_uncertainty_score":0.15754242},"labels":[],"label_agreement":null},{"id":"W2266762729","doi":"10.1080/15305058.2015.1057826","title":"Developing a Validity Argument Through Abductive Reasoning with an Empirical Demonstration of the Latent Class Analysis","year":2015,"lang":"en","type":"article","venue":"International Journal of Testing","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":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Abductive reasoning; Test (biology); Argument (complex analysis); Psychology; Class (philosophy); Empirical research; Computer science; Latent class model; Cognitive psychology; Empirical evidence; Artificial intelligence; Social psychology; Mathematics education; Natural language processing; Machine learning; Epistemology","score_opus":0.7377369571260765,"score_gpt":0.5358460428535601,"score_spread":0.20189091427251638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2266762729","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":[0.70365393,0.000030531955,0.2938888,0.0011170671,0.0004894002,0.00003831409,0.0000020837351,0.000005969108,0.00077389926],"genre_scores_gemma":[0.66980857,0.0000013003057,0.32995617,0.00007730206,0.00014090553,6.081061e-7,4.063648e-7,0.000003173852,0.000011540355],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99571246,0.0006047211,0.0009970593,0.00021078026,0.0023364963,0.00013845856],"domain_scores_gemma":[0.9865242,0.0068156,0.002148016,0.00021623728,0.004211663,0.000084274136],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0072150584,0.000105304,0.0003173408,0.00041489367,0.00008865364,0.0001709959,0.0010287695,0.00004207063,0.000010921301],"category_scores_gemma":[0.06794868,0.000055959455,0.00014781805,0.0024258564,0.00009148374,0.00059303537,0.00014507248,0.00023052856,9.078845e-7],"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":[0.00007231005,0.00004794783,0.9649629,7.471823e-7,0.00025290743,0.00001551817,0.0006857917,0.02209044,0.0001310376,0.00064773456,0.000061950865,0.0110307],"study_design_scores_gemma":[0.00066381507,0.00048556982,0.9168498,0.00018386656,0.00021191635,0.00046632014,0.0029609806,0.030746283,0.0015150458,0.045554776,0.00020324934,0.0001583927],"about_ca_topic_score_codex":0.000076640776,"about_ca_topic_score_gemma":0.000022850389,"teacher_disagreement_score":0.060733616,"about_ca_system_score_codex":0.00020797715,"about_ca_system_score_gemma":0.00040928074,"threshold_uncertainty_score":0.93990237},"labels":[],"label_agreement":null},{"id":"W2956918498","doi":"10.1080/15305058.2019.1632316","title":"Migration Background in PISA’s Measure of Social Belonging: Using a Diffractive Lens to Interpret Multi-Method DIF Studies","year":2019,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Intergenerational and Educational Inequality Studies","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Ordered logit; Differential item functioning; Logistic regression; Immigration; Measure (data warehouse); Psychology; Through-the-lens metering; Econometrics; Social psychology; Measurement invariance; Differential (mechanical device); Item response theory; Lens (geology); Psychometrics; Statistics; Structural equation modeling; Computer science; Mathematics; Geography; Developmental psychology; Confirmatory factor analysis; Data mining","score_opus":0.2921427318247282,"score_gpt":0.5026481723540723,"score_spread":0.2105054405293441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956918498","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":[0.9861232,0.00015183965,0.004579548,0.0060682236,0.0014707642,0.00013250954,0.000010945184,0.00000599798,0.0014569855],"genre_scores_gemma":[0.9701296,0.000013513819,0.028564878,0.00023172393,0.0007969276,0.000003642938,0.0000017340557,0.000008169538,0.00024979783],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99797916,0.00026584673,0.00068268174,0.00014194887,0.0007629485,0.000167396],"domain_scores_gemma":[0.9954327,0.0011258645,0.00047286728,0.000041109586,0.0028873722,0.000040139068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001648451,0.00011153396,0.0002876292,0.00032901627,0.00014135845,0.000052093492,0.00029187257,0.000051393545,0.00003771357],"category_scores_gemma":[0.004159933,0.00010288476,0.00011161977,0.0002721444,0.00006919645,0.0005205135,0.000080110665,0.00018356371,0.0000061713613],"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":[0.00049808953,0.0009763211,0.4612355,0.00007251294,0.001487698,0.00002738847,0.3915483,0.015565663,0.08830308,0.029492114,0.0017541717,0.009039187],"study_design_scores_gemma":[0.0035226569,0.00072215265,0.515481,0.0037717742,0.00019671819,0.00011026739,0.4328565,0.023423068,0.0056482153,0.008164963,0.004906434,0.0011962566],"about_ca_topic_score_codex":0.001853468,"about_ca_topic_score_gemma":0.0015207926,"teacher_disagreement_score":0.08265487,"about_ca_system_score_codex":0.0005721112,"about_ca_system_score_gemma":0.00031861765,"threshold_uncertainty_score":0.49801287},"labels":[],"label_agreement":null},{"id":"W3211365142","doi":"10.1207/s15327574ijt0601_7","title":"Book Review","year":2006,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology","score_opus":0.25453380262319725,"score_gpt":0.41852446206679766,"score_spread":0.16399065944360042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211365142","genre_codex":"review","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":[0.03187361,0.74558914,0.00046633426,0.01967066,0.0053813993,0.00011196845,0.00000845641,0.000043807573,0.19685465],"genre_scores_gemma":[0.75916326,0.008472298,0.011906907,0.14630371,0.01259487,0.000030449919,0.000013018877,0.0000616227,0.061453857],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916375,0.00003391544,0.00040275528,0.000071590264,0.00023213879,0.00009584388],"domain_scores_gemma":[0.9990789,0.0001337445,0.00033349774,0.000048073223,0.00038007813,0.000025695126],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022560838,0.000062959625,0.00013295207,0.000040335795,0.000025841215,0.000014165092,0.0002596807,0.000024923142,0.0038648273],"category_scores_gemma":[0.00013921918,0.000043848017,0.0000857492,0.00006912563,0.000029884492,0.000067664834,0.000027340704,0.00014758379,0.00013306635],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017073373,0.00013724295,0.021072574,0.00000638765,0.000043452004,0.00032097215,0.000015715446,0.00000262402,0.00022981442,0.00033541062,0.92325246,0.05456625],"study_design_scores_gemma":[0.00035718852,0.00014184693,0.16286223,0.00066032074,0.00003378712,0.00097367977,0.000010699374,9.937405e-7,0.000020727832,0.0008049547,0.83405006,0.00008349004],"about_ca_topic_score_codex":0.000044095326,"about_ca_topic_score_gemma":6.042842e-7,"teacher_disagreement_score":0.7371168,"about_ca_system_score_codex":0.000022297827,"about_ca_system_score_gemma":0.0000064264386,"threshold_uncertainty_score":0.99704576},"labels":[],"label_agreement":null},{"id":"W4309375705","doi":"10.1080/15305058.2022.2070755","title":"Generating reading comprehension items using automated processes","year":2022,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reading comprehension; Blank; Comprehension; Computer science; Natural language processing; Test (biology); Reading (process); Artificial intelligence; Salient; Process (computing); Psychology; Linguistics","score_opus":0.08765853027184589,"score_gpt":0.32709880228236776,"score_spread":0.23944027201052187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309375705","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":[0.5951998,0.00013628384,0.40256312,0.0002968126,0.0014924753,0.00003197676,0.0000010094916,0.00011965565,0.00015884382],"genre_scores_gemma":[0.66590196,8.5328435e-7,0.33363432,0.00016115108,0.00028498285,7.9307415e-7,4.941603e-7,0.0000058066234,0.000009656284],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983812,0.00007503158,0.0005051853,0.00014861816,0.00075173756,0.00013823083],"domain_scores_gemma":[0.9980558,0.00029930336,0.000641939,0.0001052889,0.00085131737,0.000046321995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005836127,0.00008139356,0.00012181054,0.00023855116,0.00025171996,0.00020660441,0.0010265429,0.000014328671,0.0000100029865],"category_scores_gemma":[0.00080405927,0.00008133123,0.00004064087,0.00032416708,0.000009164601,0.0005792496,0.0005216599,0.00023933656,8.539359e-7],"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":[0.0000043629702,0.000032477004,0.0040154755,0.000009547412,0.000031946136,0.0002113772,0.0005286653,0.8961634,0.084030375,0.00029037747,0.00008881987,0.0145932],"study_design_scores_gemma":[0.0002036134,0.000046108762,0.00011910075,0.000109748515,0.0000042210227,0.0022549317,0.00008168027,0.99564403,0.00092286064,0.00031592415,0.00021480786,0.00008295094],"about_ca_topic_score_codex":0.000037553615,"about_ca_topic_score_gemma":5.0109963e-7,"teacher_disagreement_score":0.09948067,"about_ca_system_score_codex":0.00021256412,"about_ca_system_score_gemma":0.0002556347,"threshold_uncertainty_score":0.33165914},"labels":[],"label_agreement":null},{"id":"W4381282730","doi":"10.1080/15305058.2023.2214648","title":"The analysis of TIMSS 2015 data with confirmatory mixture item response theory: A multidimensional approach","year":2023,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Confirmatory factor analysis; Item response theory; Class (philosophy); Psychology; Mathematics education; Structural equation modeling; Polytomous Rasch model; Sample (material); Latent class model; Cognition; Psychometrics; Mathematics; Statistics; Developmental psychology; Artificial intelligence; Computer science","score_opus":0.5081435997123916,"score_gpt":0.5085350331339626,"score_spread":0.0003914334215709969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381282730","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":[0.9578756,0.0005268704,0.037371013,0.001953447,0.00093503855,0.00008875431,0.000114613424,0.00003172991,0.0011029046],"genre_scores_gemma":[0.9123429,0.000013579598,0.0869462,0.00009529054,0.0001748027,0.0000013261774,0.000012538021,0.000010670462,0.0004026938],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9944501,0.0012797137,0.0011205322,0.00028627974,0.0026693863,0.000194025],"domain_scores_gemma":[0.82178193,0.17244522,0.0020733268,0.00068253756,0.002922592,0.00009438432],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037527338,0.00012042111,0.0003883866,0.0015697938,0.00015949762,0.00017180992,0.0028594008,0.00004826943,0.000037223566],"category_scores_gemma":[0.30583423,0.00006046657,0.00014364024,0.0046470216,0.00018365483,0.0003067629,0.0005449347,0.0002884439,0.000007477617],"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":[0.007351219,0.0002952498,0.5579388,0.000010536371,0.007972754,0.0005736614,0.0017475827,0.075776376,0.009435109,0.0027783173,0.044806603,0.2913138],"study_design_scores_gemma":[0.0009233812,0.00018299477,0.6400357,0.000118250304,0.00034781746,0.00047577327,0.0037348736,0.34206203,0.00012537377,0.004025065,0.007783344,0.0001854002],"about_ca_topic_score_codex":0.000011928934,"about_ca_topic_score_gemma":0.0000024455971,"teacher_disagreement_score":0.2911284,"about_ca_system_score_codex":0.00003468797,"about_ca_system_score_gemma":0.00023000392,"threshold_uncertainty_score":0.9910681},"labels":[],"label_agreement":null},{"id":"W4391876290","doi":"10.1080/15305058.2024.2318424","title":"A meta-analysis of the relationship between Wonderlic test scores and school success","year":2024,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Psychometric Methodologies and Testing","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 Calgary; Wilfrid Laurier University","funders":"","keywords":"Psychology; Test (biology); Clinical psychology; Meta-analysis; Medicine; Internal medicine","score_opus":0.8254326103415369,"score_gpt":0.5486442116530132,"score_spread":0.2767883986885237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391876290","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":[0.98052114,0.0035948197,0.010405445,0.0033147368,0.00068664714,0.000054361502,0.00003829553,0.000014403066,0.0013701397],"genre_scores_gemma":[0.9845148,0.000003811748,0.0149031775,0.000062684994,0.00020517744,9.5627e-7,3.8437187e-7,0.000005459469,0.00030357228],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99639875,0.00033159947,0.0012515561,0.00020605193,0.0017040297,0.00010800832],"domain_scores_gemma":[0.6980101,0.2977378,0.0018104437,0.0003590336,0.0019530683,0.00012957447],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008293644,0.00009919257,0.0005317974,0.0017110944,0.00008821171,0.0004819253,0.0012287556,0.000043424203,0.00020535443],"category_scores_gemma":[0.39879394,0.00005089274,0.0006360447,0.0043281373,0.00010025034,0.00040376198,0.00022305833,0.00034442052,0.000004927601],"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":[0.000002372324,0.000008815602,0.98388916,0.000003232847,0.008704969,0.000010291997,0.00006588923,0.00068973104,0.00010723048,0.00034266966,0.0002173723,0.005958269],"study_design_scores_gemma":[0.00006650066,0.0000323046,0.9566522,0.00004321203,0.011085138,0.00006421448,0.000078799385,0.002732071,0.000048949096,0.029051013,0.000093914954,0.00005165529],"about_ca_topic_score_codex":0.000049620623,"about_ca_topic_score_gemma":0.00000721717,"teacher_disagreement_score":0.3905003,"about_ca_system_score_codex":0.000036617028,"about_ca_system_score_gemma":0.000121672,"threshold_uncertainty_score":0.60627025},"labels":[],"label_agreement":null},{"id":"W4400119116","doi":"10.1080/15305058.2024.2364174","title":"Can the dark core of personality be measured briefly, multidimensionally, and invariantly? The D25 measure","year":2024,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Personality Traits and Psychology","field":"Psychology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Measure (data warehouse); Psychology; Personality; Core (optical fiber); Cognitive psychology; Social psychology; Computer science; Data mining","score_opus":0.1511349496781008,"score_gpt":0.3789092397915193,"score_spread":0.22777429011341851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400119116","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":[0.90283483,0.0042010257,0.0003068491,0.07876394,0.0036297066,0.00015101822,0.00016716257,0.000023003828,0.009922464],"genre_scores_gemma":[0.99596727,0.000012942041,0.00067318877,0.00240746,0.0006793607,0.0000031818602,0.00000362925,0.000015725576,0.000237268],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980631,0.00025743688,0.00056003436,0.00020171537,0.00074173516,0.00017599974],"domain_scores_gemma":[0.99685824,0.0017434387,0.00036245096,0.00016633506,0.0007975019,0.000072055234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024477362,0.00014454464,0.00021216917,0.000101433674,0.00011600814,0.00008040852,0.00059161463,0.000083259,0.00025661677],"category_scores_gemma":[0.0009697941,0.00008112637,0.00015212038,0.00017475046,0.0003223156,0.000085847125,0.000070380425,0.00058073713,0.0000038744224],"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":[0.0021072042,0.0010998503,0.23759173,0.00018472213,0.01087515,0.002598187,0.08123536,0.0002559482,0.080233514,0.17543244,0.14657503,0.26181087],"study_design_scores_gemma":[0.0022380054,0.00048710877,0.9300282,0.0010706651,0.00037131482,0.013699671,0.0035248823,0.0014489212,0.00014852859,0.016511427,0.030085234,0.00038601368],"about_ca_topic_score_codex":0.000750357,"about_ca_topic_score_gemma":0.00017183242,"teacher_disagreement_score":0.6924365,"about_ca_system_score_codex":0.000045334255,"about_ca_system_score_gemma":0.00018855036,"threshold_uncertainty_score":0.33082375},"labels":[],"label_agreement":null}]}